Plan & spec
10,741 rows, by stacks then stars
2,010 of these skill files have been read, by 1,360 distinct authors, and what they tell an agent counted. What Plan & spec authors agree on, and what they forbid
justnau1020/claude-os/skills/workflow/exec-plan Skill
3★ repoExecute an execution plan document by orchestrating worktree agents, enforcing commit/merge/test gates, and tracking progress. Main agent stays lean -- all work delegated.
justnau1020/claude-os/skills/workflow/plan-features Skill
3★ repoGenerate execution plan documents for multi-team agent work. Analyzes file conflicts, builds dependency graphs, and produces structured plans that drive flawless parallel execution.
u9401066/template-is-all-you-need/.claude/skills/roadmap-updater Skill
3★ repoAuto-update ROADMAP.md status based on completed features. Triggers: RM, roadmap, 路線, 規劃, 完成功能, milestone, 里程碑, 路線圖, 計畫, plan, planning, 進度, progress, 功能完成, feature done, 待辦, todo, backlog.
soulmachine/skills/swe-workflow Skill
3★ repoOrchestrates the full five-stage flow from raw idea to shipped PR — grill-with-docs → to-prd → to-issues → triage → worktree+planning-with-files. Each stage answers one question (What do I want? / What does done look like? / What are the units of work? / What's actionable? / Build it). Use when the user has an idea but no spec yet, wants to plan a feature end-to-end, says "let's PRD this," asks "how do I start on this idea?", or grabs a ready-for-agent issue to implement.
adamlinscott/claude-skills/skills/goal-workflow Skill
3★ repoRun a settled implementation goal as a bounded autonomous build loop — lock the goal from the conversation and any docs written this session, front-load every decision, map the terrain, write a completion-invariant contract before any code, then loop (building with explicit Agent-tool fan-out, committing at intervals, verifying at milestones with fresh-eyes against the contract) until the invariants hold, and close out. Gated on a `--confirm` flag asserting the user has manually set ultracode effort and auto-accept mode (a skill can set neither); without the flag it stops, gives the setup steps, and offers two paths — a managed `--confirm` run, or a copy-pasteable `/goal` command that hands the work to native goal + workflow orchestration. An optional `--commit` flag (default off) enables commit-at-intervals and push-at-milestones in both the managed run and the generated command; without it, nothing is committed. Use when a plan is settled and you want Claude to implement it end-to-end on its own — typically after a planning skill — or whenever the user says goal-workflow.
adamlinscott/claude-skills/skills/ttp Skill
3★ repoShape user-facing output to be brief and direct — lead with the substance, keep the default answer short, and expand only when the user asks for detail. Leaves the user in control: Claude settles small, reversible, or already-decided points and proceeds, but routes high-impact calls (ADR-worthy, production, project shape, which features get built, infrastructure) to the user with enough context to decide. Only shapes prose written for the user to read; Claude's own reasoning, tool use, code, and planning are untouched. Invoke with /ttp; stays on until "stop ttp" or "normal mode".
EdytaKucharska/keel/v2-backlog/feature-approach Skill
3★ repoRecommends how to build a proposed feature — the simplest viable design, what to defer, what to prove first, build vs. buy, and what the feature implies for the rest of the system. Use this skill PROACTIVELY whenever the user describes a feature they want to build, asks "how should we build X", proposes adding functionality, drafts a feature spec, or mentions wanting to ship something new — even if they don't explicitly ask for a design memo. Common trigger phrases include "we want to add X", "how should we build a [feature]", "I want users to be able to X", "we're going to add notifications/search/onboarding/billing/etc.", "what's the right way to build X", "should we build our own X or use Y", "users are asking for X, how do we ship it". Also triggers when the user shares a PRD, feature spec, user story, or rough sketch of a new capability. Especially important to trigger when the user is non-technical and likely to under-scope, over-scope, or skip prove-first. Produces a structured feature design memo covering the smallest viable shape, what to defer, build-vs-buy, structural implications, prove-first checks, and an estimate the user can hand to an engineer or AI tool.
rashidee/co2-skills/skills/mockgen-shadcn Skill
3★ repoGenerate React + shadcn/ui mockup screens from PRD.md files for UI/UX human designer review. Creates a Vite + React 19 + TypeScript + shadcn/ui mockup application with admin dashboard layout (collapsible sidebar navigation, header with logo/notifications/locale/user menu, footer with copyright/version) using React Router v7 for client-side navigation, organized by user role in a mockup/ folder. The app is BUILT (npm run build) and its dist/ output is served by the SINGLE shared Mockup Hub at <root>/mockup — a zero-dependency Node.js server with a landing page listing every application and role (unclickable when not ready) and a configurable port (PORT env / mockup.config.json). The Vite dev server remains available for design iteration only. Input: application name (mandatory), version (mandatory), module (optional). Output: mockup/ folder in the application's context folder containing MOCKUP.html index page, mockup-manifest.json, Vite + React project files, layout components, shadcn/ui components, role-specific page components, and the built dist/ folder; plus the shared hub at <root>/mockup if not already present. Trigger on keywords: "generate mockup shadcn", "generate shadcn mockup", "create shadcn mockup screens", "shadcn UI mockup", "React mockup from user stories", "mockup from PRD.md shadcn", "generate shadcn screens", "create shadcn UI screens". Accepts application name and version as input (e.g., `/mockgen-shadcn hub_middleware v1.0.3`). Optionally accepts a module name to limit generation to screens for that module only (e.g., `/mockgen-shadcn hub_middleware v1.0.3 module:Location Information`). When module is specified, only page components for that module are generated/updated; layout components, sidebars, config files, and other module pages are left untouched (the manifest is updated and the app is rebuilt). Automatically excludes strikethrough (deprecated/removed) items.
rashidee/co2-skills/skills/mockgen-tailwind Skill
3★ repoGenerate HTML mockup screens from PRD.md files for UI/UX human designer review. Creates Alpine.js + HTMX mockup assets with admin dashboard layout (left sidebar navigation, header with logo/notifications/locale/user menu, footer with copyright/version) served as partials, organized by user role in a mockup/ folder. All mockups are served by the SINGLE shared Mockup Hub at <root>/mockup — a zero-dependency Node.js server with a landing page listing every application and role (unclickable when not ready) and a configurable port (PORT env / mockup.config.json). Input: application name (mandatory), version (mandatory), module (optional). Output: mockup/ folder in the application's context folder containing MOCKUP.html index page, mockup-manifest.json, partials/, and role-specific content subfolders (assets only — no per-app server); plus the shared hub at <root>/mockup if not already present. Trigger on keywords: "generate mockup", "generate mockups", "create mockup screens", "HTML mockup", "UI mockup from user stories", "mockup from PRD.md", "generate screens", "create UI screens". Accepts application name and version as input (e.g., `/mockgen-tailwind hub_middleware v1.0.3`). Optionally accepts a module name to limit generation to screens for that module only (e.g., `/mockgen-tailwind hub_middleware v1.0.3 module:Location Information`). When module is specified, only content files for that module are generated/updated (plus the manifest); partials, sidebars, the shared hub, and other module screens are left untouched. Automatically excludes strikethrough (deprecated/removed) items.
rashidee/co2-skills/skills/modelgen-nosql Skill
3★ repoExtract NoSQL document models from Agile user stories using Domain-Driven Design (DDD) principles. Produces Mermaid class diagrams showing document structure (embedded vs referenced), JSON schema examples per collection, and detailed model documentation per module. Use this skill whenever the user asks to extract a NoSQL module model, NoSQL document model, NoSQL schema, collection design, or document structure from user stories. Also trigger when the user provides user stories grouped by module and asks for NoSQL data modeling, document-oriented design, or embed-vs-reference analysis. Even if the user says "design my NoSQL collections" or "what documents do I need", this skill applies if the input contains structured Agile user stories with module groupings. Do NOT use this skill for RDBMS or relational schema extraction — use the modelgen-relational skill for that. Also trigger when the user says "update the model" or "upgrade the model" to incrementally evolve an existing NoSQL document model based on changes in PRD.md. Accepts an application name (mandatory), version (mandatory), and optional module argument (e.g., `/modelgen-nosql hub_middleware v1.0.3` or `/modelgen-nosql hub_middleware v1.0.3 module:Location Information`).
rashidee/co2-skills/skills/modelgen-relational Skill
3★ repoExtract module models from Agile user stories using Domain-Driven Design (DDD) principles. Produces ERD diagrams (Mermaid) and detailed model documentation per module. Use this skill whenever the user asks to extract a module model, data model, entity model, table design, schema design, or ERD from user stories. Also trigger when the user provides a set of user stories grouped by module and asks for entity/relationship analysis, database schema extraction, or DDD model generation. Even if the user says "analyze these stories" or "what entities do I need", this skill applies if the input contains structured Agile user stories with module groupings. Also trigger when the user says "update the model" or "upgrade the model" to incrementally evolve an existing module model based on changes in PRD.md. Accepts an application name (mandatory), version (mandatory), and optional module argument (e.g., `/modelgen-relational hub_middleware v1.0.3` or `/modelgen-relational hub_middleware v1.0.3 module:Location Information`).
rashidee/co2-skills/skills/specgen-flutter-riverpod Skill
3★ repoGenerate a detailed specification document for building a Flutter mobile application using Flutter 3.x (Dart 3.x), Riverpod 2.x for state management, Hive 2.x for local storage, Dio 5.x for REST API with smart retry, Firebase Messaging + flutter_local_notifications for push/event notifications, go_router 14.x for navigation, freezed 2.x + json_serializable for immutable models, and build_runner for code generation. The spec also covers cached_network_image, flutter_svg, pull_to_refresh, font_awesome_flutter, material_design_icons_flutter, intl, url_launcher, and flutter_native_splash. Authentication (Keycloak OAuth2/OIDC PKCE via flutter_appauth, local JWT, or none) and optional features (WebSocket, i18n via intl) are configurable based on user input. Standardized input: application name (mandatory), version (mandatory), module (optional). Use this skill whenever the user asks to create a spec, specification, blueprint, or technical design document for a new Flutter mobile application. Also trigger when the user says things like "spec out a new Flutter app", "design a Flutter app with Riverpod", "write a technical spec for my new mobile app", "scaffold spec for a Flutter Riverpod app", or any request for a specification document describing a Flutter + Riverpod + Dio + Hive application. Even if the user only mentions a subset of the stack (e.g., "Flutter mobile app" or "Flutter with Firebase notifications"), this skill likely applies — ask and confirm.
Specgen laravel eloquent bladehtmx
rashidee/co2-skills/skills/specgen-laravel-eloquent-bladehtmx Skill
3★ repoGenerate a detailed specification document for building a monolith Laravel 12 web application with server-rendered views (Blade), Tailwind CSS, Alpine.js, htmx, and nwidart/laravel-modules modular packaging. Database (MongoDB, PostgreSQL, MySQL, or none), authentication (Keycloak OAuth2 Client, Laravel Breeze form login, or none), scheduling (Laravel Task Scheduling + Queue Batching or none), messaging (RabbitMQ pub/sub or none), and internationalisation (multi-locale via Laravel's native translation system, or none) are configurable based on user input. Standardized input: application name (mandatory), version (mandatory), module (optional). Use this skill whenever the user asks to create a spec, specification, blueprint, or technical design document for a new Laravel web application with server-side rendering. Also trigger when the user says things like "spec out a new Laravel project", "design a Laravel web skeleton", "write a technical spec for my new Laravel app", "scaffold spec for a monolith Laravel app", or any request for a specification document describing a Laravel + Blade + Tailwind application. Even if the user only mentions a subset of the stack (e.g., "Laravel web app" or "Laravel with Mongo" or "Laravel with Keycloak"), this skill likely applies — ask and confirm.
rashidee/co2-skills/skills/specgen-node-cli-web Skill
3★ repoGenerate a detailed specification document for building a self-hosted Node.js web application distributed as a global npm CLI — installed via `npm install -g <app-name>`, started via `<app-name> start`, and accessed at `http://IP:PORT`. Single-process, local-first architecture: one Node 22 process serves both the REST API (Hono 4) and an embedded pre-built React 19 + Vite 6 SPA styled with Tailwind CSS v4 and vendored shadcn/ui. Data lives in per-user SQLite (better-sqlite3 + Drizzle ORM with shipped migrations, auto-migrated on start). Authentication is hand-rolled scrypt sessions with a first-run auto-generated admin, forced password change, and admin-managed users — no OAuth, no JWT, no email flows. CLI parsing via commander 12, bundling via tsup 8, monorepo via pnpm workspaces, Biome lint/format, Vitest + Playwright tests, mandatory built-binary smoke test. Standardized input: application name (mandatory), version (mandatory), module (optional). Use this skill whenever the user asks to create a spec, specification, blueprint, or technical design document for a self-hosted web app installed as a global CLI, a "local-first web tool", an "npm-installable web dashboard", a "CLI that serves a web UI", or a single-binary-style Node web application with an embedded frontend. Also trigger when the user says things like "spec out a self-hosted Node web app", "design an npm global CLI with a web interface", "write a spec for a local web tool installed with npm -g", or any request describing a web application that end users install on their own machine and open at an IP:PORT. Even if the user only mentions a subset (e.g., "Hono + SQLite app started from the terminal" or "CLI-launched dashboard"), this skill likely applies — ask and confirm.
rashidee/co2-skills/skills/specgen-react-mui Skill
3★ repoGenerate a detailed specification document for building a React SPA (Single Page Application) using React 19, TypeScript 5, Vite 6, Material UI (MUI) v6, React Router v7, TanStack Query v5, Zustand v5, React Hook Form v7, and Zod v3. Authentication (Keycloak OAuth2/OIDC PKCE, generic OIDC, or none), API integration (REST via Axios), and optional features (WebSocket, i18n, MUI X Data Grid, MUI X Charts) are configurable based on user input. Standardized input: application name (mandatory), version (mandatory), module (optional). Use this skill whenever the user asks to create a spec, specification, blueprint, or technical design document for a new React SPA or frontend application. Also trigger when the user says things like "spec out a new React project", "design a React SPA", "write a technical spec for my new frontend app", "scaffold spec for a React MUI app", or any request for a specification document describing a React + MUI + TypeScript application. Even if the user only mentions a subset of the stack (e.g., "React SPA" or "React with Keycloak" or "React MUI dashboard"), this skill likely applies — ask and confirm.
rashidee/co2-skills/skills/specgen-react-tailwind Skill
3★ repoGenerate a detailed specification document for building a React SPA (Single Page Application) using React 19, TypeScript 5, Vite 6, Tailwind CSS v3, Headless UI v2, Heroicons, React Router v7, TanStack Query v5, Zustand v5, React Hook Form v7, and Zod v3. Components are built utility-first with Tailwind and made accessible with Headless UI primitives (no component framework like MUI). Authentication (Keycloak OAuth2/OIDC PKCE, generic OIDC, or none), API integration (REST via Axios), and optional features (WebSocket, i18n, TanStack Table data grids, Recharts charts, react-day-picker date pickers, Tiptap rich text) are configurable based on user input. Standardized input: application name (mandatory), version (mandatory), module (optional). Use this skill whenever the user asks to create a spec, specification, blueprint, or technical design document for a new React SPA or frontend application styled with Tailwind CSS. Also trigger when the user says things like "spec out a new React Tailwind project", "design a React SPA with Tailwind", "write a technical spec for my new Tailwind frontend app", "scaffold spec for a React Tailwind app", or any request for a specification document describing a React + Tailwind + TypeScript application. Even if the user only mentions a subset of the stack (e.g., "React SPA with Tailwind" or "React + Headless UI" or "React Tailwind dashboard"), this skill likely applies — ask and confirm.
rashidee/co2-skills/skills/specgen-sdk-java Skill
3★ repoGenerate a detailed specification document for building a distributable Java SDK library packaged as a Multi-Release fat JAR via Maven. Targets JDK 8 baseline with JDK 11+ overlay classes (Multi-Release JAR) so a single artifact runs on every long-term JDK in production. The SDK is a thin client wrapping a remote REST API (and any additional protocols extracted from the PRD's Architecture Principle section). REST communication is implemented with OkHttp; everything else (JSON parsing, models, builders, retry, logging) is implemented with the JDK and in-house code — third-party dependencies are kept to the absolute minimum. Standardized input: application name (mandatory), version (mandatory), module (optional). Use this skill whenever the user asks to create a spec, specification, blueprint, or technical design document for a new Java SDK, Java client library, or REST API client wrapper. Also trigger when the user says things like "spec out a new Java SDK", "design a Java client library for my API", "write a technical spec for an SDK that wraps Swagger/OpenAPI", "scaffold spec for a fat-jar Java SDK", or any request describing a Java library that wraps a REST/HTTP API for downstream consumers. Even if the user only mentions a subset (e.g., "Java wrapper around my API", "client library for our microservice", "SDK that supports JDK 8 and 11"), this skill likely applies — ask and confirm.
rashidee/co2-skills/skills/specgen-spring-jpa-jtehtmx Skill
3★ repoGenerate a detailed specification document for building a monolith Spring Boot 3 web application with server-rendered views (JTE), Tailwind CSS, Alpine.js, htmx, and Spring Modulith packaging. Database (MongoDB, PostgreSQL, MySQL, or none), authentication (Keycloak OAuth2 Client, Spring Security form login, or none), scheduling (Quartz + Spring Batch or none), messaging (RabbitMQ pub/sub or none), and internationalisation (multi-locale via Spring's native MessageSource, or none) are configurable based on user input. Standardized input: application name (mandatory), version (mandatory), module (optional). Use this skill whenever the user asks to create a spec, specification, blueprint, or technical design document for a new Spring Boot web application with server-side rendering. Also trigger when the user says things like "spec out a new web project", "design a Spring Boot web skeleton", "write a technical spec for my new web app", "scaffold spec for a monolith web app", or any request for a specification document describing a Spring Boot + JTE + Tailwind application. Even if the user only mentions a subset of the stack (e.g., "Spring Boot web app" or "Spring web with Mongo" or "Spring Boot with Keycloak"), this skill likely applies — ask and confirm.
rashidee/co2-skills/skills/specgen-spring-jpa-restapi Skill
3★ repoGenerate a detailed specification document for building a Spring Boot 3 REST API application with Spring Modulith packaging. Database (MongoDB, PostgreSQL, MySQL, or none), authentication (Keycloak OAuth2 Resource Server, Spring Security JWT, or none), scheduling (Quartz + Spring Batch or none), and messaging (RabbitMQ pub/sub or none) are configurable based on user input. Standardized input: application name (mandatory), version (mandatory), module (optional). Use this skill whenever the user asks to create a spec, specification, blueprint, or technical design document for a new Spring Boot REST API application. Also trigger when the user says things like "spec out a new REST API project", "design a Spring Boot API skeleton", "write a technical spec for my new API", "scaffold spec for a REST API", or any request for a specification document describing a Spring Boot REST API application. Even if the user only mentions a subset of the stack (e.g., "Spring Boot API" or "Spring REST with MySQL" or "Spring Boot API with Keycloak"), this skill likely applies — ask and confirm.
rashidee/co2-skills/skills/specgen-ts-cli Skill
3★ repoGenerate a detailed specification document for building a distributable Node.js CLI application written in TypeScript. Uses Commander.js for command parsing, tsup for bundling, and @yao-pkg/pkg for cross-platform binary packaging (Windows, macOS, Linux). Interactive prompts (Inquirer.js), persistent user config (conf), project-level config (cosmiconfig), shell execution (execa), HTTP client (got), plugin system, and auto-update checking are configurable based on application needs. Standardized input: application name (mandatory), version (mandatory), command (optional). Use this skill whenever the user asks to create a spec, specification, blueprint, or technical design document for a new CLI tool, command-line application, terminal tool, or developer tool. Also trigger when the user says things like "spec out a new CLI", "design a TypeScript CLI", "write a technical spec for my CLI tool", "scaffold spec for a Node CLI", or any request describing a command-line application. Even if the user only mentions a subset (e.g., "CLI with config file support" or "distributable Node tool"), this skill likely applies — ask and confirm.
rashidee/co2-skills/skills/testgen-functional Skill
3★ repoGenerate Playwright E2E test plan and specification documents from project artifacts (user stories, module models, mockups, specifications). Produces a TEST_PLAN.md root summary and per-module TEST_SPEC.md files containing test scenarios, data seeding scripts, and cleanup scripts — all as detailed Markdown blueprints, not actual test code. Input: application name (mandatory), version (mandatory), module (optional). Output: TEST_PLAN.md + per-module TEST_SPEC.md files in the auto-resolved test output folder. Trigger on keywords: "generate test plan", "generate test spec", "create test specification", "E2E test plan", "Playwright test plan", "test plan from user stories", "test spec from PRD.md", "generate test scenarios", "create test blueprint". Accepts application name and version as input (e.g., `/testgen-functional hub_middleware v1.0.3`). Optionally accepts a module name to limit generation to test specs for that module only (e.g., `/testgen-functional hub_middleware v1.0.3 module:Location Information`). Automatically excludes strikethrough (deprecated/removed) items.
rashidee/co2-skills/skills/tracegen-matrix Skill
3★ repoRequirement-to-code traceability generator — links every PRD requirement ID (User Stories, Non-Functional Requirements, Constraints) and bug code from a module's SPEC.md to the source code that implements it, and writes a per-application context/TRACEABILITY.md matrix. Resolves links primarily from the in-source CO2 traceability comments written by conductor-feature-develop and conductor-defect (e.g. `Implements: USHM00003`, `Bug fixes: [BUG-024]`), with a name-based source-scan fallback, and OPTIONAL precision enrichment from the codebase-memory knowledge graph when that MCP server is installed. Works fully WITHOUT codebase-memory. Takes an application name (mandatory), with optional version and module filters. Use when the user asks to "generate traceability", "update the traceability matrix", "link requirements to code", "regenerate TRACEABILITY.md", or when invoked as a sub-step by the feature/defect conductors after code or bug-fix changes.
rashidee/co2-skills/skills/util-updprd Skill
3★ repoApply a free-form requirement change to the PRD.md files of a CO2 project. Takes a human-written prompt describing NEW requirements or updates to existing ones, analyzes the PRD.md of every custom application to determine which applications, modules and subsections (User Story, Non Functional Requirement, Constraint, Reference, Test) are impacted, and decides for each impacted item whether to ADD, CANCEL or MODIFY it. Automatically classifies the change complexity per application as major, minor or patch, computes the next semantic version, and writes the new/updated items under a NEW version tag layered on top of the existing versions in each PRD.md — never rewriting or deleting prior versions. Cancelled items are struck through in place and recorded in the new version. New items are tagged with unique IDs (via util-ustagger) and a CHANGELOG.md entry is appended per impacted application. Presents an impact plan for human confirmation before writing (skippable with `--auto-approve` for orchestrated runs). ALWAYS stops after updating the PRDs and hands back for human review — it never chains into conductor-feature-prepare / -develop / -defect or any generator skill. Trigger on keywords: "update PRD", "update the PRD", "add requirement", "new requirement", "change requirement", "update requirements", "add user story", "cancel user story", "modify user story", "add NFR", "add constraint", "requirement update", "bump PRD version", "new version of requirements", "apply this requirement", "we now need", "the client wants". Accepts a free-form change prompt as the main argument, with optional `application:<app>` and `module:<module>` scope filters (e.g., `/util-updprd "Add SSO login for all users"`, `/util-updprd "Corridor codes must be unique" application:hub_middleware`).
rashidee/co2-skills/skills/util-usanalyzer Skill
3★ repoAnalyze PRD.md files for quality issues: incomplete sentences, non-existent references, cross-module inconsistencies, contradictory requirements, duplicate roles, design system validation, architecture principle violations, and process flow coverage gaps. Validates bi-directional coverage between User Stories/NFRs and High Level Process Flows — detects modules not covered by any process flow and process flow steps not covered by any User Story or NFR. Adds inline [TODO] annotations directly into the PRD.md file for each issue found. Trigger on keywords: "analyze user story", "analyze user stories", "check user story quality", "validate user stories", "find user story issues", "audit user stories", "review user stories", "check requirements quality", "find inconsistencies", "find contradictions". Accepts an application name as input (e.g., `/util-usanalyzer mainapp`, `/util-usanalyzer "Main App"`).
rashidee/co2-skills/skills/util-ustagger Skill
3★ repoTag new items in PRD.md files with unique ID codes and validate no duplicate tags exist. Applies to PRD.md documents structured with module sections containing User Stories, Non Functional Requirements, Constraints, References, and Test instructions. Each top-level bullet item gets a unique 9-character code with category prefix, application initials, and running number (interval of 3). Trigger on keywords: "tag user story", "tag user stories", "fix user story tag", "fix user story tags", "add IDs to requirements", "tag items in PRD.md", "number the requirements", "add requirement codes", "validate tags", "check duplicate tags", "verify tagging completeness". Accepts an application name and version as input (e.g., `/util-ustagger hub_middleware v1.0.3`, `/util-ustagger "Hub Middleware" v1.0.3`).
shwetank/bettersense/plugin/skills/impact-audit Skill
no license3★ repoUse when a PM or team wants to stress-test whether their work is actually connected to something the business cares about. Runs before strategy-doc or prioritization-frameworks — it answers "are we even pointed at the right thing?" Trigger phrases include "are we doing the right work?", "I'm worried my team isn't driving real impact", "help me check if my team is aligned", "I'm worried about layoffs", or any moment of doubt about whether the team's work would survive scrutiny.
shwetank/bettersense/plugin/skills/model-migration-planner Skill
no license3★ repoUse when a new model version ships (or a current one is deprecated) and the user must decide whether and how to migrate a LIVE AI feature — "Claude X just came out, should we move?", "our model is being deprecated in 90 days", "the new model is cheaper, can we switch?", "plan the migration to [model]". Runs the checklist: inventory what's pinned to the old model, re-run evals before believing anything, revisit decision-log entries tied to the old version, re-baseline cost and latency, stage the rollout with rollback criteria. Distinct from ai-pm-frameworks (choosing a model for a NEW feature) and the-vendor-evaluator (choosing a provider).
shwetank/bettersense/plugin/skills/prioritization-frameworks Skill
no license3★ repoUse when the user is prioritizing a backlog, building a roadmap, cutting scope, or arguing about what to build next. Trigger phrases include "what should we build first?", "help me cut this list", "I need to defend my roadmap", "should we do X or Y?". Surfaces the right framework (RICE, ICE, WSJF, MoSCoW, Kano, Cost of Delay) for the situation and forces the underlying assumptions out into the open.
shwetank/bettersense/plugin/skills/report-career-architect Skill
no license3★ repoUse when designing or revisiting a 12–18 month growth plan for one of the user's direct reports. Trigger phrases include "build a growth plan for [report]", "what should [name]'s next year look like", "I want to architect [report]'s path to senior", "I'm prepping for promo cycle and [report] needs a plan", "let's think about [report]'s development". Distinct from `one-on-one-prep` (per-meeting agenda) and from `coaching-mode` (the conversational layer). This is the *planning* layer — turning observations from `stakeholder-reflect` into a structured arc with concrete experiences, owners, and check-in cadence.
shwetank/bettersense/plugin/skills/stakeholder-due Skill
no license3★ repoUse when the user wants to know which stakeholder reflections are overdue. Trigger phrases include "what's due", "who haven't I thought about lately", "what's on my plate this week for stakeholder reflection", "stakeholder check-in", or any Monday-morning planning moment. Scans `~/bettersense-work-reflections/`, computes which question × stakeholder pairs are overdue based on `suggested_freq` and last entry date, and outputs a prioritized list. Designed to be invoked on demand or fired on a weekly Desktop scheduled task (not cloud routines — those cannot access local files).
shwetank/bettersense/plugin/skills/stakeholder-manage Skill
no license3★ repoUse when the user wants to *change* something about an already-registered stakeholder — list them, edit role/background, re-categorize after a reorg, rename, archive (because they left), or delete. Trigger phrases include "list my stakeholders", "show all my reports", "Jill is my manager now", "move Jill to managing-up", "Draymond left the company", "archive [name]", "Jill changed her name to [...]", "update [name]'s role", "delete [name] — registered by mistake". Mirrors stakeholder data lifecycle without touching the reflection content. Composes with `stakeholder-register` (which handles add).
shwetank/bettersense/plugin/skills/stakeholder-reflect Skill
no license3★ repoUse when the user wants to reflect on a registered stakeholder — a manager, peer, direct report, or team — and capture the insight to a durable file. Trigger phrases include "let me reflect on John", "I want to think through my 1:1 with Jill", "log my thoughts on the Client Delivery ABC team", "reflect on [name]". Loads the stakeholder file, picks 1–3 questions appropriate to the moment based on cadence and what hasn't been touched recently, guides the reflection, and writes the dated entry back.
shwetank/bettersense/plugin/skills/stakeholder-register Skill
no license3★ repoUse when the user wants to register a new stakeholder for ongoing reflection — a manager, peer, direct report, or team. Trigger phrases include "add a new stakeholder", "register Jill in managing-across", "I just got a new manager", "I'm now leading the X team", "let me set up reflection for [name]". Creates a persistent file at `~/bettersense-work-reflections/<category>/<slug>.md` that the `stakeholder-reflect`, `stakeholder-due`, and `stakeholder-synthesize` skills will use.
shwetank/bettersense/plugin/skills/stakeholder-synthesize Skill
no license3★ repoUse when the user wants to derive insight across accumulated stakeholder reflections — patterns, trends, contradictions, blind spots. Trigger phrases include "how is my managing-up overall", "summarize what I've learned about Jill this quarter", "before my performance review, what do I know about my reports", "what patterns do I see across my team leads", "give me a read on the Client Delivery ABC team". Reads one or many stakeholder files and produces synthesis with citations to specific dated entries — never claims a pattern without evidence.
shwetank/bettersense/plugin/skills/strategy-doc Skill
no license3★ repoUse to create or update a product/area strategy document — target problem, approach, personas, key metrics (3-5 SMART), 2-4 multi-month strategic tracks, and an explicit "not working on" section. Trigger phrases include "draft a strategy doc for [product/area]", "I need a strategy.md for the platform team", "interview me about my strategy", "update my strategy doc", "what's in my strategy doc". Lives at `~/bettersense-work-reflections/strategy/<area-slug>.md` and is read as an anchor by `the-spec-writer`, `prioritization-frameworks`, `metrics-design`, `product-pulse`, and `pulse-synthesize`. Inspired by Every.to's `/ce:strategy` pattern but composes more deeply with the rest of the bundle and supports multiple products/areas.
shwetank/bettersense/plugin/skills/tech-strategy-writer Skill
no license3★ repoUse when a senior IC (staff/principal engineer, architect, tech lead) needs to write a technical strategy or direction doc — where a system or domain should go over 12–24 months and why. Trigger phrases include "write a tech strategy for [domain]", "I need a technical direction doc", "our platform needs a north star doc", "help me write the tech vision for [area]". The staff+ artifact: turning engineering judgment into direction others can follow without you in the room. Distinct from strategy-doc (its product/business peer) and the-rfc-reviewer (reviewing one proposal). Saves to strategy/tech-<area>.md.
janewu77/jw-skills/jw-agenda/skills/jw-agenda-planning-sync Skill
no license3★ repoPlanning sync: check consistency across all planning levels (tasks/TODO, yearly, monthly, weekly, daily), list discrepancies, batch update after user confirmation. Triggers: '同步规划', '检查一致性', 'planning sync', '运行 planning-sync'.
janewu77/jw-skills/jw-agenda/skills/jw-agenda-weekly-plan Skill
no license3★ repoWeekly plan generator: create day-by-day breakdown from monthly goals and last week's carry-over. Triggers: '生成本周计划', '周规划', 'weekly plan', '运行 weekly-plan'.
endorphin-ai/claude-code-teams/go-react-team/.claude/skills/pm Skill
no license3★ repoProduct management skill for PRD writing and acceptance review. Use when creating requirements documents or validating deliverables against acceptance criteria.
Daisybastioned440/lite-research-agents/skills/research-proposal Skill
3★ repoDefines the structure and requirements for a research proposal.
The same file is in 1 other repository
frankaging/lite-research-agents/skills/research-proposal Skill
3★ repoDefines the structure and requirements for a research proposal.
The same file is in 1 other repository
Optim-Agent/optim-plans/skills/huge-plan Skill
3★ repoUse huge-plan for open-ended high-risk repo efforts needing websearch during brainstorming and refinement until convergence; exclude direct implementation-only, factual/explanation, trivial, or explicit no-plan requests.
Optim-Agent/optim-plans/skills/mini-plan Skill
3★ repoUse mini-plan for subtle low-risk repo changes needing one alignment question before execution; exclude direct implementation-only, factual/explanation, trivial, or explicit no-plan requests.
Optim-Agent/optim-plans/skills/plan Skill
3★ repoUse plan for normal repo changes needing bounded decisions, refinement, and high-priority review before execution; exclude direct implementation-only, factual/explanation, trivial, or explicit no-plan requests.
Optim-Agent/optim-plans/skills/small-plan Skill
3★ repoUse small-plan for small repo changes needing up to three intent checks and exactly one refinement round; exclude direct implementation-only, factual/explanation, trivial, or explicit no-plan requests.
harryl6798/vc-diligence-skill/skills/tech-brief-orchestrator Skill
no license3★ repoHigh-level technical "Editor-in-Chief" that coordinates specialized sub-agents to produce exhaustive, research-grade technical briefs.
shakeebshaan/claude-code-quant-skills/skills/strategy-critique Skill
3★ repoAdversarial review of a trading strategy. Claude acts as a skeptical prop-desk risk manager and tries to find why the strategy will blow up. Use when evaluating a new strategy idea, before scaling up capital, or when a backtest looks "too good."
TitusKirch/skills/skills/meta/validate-skills Skill
3★ repoValidates agent skills against the Agent Skills specification — one named skill, or every skill in a repo — and reports what fails and where. Drives skills-ref, the standard's reference validator, rather than reimplementing the checks; where skills-ref cannot be obtained it reports the spec tier as unverified rather than passing a weaker hand-check off as green. Reports spec violations (portability-breaking) separately from house-style deviations (a repo's own conventions) — distinct findings, never conflated. Names Anthropic's skill-creator as the adjacent quality tool it is, not a conformance validator. Use when the user wants to validate, check, lint or conformance-test a skill or SKILL.md, verify frontmatter against the spec, find skills that break the standard, or says things like "validate the skills", "check this skill against the spec", "is my SKILL.md valid", "Skills prüfen", "Skill validieren".
ronaknnathani/relay/skills/plan Skill
3★ repoTurn a clarified requirements artifact into a concrete, executable implementation plan — a decisive architecture blueprint and a phased build sequence with exact file paths. Use after requirements are pinned down (e.g. by `clarify`) and before writing code, whenever a multi-step change needs a design and a task breakdown. Its output feeds `implement`.
ronaknnathani/relay/skills/stack-ship Skill
3★ repoSkills to orchestrate coding agents to do long horizon tasks with little to no steering
mrzhangguoguo/oh-my-workbuddy/skills/pipeline Skill
3★ repoConfigurable orchestrator that sequences planning/execution/review stages as ordered WorkBuddy skill invocations with a task-list state and resume support. Use to run a repeatable multi-stage workflow (interview → plan → execute → review → QA). Triggers: 'run the pipeline', 'autopilot pipeline', 'sequence stages', 'stage orchestrator'.
mrzhangguoguo/oh-my-workbuddy/skills/plan Skill
3★ repoStrategic planning with optional interview, consensus (Planner→Architect→Critic), and review modes. Use to scope vague ideas, produce quality-gated work plans, or review an existing plan before implementation. Triggers: 'plan this', 'let's plan', 'ralplan', 'review this plan', 'plan --consensus', 'plan --review'.
mrzhangguoguo/oh-my-workbuddy/skills/prometheus-strict Skill
3★ repoClean-room interview-driven planner with three voices (Metis clarifies, Momus challenges, Oracle synthesizes), then hands off to ultragoal/team. Use for rigorous pre-execution planning when ambiguity is risky. Triggers: 'prometheus strict', 'strict plan', 'interview-driven plan', 'rigorous planning before execution'.
mrzhangguoguo/oh-my-workbuddy/skills/ralph-init Skill
3★ repoDeprecated. Do not invoke. Use ralph directly after PRD/test-spec planning is complete.
mrzhangguoguo/oh-my-workbuddy/skills/ralplan Skill
3★ repoAlias for plan --consensus. Triggers iterative Planner→Architect→Critic consensus planning with RALPLAN-DR structured deliberation. Use when you want multi-perspective sign-off on a plan before execution. Triggers: 'ralplan', 'consensus plan', 'plan --consensus'.
mrzhangguoguo/oh-my-workbuddy/skills/review Skill
3★ repoDeprecated. Do not invoke. Use code-review directly for implementation review, or plan --review only when reviewing an existing planning artifact.
tony-adamson/groundwork/codex/skills/solution-design Skill
no license3★ repoUse when explicitly asked for $solution-design to create SOLUTION.md for one concrete software change before implementation planning. Produces a minimal evidence-based design; does not write code or create an implementation plan.
The same file is in 1 other repository
tony-adamson/groundwork/skills/planf3 Skill
no license3★ repoCreates or executes a minimal Markdown implementation plan based on SOLUTION.md or an explicit request. Use only when the user explicitly asks: planning or Build Plan. No presentation artifacts and no future-proof architecture.
bowtiefunnel/bowtie-funnel-Labs/skills/pick-gtm-agent-pattern Skill
3★ repoUse when planning a new GTM AI agent, turning an existing GTM workflow into an agent, or auditing a GTM agent for over-engineering — before an architecture is settled or a spec is written. Anchors the choice against the 46-agent Bowtie Funnel Model Switchboard fleet. Triggers on "plan this agent", "what pattern should this GTM agent use", "make this workflow an agent", "should this be an agent", "rebuild X agent", or "is this over-engineered".
protosphinx/sphinxstack/skills/exam-prep-plan Skill
3★ repoBuild a dated plan for a real upcoming exam. Then run quiz sessions that find and track the weak spots. Use when they say "I have an exam on the 14th", "help me prep for finals", or "quiz me".