Plan & spec
10,699 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
markjoshwel/skills/task-planning-majo Skill
no license0★ repoTask planning workflow for complex work. Load this skill when the user says things like "this is complex", "I need a plan", "break this down", or when a task involves multiple files, unclear requirements, or significant architecture decisions. Triggers include multi-step implementations, refactoring across codebase, feature design, or when the approach is ambiguous.
guillevc/skills/skills/living-spec/init-spec Skill
0★ repoBootstrap a living spec on an existing codebase by extracting the terms and decisions already baked into the code. Run once when adopting living-spec. User-invoked.
itssungho17/ssdam/templetes/new-task Skill
no license0★ repoSecond skill in the SSDAM pipeline. Transforms one task entry from `mission-spec.yaml` into a fully specified `task-spec.TSK-NNN.yaml` that includes the task's contracts, evaluation criteria, and execution plan.
gologo13/agent-skills/skills/roadmap Skill
0★ repoAnalyze the codebase and generate a visual roadmap of potential features and improvements; keywords: mermaid, diagram, performance, roadmap. Use only on explicit request; skip in routine implementation discussions.
nicoladevera/pm-agent-kit/.claude/skills/discovery-plan Skill
0★ repoPlans what to learn before committing — assumption mapping, method selection, evidence thresholds, sequencing. Use when asked to "plan discovery", "what should we research first", "create a discovery plan", "map our assumptions", or "help us decide what to test".
nicoladevera/pm-agent-kit/.claude/skills/doc-review Skill
0★ repoReviews PM documents against quality criteria and produces actionable feedback with severity ratings. Use when asked to "review this PRD", "give feedback on this doc", "evaluate this spec", "review this ticket", or "assess this project brief". Detects document type automatically.
nicoladevera/pm-agent-kit/.claude/skills/meeting-brief Skill
0★ repoPrepares a pre-meeting brief with agenda, decisions to make, and attendee context. Use when asked to "prep for this meeting", "create a meeting brief", "write an agenda", or "help me prepare for [meeting name]".
nicoladevera/pm-agent-kit/.claude/skills/prd-draft Skill
0★ repoDrafts a full PRD from rough input — problem statements, meeting notes, bullets, or partial drafts. Use when asked to "write a PRD", "draft a product requirements doc", "turn these notes into a PRD", or "structure this problem as a PRD". Applies quality criteria from doc-review automatically.
nicoladevera/pm-agent-kit/.claude/skills/roadmap-prioritization Skill
0★ repoCompares initiative candidates, sequences work, and produces prioritization rationale with explicit trade-offs. Use when asked to "prioritize the roadmap", "help me decide what to build next", "compare these initiatives", "sequence our work", or "roadmap planning".
nicoladevera/pm-agent-kit/.claude/skills/sprint-plan Skill
0★ repoAnalyzes backlog health or drafts a sprint plan with goals, capacity math, and story selection. Use when asked to "plan the sprint", "analyze the backlog", "create a sprint plan", "help with sprint planning", or "select stories for the sprint".
scaccogatto/minimalist-entrepreneur/skills/marketing-plan Skill
0★ repoCreate a minimalist marketing plan focused on building an audience through content, not ads. Use when someone has product-market fit (~100 customers) and wants to scale with marketing, or needs a content strategy. Also use when the user mentions "marketing plan," "content marketing," "build in public," "social media strategy," "email list," "audience building," or "organic growth." For early sales (pre-100 customers), see first-customers. For sustainable growth decisions, see grow-sustainably.
abijith-suresh/skills/skills/grill-me Skill
0★ repoInterview the user relentlessly about a plan or design until shared understanding is reached, resolving each branch of the decision tree one question at a time. Use only when the user explicitly invokes the grill-me skill. Do not trigger from ordinary planning or design requests.
abijith-suresh/skills/skills/plan Skill
0★ repoPresents a concrete implementation plan in chat based on a decisions summary. Use only when the user explicitly invokes the plan skill. Does not explore the codebase or ask clarifying questions. Do not trigger from ordinary planning requests.
vijpatel7/favorite_skills_and_plugins/.agents/skills/prd Skill
0★ repoGenerate a Product Requirements Document (PRD) for a new feature. Use when planning a feature, starting a new project, or when asked to create a PRD. Triggers on: create a prd, write prd for, plan this feature, requirements for, spec out.
The same file is in 1 other repository
2sem/mobile-team-skills/plugins/mobile-team-skills/skills/ios-design-spec Skill
no license0★ repoQuick HIG audit, SwiftUI component selection, and accessibility check for simple iOS UI questions. Use on main agent for lightweight design decisions. Escalate to designer subagent for full screen design, navigation architecture, or complex interaction design.
2sem/mobile-team-skills/skills/appstore-screenshot-designer Skill
no license0★ repoUse when planning or generating App Store screenshots for an iOS app listing, including slot order, overlay copy, screenshot prompts, device-safe layouts, localization, or a creative brief; escalate when final visual polish or full ASO strategy is needed.
2sem/mobile-team-skills/skills/ios-design-spec Skill
no license0★ repoQuick HIG audit, SwiftUI component selection, and accessibility check for simple iOS UI questions. Use on main agent for lightweight design decisions. Escalate to designer subagent for full screen design, navigation architecture, or complex interaction design.
bryanp/agent-skills/code/impl/plan Skill
no license0★ repoDocument an implementation plan based on given context
LaProgrammerie/ai-engineering-core/skills/planning Skill
0★ repoTurn a goal into a structured plan suitable for requirements/design/tasks workflows: scoped decomposition, dependencies, risks, and explicit non-goals.
calvyntwh/karu-custom-skills/skills/pareto-principle Skill
0★ repoStrategic Prioritization using the 80/20 Rule. Optimization of Scope. Use when planning tasks, managing feature creep, or maximizing ROI.
uncfreak1255-code/sawyer-skills-legacy/.claude/skills/autonomous-agents Skill
no license0★ repoAutonomous agents are AI systems that can independently decompose goals, plan actions, execute tools, and self-correct without constant human guidance. The challenge isn't making them capable - it's making them reliable. Every extra decision multiplies failure probability. This skill covers agent loops (ReAct, Plan-Execute), goal decomposition, reflection patterns, and production reliability. Key insight: compounding error rates kill autonomous agents. A 95% success rate per step drops to 60% b
The same file is in 3 other repositories
uncfreak1255-code/sawyer-skills-legacy/.claude/skills/content-strategy Skill
no license0★ repoWhen the user wants to plan a content strategy, decide what content to create, or figure out what topics to cover. Also use when the user mentions "content strategy," "what should I write about," "content ideas," "blog strategy," "topic clusters," or "content planning." For writing individual pieces, see copywriting. For SEO-specific audits, see seo-audit.
The same file is in 1 other repository
arendon1/agent-skills/process/check Skill
0★ repoRead-only drift detector. Diffs the plan artifacts against the current code and reports violations grouped by severity. Writes nothing — suggests remedies but never invokes them. Use when checking drift, auditing the spec, verifying invariants hold, or when the user says "check drift", "audit the spec", "does the code still match", "spec vs code", "is the plan still accurate".
arendon1/agent-skills/process/dispatch Skill
0★ repoDispatch fresh subagents for independent tasks, with two-stage review (spec compliance, then code quality). Use when a plan has independent tasks that can run in parallel, or when a task is large enough to benefit from an isolated subagent. Use when the user says "parallel", "dispatch", "subagent", or when the plan has independent tasks, or when a task is large enough to benefit from isolation.
arendon1/agent-skills/process/grill Skill
0★ repoSharpen a fuzzy idea into requirements before spec. Calibrated interrogation: one question at a time, recommend an answer, land each in PRD.md or CONTEXT.md. Creates the plan folder. The cheapest place to kill a bad idea is before a task exists. Use when the user has a vague idea, says "grill me", "stress-test this", "challenge my plan", "interview me", or before designing anything non-trivial.
arendon1/agent-skills/process/lessons Skill
0★ repoBug to spec protocol. When a bug is found or a test fails during build, trace the root cause, decide whether a new invariant would catch recurrence, and append a lesson to the active plan's LESSONS.md. This is the reflex that stops classes of bugs from recurring. Use when a test fails, a bug is reported, a post-mortem is run, or a build verification fails.
arendon1/agent-skills/process/plan Skill
0★ repoBreak a PRD/ARD/SPEC into an implementation plan of vertical-slice tasks. Each task cites the invariants and interfaces it touches, names the test that proves it, and has a status cell. Sole mutator of PLAN.md in the active plan. Use when ready to break requirements into tasks, after grill/design/spec and before build, or when the user says "plan this", "break this down", "tasks", "what's the plan".
arendon1/agent-skills/process/review Skill
0★ repoAdversarial senior review of the plan before build, or of the code after build. Constructs a skeptical reviewer anchored to the codebase, RESEARCH.md, and live best-practice, then tries to REFUTE — not rubber-stamp. Every finding cites evidence. Ends in a go/no-go gate. Use when reviewing high-blast-radius work before build, or reviewing the diff after build, or when the user says "review the spec", "red-team this", "is this sound", "senior review".
arendon1/agent-skills/process/spec Skill
0★ repoDetailed technical specification. Turn a PRD/ARD into a precise SPEC.md: exact schemas, algorithms, data shapes, edge cases, acceptance criteria. Sole mutator of SPEC.md in the active plan. Has NEW / AMEND / DISTILL modes. Use when the objective needs more detail than the ARD before planning, after design, or when the user says "spec this", "detailed spec", "specify the behavior".
arendon1/agent-skills/process/triage Skill
0★ repoMove issues through a triage state machine: from raw inbox to labeled, scoped, and ready for planning. Define triage roles/labels, apply them consistently, and surface what is ready to become a plan. Use when managing a backlog of issues or tickets before they become plans, or when the user says "triage", "go through issues", "organize the backlog", "what should I work on", "prioritize issues".
arendon1/agent-skills/utility/caveman Skill
0★ repoCompressed English encoding for plan artifacts and spec-adjacent prose. Cuts tokens ~75% vs prose while staying readable. Applies to PRD.md, ARD.md, SPEC.md, PLAN.md, LESSONS.md, RESEARCH.md, CONTEXT.md. Use when writing to a plan artifact, spec-adjacent prose, or when the user says "caveman", "compress this", "be brief", "write to PLAN.md".
appalize/aso-skills/skills/monetization-strategy Skill
0★ repoWhen the user wants to design or optimize their app's monetization — pricing, paywalls, subscriptions, or in-app purchases. Also use when the user mentions "pricing", "paywall", "subscription", "IAP", "how to monetize", "revenue optimization", "free trial", or "conversion to paid". For retention impact, see retention-optimization. For competitive pricing, see competitor-analysis.
The same file is in 2 other repositories
appalize/aso-skills/skills/rating-prompt-strategy Skill
0★ repoWhen the user wants to improve their app's star rating, increase ratings volume, optimize when and how they prompt users for a review, or recover from a bad rating period. Use when the user mentions "app rating", "star rating", "review prompt", "SKStoreReviewRequest", "In-App Review API", "ask for review", "low rating", "rating drop", "get more reviews", or "recover from 1-star". For responding to reviews, see review-management. For overall ASO health, see aso-audit.
The same file is in 2 other repositories
andrefabricio/prodotypor/files/.claude/skills/03-prd Skill
0★ repoStep 3 of 8 — PRD creation. Produces Product Requirements Documents with user stories, acceptance criteria, and success metrics. Sub-commands: [continue] resume, [status] check progress, [update] force status refresh.
andrefabricio/prodotypor/files/.claude/skills/05-design-doc Skill
0★ repoStep 5 of 8 — Design document creation. Produces the authoritative visual identity and design system specification from PRDs and inspiration research. Sub-commands: [continue] resume, [status] check progress, [update] force status refresh.
andrefabricio/prodotypor/files/.claude/skills/06-design-plan Skill
0★ repoStep 6 of 8 — Design plan creation. Produces a Figma construction plan with screen inventory, batch organization, frame tree specs, and token sync tracking. Sub-commands: [continue] resume, [status] check progress, [update] force status refresh.
SpencerGoss/agent-engineering/spec-driven-dev Skill
0★ repoUse when about to build or implement a specific feature with clear scope — before writing implementation code. Trigger on: "implement [feature]", "build [feature]", "add [feature]", "create a system that [does X]", "planning session for [feature]", or an explicit feature request with defined scope. NOT for: vague "let's work on X", simple additions, config changes, bug fixes, or exploratory discussion.
SpencerGoss/agent-engineering/tdd-workflow Skill
0★ repoUse when a spec or plan exists and it's time to write code — or when fixing a bug. Trigger on: "fix this bug", "write tests for", "write a function that", "create a module", "the spec is ready, let's implement", or any request to write working code when the WHAT is already clear. The hard gate: no implementation before a failing test exists.
rawgroundbeef/skills/prd Skill
no license0★ repoCreate a PRD through user interview, codebase exploration, and module design, then output as a markdown file. Use when user wants to write a PRD, create a product requirements document, plan a new feature, or scope out work before implementation. Triggers on "write a prd", "create a prd", "let's plan this feature", "scope this out", "product requirements", or any request to formalize feature planning into a document.
rawgroundbeef/skills/slice Skill
no license0★ repoVertical-slice planning pipeline that turns rough requirements into slice-local discovery, decisions, UAT, PRD, follow-ups, and a bootstrap prompt before implementation. Use when starting feature work, shaping a vertical slice, converting rough requirements into acceptance criteria, or preparing a fresh-context agent to implement from durable artifacts.
GustavoAlecio/claude-setup/skills/plan Skill
0★ repoEtapa 2 do Fluxo Smart — gera plano tecnico detalhado baseado na especificacao aprovada
Backlog prioritization assistant
sisodiabhumca/agent-skills/skills/backlog-prioritization-assistant Skill
0★ repoVendor-neutral skill to prioritize a backlog using configurable scoring (RICE/WSJF-style) and produce a ranked list with rationale.
sisodiabhumca/agent-skills/skills/cache-invalidation-planner Skill
0★ repoVendor-neutral skill to plan cache invalidation strategies for high-risk data updates.
Capacity planning signal analyzer
sisodiabhumca/agent-skills/skills/capacity-planning-signal-analyzer Skill
0★ repoVendor-neutral skill to synthesize utilization trends and forecast capacity risks for platform teams.
Data retention enforcement planner
sisodiabhumca/agent-skills/skills/data-retention-enforcement-planner Skill
0★ repoVendor-neutral skill to plan retention enforcement jobs with legal hold and deletion safeguards.
sisodiabhumca/agent-skills/skills/feature-flag-cleanup-planner Skill
0★ repoVendor-neutral skill to prioritize feature flags for cleanup using simple heuristics and produce a deprecation plan.
sisodiabhumca/agent-skills/skills/feature-flag-rollout-planner Skill
0★ repoVendor-neutral skill to generate a staged feature-flag rollout plan (phases, metrics, guardrails, rollback criteria) from feature context and risk inputs.
sisodiabhumca/agent-skills/skills/growth-experiment-planner Skill
0★ repoUse when planning A/B tests in LaunchDarkly, Optimizely, or similar platforms. Sizes the experiment (sample size, MDE, runtime), drafts hypothesis + success metrics + guardrails, and produces a launch checklist + rollback plan.
sisodiabhumca/agent-skills/skills/roadmap-dependency-heatmap Skill
0★ repoVendor-neutral skill to map roadmap dependencies and surface delivery risk concentrations.
sisodiabhumca/agent-skills/skills/secrets-rotation-planner Skill
0★ repoVendor-neutral skill to plan credential rotations based on age, exposure, and dependency blast radius.
Vendor contract renewal planner
sisodiabhumca/agent-skills/skills/vendor-contract-renewal-planner Skill
0★ repoVendor-neutral skill to prioritize upcoming vendor renewals from contract metadata and usage signals.
rynhardt-potgieter/sprint_workflow/plugins/sprint-workflow/skills/linear-sprint-planning Skill
0★ repoLinear MCP integration patterns — issue taxonomy (Epic/Task labels), Milestone-based sprint grouping, status lifecycle, label definitions, query patterns, creation patterns, retry handling, and team/project discovery. Use this skill when sprint tracking is routed through Linear instead of markdown files.
scribeless/skills/skills/scribeless-campaign-planner Skill
0★ repoPlan Scribeless handwritten direct mail campaigns for customer retention, acquisition, ABM, real estate, financial services, nonprofit, home services, ecommerce, and other business use cases. Use when a user wants help choosing a campaign audience, message, product, delivery method, personalization variables, Smart QR tracking, or campaign success criteria before building in Scribeless.
AnotherDaniel/tsfagent/.agents/skills/specification-writer Skill
0★ repoWrite and maintain OpenFastTrace (OFT) requirements specifications in markdown. Use when: creating new requirements, adding requirements to specification documents, reviewing requirement format, generating req~ identifiers, setting Needs/Depends tracing directives. Keywords: requirement, specification, OFT, OpenFastTrace, req~, BCP14, RFC 2119, tracing.
shuakami/paperchart/skills/critical-path Skill
0★ repoRender a Gantt-style horizontal timeline for a network or load waterfall, with named milestone markers (DOMContentLoaded, user interaction, etc.) and two-colour bars that separate critical-path resources from deferred ones. Use when a technical blog post needs to explain a first-load network waterfall or an asset loading strategy.
ploteddie-bit/skills/content-strategy Skill
no license0★ repoBuild and execute a content marketing strategy for a solopreneur business. Use when planning what content to create, deciding on content formats and channels, building a content calendar, measuring content performance, or systematizing content production. Covers audience research for content, content pillars, distribution strategy, repurposing workflows, and metrics. Trigger on "content strategy", "content marketing", "what content should I create", "content plan", "content calendar", "content ideas", "content distribution", "grow through content".
MAHDTech/agent-skills/skills/deprecated/plan-before-coding Skill
0★ repoIntercepts requests to ensure the AI agent and human work back and forth to create an implementation plan before diving into code. Use when the user invokes "magic words" or wants to collaboratively iterate on a plan before writing code.
MAHDTech/agent-skills/skills/planning/store-plan Skill
0★ repoCapture the current conversation's plan, decisions, and action items into a structured, reviewable markdown file in the project's plans/ directory.
MAHDTech/agent-skills/skills/planning/to-spec Skill
0★ repoTurn the current conversation into a spec (sometimes called a PRD) and publish it to your project's issue tracker — no interview, just synthesis of what you have already discussed.
MAHDTech/agent-skills/skills/planning/to-tickets Skill
0★ repoBreak a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, and publish them to your project's issue tracker — as one file per ticket locally, or as native blocking links on a real tracker.