agentsclimarketplace

Engineering

98,276 rows, by stacks then stars

  • Skill package

    alpiex1336-code/skill-package Skill

    1★

    **MANDATORY RUNTIME ORCHESTRATION:** For product-making/changing work, pass **NON-NEGOTIABLE EXECUTION GATES** before **Implement**-phase artifact writes—invoke **runtime subagents** via **Task tool** (or equivalent delegation) for **Orchestra wave**s; **N > 1** **composed role label**s per wave; **one runtime subagent per Work Filter–accepted Quintessence row** at Implement when tooling allows. **Simulated fallback** when Task/delegation is unavailable—not the default. **In-session wave ledger** required before Implement on thorough/deep-upgrade runs—not deferred to the final reply. **Execution gate** discipline applies default-on; map the same workflow to any artifact in scope (product, code, docs, policy, research, planning, governance, or this skill package). **Default-on** means use for every turn; scale orchestra depth with **`improvement_mode`** and user scope—skip full orchestration only when the user explicitly requests a trivial single-step action where multi-role review adds no value. **Improvement mode selection:** resolve by intent before orchestration: when the user clearly signals **normal** (small fix, small talk, single concern) or **thorough** / **deep-upgrade** (whole-product, all-aspects, maximum optimization), choose that mode and scale the workflow accordingly; when product-making/changing intent is present and the mode cannot be identified, **ask once and wait** for **normal** vs **thorough**. **Deep-upgrade intent** pins **thorough** and the **Deep-upgrade procedural tier**. **Quintessence pipeline:** sample many composed roles across waves, **integrate** overlapping ideas and roles into **`theme_key`** quintessence rows, adopt via Work Filter, then **implement/verify** preferably with **subagents per quintessence theme**. Coordinates many subagents per run using composed two-part roles from the word banks (`[Slot A][Slot B]`); see **Execution contract** and [reference-execution-gates.md](reference-execution-gates.md). **Cursor / LLM skill:** same **Stochastic Role Orchestra** pattern for any assistant that reads this file. Expects **universal aspect-coverage** discipline—build a **target coverage set** per engagement (see **Lexicon**), then **bias** role draws toward **uncovered** aspect classes. Uses **word-bank priority tiers (P0 / P1 / P2)** so **`improvement_mode` = thorough** whole-product runs have a **session floor** of **P0 families** (see [reference-word-banks.md](reference-word-banks.md)). **`normal`** biases **incremental modification**; **`thorough`** authorizes **material reshaping** while preserving **north-star invariant**. Requires epistemic honesty (no invented context; anti-sycophancy). **Outward closure:** after honest saturation (**Workflow §8**), terminal replies stay decisive. **Voice:** professional register; avoid LLM-default “AI voice.” **Skill-targeting requests** use **Recursive self-application**. Triggers include “essential fixes only,” “surgical,” “full product pass,” “**thorough** pass,” “multi-agent review,” “orchestrated review,” **mature product iteration**, greenfield/brownfield maturity passes. **Supersedes** informal fixed job-title maturity loops by mapping concerns onto **composed roles** + depth references—stricter anti–single-voice discipline.

  • Apply tdd loop en

    roebi/sw-dev-agent-framework/skills/apply-tdd-loop-en Skill

    no license1★ repo

    Applies the Test-Driven Development (TDD) cycle as an agentic loop of RED -> GREEN -> REFACTOR iterations until all requirements are covered or all existing code paths are tested. Use when a user or agent wants to write code strictly test-first, add missing tests to existing code, or drive a full TDD session for a module, class, or function. Activate for trigger phrases like: "apply TDD", "write this test-first", "do a TDD loop", "TDD cycle for", "drive TDD on", "red green refactor", or "add tests then implement".

  • Apertis api

    apertis-ai/apertis-skills/skills/apertis-api Skill

    no license1★ repo

    Use Apertis API to access 500+ AI models with OpenAI-compatible SDK. Covers authentication, endpoints, popular model families, web search (:web suffix), the Vercel AI SDK provider, and MCP server setup.

  • Wiggly repo builder

    smsheik1/wiggly/.agents/skills/wiggly-repo-builder Skill

    no license1★ repo

    Build, test, package, and refine a Wiggly Repo: an agent-operated image or video Format kit with an official runtime, contracts, assets, BYOK requirements, validation, inspection, and final outputs. Use when creating a Wiggly Repo from a reference or format idea, turning a prototype into a reusable agent package, testing whether a fresh agent can operate a Format, or updating the shared Wiggly Repo standard after a real run.

  • Winguictl

    easyteacher/winguictl Skill

    no license1★

    Windows desktop automation CLI. Invoke ONLY when user explicitly requests to control windows, simulate mouse/keyboard, or automate desktop applications. Do NOT proactively suggest using this skill.

  • Wktrees

    dsisnero/wktrees.cr/skills/wktrees Skill

    1★ repo

    Guidance for wktrees (the `wktrees` CLI) — git worktree management, hooks, and config. Load when editing .config/wt.toml or ~/.config/worktrees/config.toml; adding, modifying, or debugging hooks; configuring commit message generation or command aliases; or troubleshooting wktrees behavior.

  • MGC Script Execution

    zkeviny/MGC-Blackbox/mgc_skill/MGC_Script_Execution Skill

    no license1★ repo

    Zero‑exposure script execution using MGC Blackbox. Store scripts encrypted, execute locally, AI never sees plaintext. Supports MCP/API/WebUI execution, internal credential calls, and script sealing.

  • Engineering figure table

    169884902hzl/engineering-paper-skills/skills/engineering-figure-table Skill

    1★ repo

    Plan, revise, audit, or polish figures, tables, captions, table notes, and visual evidence flow for English engineering conference or journal papers. Use when the user asks about figure responsibility, multi-panel layout, main-result tables, ablation tables, captions, table formatting, object/category naming consistency, page budget for visuals, or whether visuals support manuscript claims.

  • Shadcn component lock

    MonkeyUI-dev/shadcn-component-lock Skill

    1★

    Generates and maintains a `shadcn-component-lock.md` file at the project root that tells Vibe Coding agents which files in the shadcn UI directory are stock shadcn/ui primitives — reused across the project and NOT to be edited directly. Use this skill whenever the user runs `npx shadcn@latest add`, `init`, or `apply`; whenever new files appear under the project's shadcn `aliases.ui` directory; whenever the user asks to "lock", "freeze", "pin", "regenerate", "refresh", or "update" the shadcn component lockfile; or whenever a Vibe Coding agent (e.g. Cursor, Copilot, Codex, Claude Code) is about to modify a file under `components/ui` and needs to know whether it is safe to touch. Coordinates with the official `shadcn` skill from shadcn-ui/ui.

  • Git workflow lifecycle

    jjanuszczak/margo/skills/git-workflow-lifecycle Skill

    1★ repo

    Automate the end-to-end lifecycle of a feature branch, from submission (commit, push, PR) to cleanup (merge check, sync main, delete branch). Use when you have finished work on a branch or when a PR has been merged and you need to clean up.

  • Agent coding conventions

    ymy88/agent-coding-conventions Skill

    1★

    Conventions for writing code and using developer tools reliably as an AI coding agent. Use when judging how far to trust a code-intelligence / static-analysis / indexing tool's output (e.g. codegraph) — especially negative claims like "no callers", "no covering tests", "impact is only these files"; or when a design choice (factory vs public constructor, DI, reflection, dynamic dispatch) affects how legible the code is to an agent. Consult BEFORE trusting a tool's claim as fact, and BEFORE changing a design to satisfy a tool.

  • Automate ui flows

    workingclassbuddha/codexmaxxing/skills/automate-ui-flows Skill

    1★ repo

    Automate, inspect, and verify real UI flows in a browser. Use when Codex needs to open localhost or a web URL, click through an app, fill forms, reproduce UI bugs, verify browser behavior, capture screenshots, test responsive layouts, smoke-test Chrome extension side panels or popups, or produce UI evidence after frontend changes.

  • Mission control 3d visual regression

    MN755/Codex-Mission_Control/.codex/plugins/mission-control/skills/mission-control-3d-visual-regression Skill

    1★ repo

    Route 3D visual-regression and render-diff work through Mission Control with explicit evidence targets and scene-aware validation.

  • Engineering cost review

    choegyumin/agent-skills/skills/engineering-cost-review Skill

    no license1★ repo

    Use when reviewing a blueprint (PRD, spec, implementation plan, design/architecture doc, or product scope and technical decisions from the current session) right after it is written or before implementation, to check whether its implementation cost is economical and rational. Not for reviewing already-implemented code.

  • Duckeighty doctor

    mackee/duckeighty/skills/duckeighty-doctor Skill

    1★ repo

    Diagnose whether the duckeighty local HTTPS ingress is correctly set up on this host. Checks the shared_ingress Docker network, traefik and dnsmasq containers, the macOS /etc/resolver entry, local CA trust, DNS resolution for *.duckeighty.test, and HTTPS reachability of traefik. Produces a checklist and the one command needed to fix whatever failed. Does not mutate any state. TRIGGER: the user reports that a *.duckeighty.test URL returns 404, NXDOMAIN, a TLS error, or connection refused; asks to check whether duckeighty is running; asks to debug the ingress; or is about to use the duckeighty-integrate skill and wants to confirm the stack is up first. SKIP: issues unrelated to the ingress path (e.g. the user is debugging application logic, not routing / DNS / TLS).

  • Spring liquibase migration

    JavoxirJava/spring-liquibase-migration Skill

    no license1★

    Use this skill when adding, generating, reviewing, or fixing Liquibase database migrations in Spring Boot projects. It should configure Spring Boot Liquibase, create master changelog files, write safe YAML/XML/SQL changesets, add rollback blocks, use preconditions, follow existing changelog style, and avoid modifying already executed changesets.

  • Bootstrap agent docs

    gzb1128/skill-forge/plugins/agent-docs/skills/bootstrap-agent-docs Skill

    1★ repo

    Skill Forge: Claude Code plugin marketplace for agent harness docs, code quality workflows, and OpenCode customization.

  • Alerting sla

    almasumdev/awesome-mobile-observability-agent-skills/.github/skills/alerts/alerting-sla Skill

    no license1★ repo

    Define SLIs, SLOs, error budgets, and rollout halts for mobile apps, with multi-window burn-rate alerts. Use when formalizing reliability targets or gating staged releases.

  • Codebase onboarding check

    Agent-Hellboy/codebase-onboarding-check Skill

    1★

    Onboard quickly by reading design docs, plans, READMEs, or the codebase to extract key concepts, surface gaps, and generate comprehension checks with answer keys. Includes an adaptive proficiency probe with learning resources and persistent session memory so the user can resume onboarding where they left off. Use when a user wants help understanding a project, validating their grasp of the architecture, or creating a readiness plan before contributing code.

  • Shopvidi us skill

    Alpha-Park/shopvidi-us-skill Skill

    no license1★

    Automate ShopVidi US wholesale tasks via Rube MCP (Composio), including product scraping, bulk orders, and inventory tracking for Art Toys and Lifestyle Goods.

    The same file is in 1 other repository

  • Popup

    richard-kim-79/popup-skills/popup Skill

    1★ repo

    Create instant shareable web pages on popup2026.com — no login, no PIN, 30-second setup. Use when the user wants to make a "팝업 페이지", "공유 링크", "랜딩 페이지", "이벤트 안내", "링크 모음", host a raw HTML file, or host a PDF. Tools are reached via the Remote MCP server at https://popup2026.com/api/mcp.

  • Knowledge base

    jakebrownscombe/science-lab-AI-framework/knowledge_base Skill

    1★ repo

    A customizable framework for using LLMs in scientific workflows.

  • Vibe coding playbook

    ayi-ai/vibe-coding-playbook Skill

    1★

    A lightweight engineering workflow for turning an idea into a real, shippable product with an AI coding agent. Core = Karpathy's four coding disciplines (think before coding / simplicity first / surgical changes / goal-driven; battle-tested), plus an Explore→Plan→Build→Polish→Ship process, task tiers (skip the process for small changes, full process only for shipped products), and the "AI is an amplifier" mindset (good habits ×10, bad habits ×100; controlling complexity is still the human's job). For everyone: terse for engineers, explained for newcomers, no jargon dumps. Ships with a paste-in kickoff prompt, a drop-in .cursor/rules discipline file, and PRD/architecture/status doc templates. Use when building an app/product/website/tool from scratch with Cursor/Codex/Claude Code, when asked to set rules before coding, when worried about code rotting into a mess or the AI changing unrelated code on its own, when asked how to do "vibe coding", whether to write a PRD/architecture, how to start a new project, or when "amplifier / spaghetti code / minimal loop / surgical change / complexity / task tier" come up.

  • Arxiv monitor

    Moonweave-Research/groundcheck/arxiv-monitor Skill

    1★ repo

    Fetches new arXiv papers matching a research watchlist, scores relevance with LLM, and delivers a filtered daily digest. Invoke when the user wants to check new arXiv papers on a topic, set up a daily paper monitoring routine, asks 'what's new on arXiv about X?', or wants to scan recent preprints in their field. Also use as a Claude Code Routine template for scheduled daily briefings. Do NOT invoke for finding a specific known paper (use ref-verify) or for general web research.

  • Ts npm oxlint starter

    kongyo2/agent-primary-ts-starters/ts-npm-oxlint-starter Skill

    1★ repo

    Add Oxlint to a TypeScript npm project with agent-friendly defaults that focus error-level diagnostics on real bugs, silence stylistic noise, and emit output in oxlint's `agent` format for downstream LLM consumption. Use when bootstrapping a new TS project that needs linting, or when adding Oxlint to an existing TS npm project — even if the user doesn't explicitly say "oxlint" or "linter".

    The same file is in 1 other repository

  • Claude skill safe debug loop

    Shavy72/claude-skill-safe-debug-loop Skill

    1★

    Multi-session skill for the strategic remediation of a complex dashboard/app module that is already built but has too many bugs for an MVP launch. Triggers on "/safe-debug-loop", "/safe-debug-loop Phase 1", "/safe-debug-loop Phase 2", "clean this up", "sweep the bugs", "too many bugs", "module remediation", "dashboard remediation", "bug swamp", "too many bugs for beta", "can't launch", "MVP launch impossible", "module refactor", "systematic bug sweep", "iterative bug fixing", "from bug-mess to MVP" — plus the German aliases "sanieren", "durchkehren", "viele Bugs", "Modul-Sanierung", "Dashboard-Sanierung", "Bug-Sumpf", "zu viele Bugs für Beta", "kann nicht launchen", "MVP launch unmöglich". MANDATORY TRIGGER whenever a user describes a module that is live, has UI/UX plus program flow, BUT has too many bugs to launch. The skill orchestrates 2 MAX-effort Claude sessions: Phase 1 = fully autonomous researcher + detective cross-check (no code touched, bug-plan markdown only). Phase 2 = iterative one-bug-at-a-time loop with an explain-it-to-a-12-year-old step, an isolated smoke test, and cleanup. Use this AGGRESSIVELY whenever a user shows signs of "module built but stuck in a bug mess".

  • Loopify bootstrap

    AndreRatzenberger/loopify/plugins/loopify/skills/loopify-bootstrap Skill

    1★ repo

    Use when seeding a repository with loop materials such as a goal prompt, Loop Contract, quality gate, trace template, acceptance checklist, and test skeletons.

  • Flight monitor agent

    xunyuAI/skills/flight-monitor-agent Skill

    no license1★ repo

    机票实时查价 Skill:RollingGo 查价、精简/全量穷举、暖色 HTML 分页报告。 用户说「查机票」「穷举搜索」「RollingGo 查价」「国庆特价」「开口程」「东南亚/日本/菲律宾机票」时使用。 适配 Cursor、Claude Code、Codex、OpenClaw 等支持 Skills 协议的 Agent 工具。

  • Proven python

    shanwije/proven-python/skills/proven-python Skill

    1★ repo

    Python engineering-discipline guardrails for writing, refactoring, testing, and reviewing Python code. Enforces test-driven development, full type coverage, small readable functions, PEP 257 docstrings, configuration over hardcoding, deliberate design, and a green toolchain (ruff, mypy, pytest) before any task is treated as finished. Use this whenever you are about to write, change, debug, test, package, or review Python code, set up a Python project, or decide whether Python code is done, even if the user never says the words "best practices", "clean code", "TDD", "type hints", or "design patterns".

  • Agent control

    Timur00Kh/cmux-agent-control-skill/skills/agent-control Skill

    1★ repo

    Run and orchestrate multiple Pi AI agents inside cmux on macOS. Covers pane creation, non-disruptive layout management, interactive Pi sub-agent spawning, sending task prompts, reading screens, and monitoring worker sessions.

  • Vercel eve framework

    Xtqm/skills/skills/vercel-eve-framework Skill

    1★ repo

    Expert guidance for building AI agents with Vercel's Eve framework — an open-source, filesystem-first, TypeScript-native agent framework (public beta since June 17, 2026). EXPLICIT triggers — activate when user mentions: "eve agent", "vercel eve", "eve dev", "eve framework", "npx eve@latest", agent.ts, agent/instructions.md, agent/tools/, agent/skills/, agent/channels/, agent/connections/, agent/schedules/, agent/subagents/, "defineTool", "defineAgent", "defineEval", "defineMcpClientConnection", "eve eval", "eve channels add", Vercel Sandbox in agent context, Vercel Workflows in agent context, AI Gateway in agent context. SEMANTIC triggers — activate even without "Eve" keyword when user describes: "durable AI agent on Vercel", "long-running AI agent", "agent that survives crashes or deploys", "workflow-backed agent", "checkpointed agent sessions", "agent that runs for hours / days / weeks", "agent with human-in-the-loop approvals", "filesystem-driven agent framework", "Vercel agent framework", "agent directory structure", "agent that deploys to Vercel", "agent with sandboxed code execution", "agent with isolated compute". ACTION triggers — activate when the user wants to: scaffold a new agent project on Vercel, add channels (Slack, Discord, Teams, GitHub) to an existing agent, add approval gates to agent tools, connect an agent to MCP servers, set up agent observability with OpenTelemetry, test agent behaviour with scored evals, migrate from another agent framework to Eve. This skill covers the complete Eve surface. For deep topics it routes to focused reference files, each loaded only when relevant, reducing context overhead by ~70%.

  • Github oss ops

    hyt315/github-oss-ops Skill

    1★

    Use when maintaining an open-source GitHub repository after launch, including Issue triage, reply drafting, PR review assistance, CI diagnosis, release preparation, stale-item review, repository health reporting, and approval-gated GitHub writes. Triggers include Issue 管理、分流、triage、PR 审查、回复 Issue、版本号、发版、Release、changelog、过期 Issue、stale、运营报告、开源项目运营、oss ops, and project operations.

  • Design system extractor

    KunalKumarkkr01/design-system-extractor/skills/design-system-extractor Skill

    1★ repo

    Reverse-engineer the design system of any live website into a single, implementation-ready reference (a design.md plus annotated screenshots) that another LLM or developer can follow to faithfully recreate the look and feel. Use this whenever the user wants to capture, document, extract, clone, mirror, copy, or reproduce the design / UI / styling / "vibe" / look-and-feel of an existing site or web app — for example "document the design system of stripe.com", "make a style guide from this URL", "I want my app to look like X, extract their design tokens", or "explore this site and tell me how it's built visually". Works on any reachable URL. Requires the Chrome DevTools MCP server to drive a real browser; the skill is non-functional without it.

  • Project ninja

    made-on-weekends/vibe-code-ninja/project-ninja Skill

    no license1★ repo

    Maintain alignment between code and project documentation across AGENTS.md, CLAUDE.md, GEMINI.md, README.md, and the docs/ folder (PRODUCT, ARCHITECTURE, API, DATABASE, SCHEMA, DESIGN, BRAND, UX, COMPONENTS, DECISIONS, SECURITY, TESTING). Stack-agnostic — works for any language or framework. Use this skill at the start of any non-trivial coding session to load ONLY the relevant docs (token-efficient routing), before adding or removing features (to prevent scope drift and accidental deletions), and after changes are merged (to update only the docs that actually need updating). Trigger this skill whenever the user mentions align, drift, scope, documentation, project setup, init, update docs, refactor, or any feature add or remove — even if they do not explicitly ask for documentation work. Also trigger on phrases like "is this in scope", "did we decide", "what's the convention", or any time the user is about to delete code.

  • Claude code cli

    Michaelihc/claude-code-cli-codex-skill/claude-code-cli Skill

    1★ repo

    Delegate work from Codex to the local Claude Code CLI with low-waste, current command patterns. Use when Codex needs to call `claude`, choose Claude Code model or effort settings, use `ultrathink` or `ultracode`, run print-mode JSON calls, resume or continue Claude sessions across turns, manage background Claude agents or workflows, cap spend with `--max-budget-usd`, restrict Claude tools, or compare Claude output against Codex work.

  • Debug

    DavisMcCracken/pyxis/skills/debug Skill

    1★ repo

    Diagnose hard or uncertain bugs, reproduce-first — build a feedback loop before hypothesizing. Use when reproduction or cause is unclear, the failure is intermittent or cross-system, or performance regressed.

  • Api security

    pop123-ux/agent-security-skills/skills/api-security Skill

    1★ repo

    Production-grade security Agent Skills (SKILL.md) for Claude Code, Claude agents & OpenClaw: OWASP API Top 10 patterns + authentication/authorization patterns.

  • Problem solving systems thinking

    bybaochaule/problem-solving-systems-thinking Skill

    1★

    Use this skill to decompose complex problems, map workflows, identify decision points, and design end-to-end agent flows for operational, business, product, or automation systems. Trigger when the user asks for problem decomposition, systems thinking, workflow mapping, lead generation process design, decision trees, SOP design, agent flow design, bottleneck analysis, or how an agent should think, decide, and act. Do not use it for executing workflows, making unsupervised high-stakes decisions, or replacing expert legal, medical, financial, or compliance review.

  • Developer

    matt-bat/agent-skill-foundry/packs/developer Skill

    no license1★ repo

    Use for general Agent engineering work that needs a compact operating policy for clarification, sequencing, safe command execution, regression control, documentation upkeep, quality review, frontend judgment, and the persistent --quizme clarification mode.

  • Production readiness audit

    P1tak4s/production-readiness-audit Skill

    1★

    Audit, scan, and harden a codebase for production across security, reliability, testing, data/compliance, operations, and accessibility. Use when the user asks to security-check, security-scan, security-review, audit, harden, or assess production-readiness of a project; when checking for injection, auth/authz, secrets, TLS, rate limiting, dependency/supply-chain vulns, multi-tenancy isolation, PII/GDPR/HIPAA handling, audit logging, error handling, retries/idempotency, circuit breakers, race conditions, caching, tests/coverage/load/chaos testing, RTO/RPO/disaster recovery, observability/alerting, deploy safety/rollback, architecture diagrams/ADRs, or accessibility; or when asked to scaffold these controls, a threat model, DR plan, or audit report. Combines a stdlib-only scanner script with deep reference checklists and ready-to-fill templates.

  • Review until clean

    lzehrung/review-until-clean-odw/skills/review-until-clean Skill

    no license1★ repo

    Portable pre-PR review-until-clean workflow and agent skill

  • Seaworthy

    AmirHosein-Lotfi/Seaworthy/skills/seaworthy Skill

    1★ repo

    Pre-deploy security and secrets gate for AI-built ("vibe-coded") web apps. Scans the repo for the exact disaster pattern behind real 2026 breaches — hardcoded secrets, .env files committed to git history, Supabase Row Level Security disabled or unconfirmed, exposed service-role keys, API/serverless routes with no auth check before a database read or write, wildcard CORS combined with credentials, debug mode left on in production config, publicly-writable storage buckets, and unprotected admin routes. Produces a blunt, plain-English SAFE-TO-SHIP / SHIP-WITH-CAUTION / DO-NOT-DEPLOY verdict instead of an engineer-style audit report — built for someone who mostly prompted an AI to build their app and may not know what RLS or CORS even mean. Use this whenever the user asks "is this safe to deploy", "can I push this to production", "is my app secure enough to launch", "is my app seaworthy", "pre-launch check", "security check before deploy", "am I about to get hacked", or anything adjacent — and proactively run it before any deploy-shaped action (vercel deploy, git push to main/production, "let's launch") even if the user didn't explicitly ask for a security check.

  • Agent self audit

    Xxt-XN/agent-self-audit Skill

    no license1★

    AI coding assistant health check and configuration audit. Detects bloat, drift, security issues, skill gaps, and pipeline violations. Quick mode (6+1 items, under 500 tokens) or Full mode (13 items with trend analysis, predictive warnings, and market intelligence). Use for: system health check, config audit, diagnostic, drift detection, compliance review, self-optimization. 用于:系统健康检查、配置审计、诊断、漂移检测、合规审查、自我优化。

  • Audit config

    Teddy563/mcwrench/skills/audit-config Skill

    1★ repo

    Audits a Minecraft server's configuration tree for performance, security and footgun issues and reports a prioritised fix list. Use whenever the user asks to "audit my config", "check my server config", "review paper-global.yml", "why is my server set up wrong", "is this config safe", "lint my server", or points at a folder containing server.properties, paper-global.yml, paper-world-defaults.yml, paper-world.yml, spigot.yml, bukkit.yml, purpur.yml or velocity.toml. Also use proactively after the user shares any of those files or pastes their contents. Flags online-mode/forwarding mismatches, exposed RCON, YAML tab characters, view-distance/simulation-distance mismatches, missing entity limits, and unsafe unsupported-settings. Reports findings as critical, high, medium and low.

  • Skill creator

    udohjeremiah/skills/.agents/skills/skill-creator Skill

    1★ repo

    Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

    The same file is in 66 other repositories

  • Cli as harness

    jesse-black/skills/skills/cli-as-harness Skill

    1★ repo

    Author CLI surfaces as agent-facing documentation, especially `--help` and actionable error messages. Use with any language or parser design when adding or changing a CLI interface, improving help text or validation errors, moving command reference out of AGENTS.md / CLAUDE.md / a README / a skill and into CLI surfaces, or making errors suggest the corrected command line or tool call.

  • Agentskillshub cli

    zhuyansen/agentskillshub-cli Skill

    1★

    Use when the user wants to find, evaluate, audit, or install an open-source AI agent skill or MCP server — e.g. "find an MCP server for Postgres", "is this skill safe to install", "what should I use to scrape a website". Searches a quality-scored, security-graded catalog of ~20K skills locally (cached index, zero backend load) and returns each result's security grade, quality score, and install commands so you can check trust BEFORE installing.

  • Loop it

    fhajjej-ship-it/loop-it/skills/loop-it Skill

    1★ repo

    Choose, compile, launch, or run bounded AI-agent goals with explicit deliverables, proof rubrics, verifier gates, iteration caps, stop conditions, and approval boundaries. Includes a categorized Loop goals library for product, design, research, content, data, and operations plus advanced engineering loops for Codex, Claude Code, Cursor, and other SKILL.md-compatible agents. Use when the user says "loop it", asks for a loop goal, asks what should be looped next, or wants iterative improvement with proof. Do not use for simple one-shot edits unless the user asks for a repeatable loop.

  • Sharp api design

    zhouhuijia/sharp-skills/skills/sharp-api-design Skill

    no license1★ repo

    API design quality enforcement. Covers REST API endpoint design, error handling, versioning, pagination, naming conventions, and request/response modeling. This skill should be used when the user asks to design, review, or improve an API — whether a new API from scratch or refactoring an existing one. It corrects the most common AI API design failures: inconsistent naming, mixed REST/RPC styles, broken error patterns, and pagination chaos.

  • Ra1 fix

    tjboudreaux/ready-agent-1/skills/ra1-fix Skill

    1★ repo

    Ready Agent 1 gears up your repo (the Loadout) — remediate agent-readiness gaps by applying safe configuration scaffolds, drafting documentation for review, and listing GitHub settings to change. Use when the user asks to fix readiness, remediate readiness findings, raise the readiness level, apply readiness fixes, or scaffold missing config (linters, CI, CODEOWNERS, issue/PR templates, dependabot, devcontainer, .env.example). Applies changes to a local branch only and never pushes without confirmation.

  • Skill compass

    Thomaszhou22/skill-compass Skill

    no license1★

    Diagnose, fix, and prevent agent skill trigger failures. Use when a skill doesn't activate, when skills trigger incorrectly, when troubleshooting "skill not working" issues, when auditing skill descriptions for quality, when optimizing trigger accuracy, or when asked "why didn't my skill fire?". Also use proactively after installing new skills or when agent behavior seems to ignore available skills. Covers description optimization, YAML frontmatter validation, token budget analysis, conflict detection, and auto-remediation.

  • Android project standard

    VoldemortGin/AI-Coding-Skill-Bible/android-project-standard Skill

    1★ repo

    Enforce a strict, model-agnostic, AI-navigable Kotlin/Android project standard: the Kotlin compiler's null-safety + sealed/`when` exhaustiveness as the static guarantee, plus `allWarningsAsErrors` + library-module `explicitApi()` + a detekt static-analysis gate as a one-command zero-warning gate, the escape hatches (`!!` non-null assertion / unchecked `as` / `lateinit` abuse / platform-type leaks / `GlobalScope`) shut via detekt-as-error, kotlinx.serialization + `@JvmInline value class` newtypes at boundaries (parse don't validate), a Gradle multi-module module-per-domain structure, a zero-SDK zero-framework `:domain` module behind provider interface seams with a default `MockProvider`, Hilt composition-root injection in `:app`, a version catalog pinning every version, an ktlint + detekt double lint gate, a CLAUDE.md in every module, and scaffold/conformance scripts. Use whenever starting or scaffolding a Kotlin or Android project; setting up Gradle / settings.gradle.kts / libs.versions.toml / detekt / ktlint / CI; deciding module structure; adding an LLM / embedding / vector-store dependency; wiring providers or adapters with Hilt; or checking that an existing Android project conforms. Apply it even when the user only says "start an Android project", "set up the structure", "add an LLM", or "wire up CI" without naming the standard. This skill governs the Kotlin host's internals; it is complementary to polyglot-core-standard, which governs the cross-language seam (generated UniFFI/JNI bindings).

  • Goal task prompt

    zitao4588-create/goal-task-prompt/skill/goal-task-prompt Skill

    1★ repo

    Use this skill when the user wants to turn a rough idea, project ask, debugging request, or large task into a concise, copy-ready Codex /goal prompt. Also use it for Loop Cards, delegation briefs, multi-agent orchestration, and prompt or skill evaluation when the user explicitly needs those advanced formats.

  • Mac setup bundle builder

    jakowicz/skills/skills/mac-setup-bundle-builder Skill

    no license1★ repo

    Create personalized AI-agent-driven Mac rebuild bundles from a user's current Mac. Use when asked to inventory a Mac and generate a tailored setup/rebuild bundle covering whatever is actually installed: apps, package managers, runtime/version managers, dotfiles, system settings, app settings, private migration notes, containers, virtual machines, local services, AI tools, repos, live progress logs, verification checks, and final HTML reports for recreating that user's Mac setup on a new machine.

  • Memory card studio

    wuA-zs/memory-card-studio/memory-card-studio Skill

    1★ repo

    Use when the user asks to create or update persistent local memory-card projects, generate flashcards or spaced-repetition card libraries from files, URLs, web pages, or other readable sources, create a zero-install card-review frontend, start today's due-card review, or study an existing local card library in conversation.

  • Prompt engineering instructions

    bybaochaule/prompt-engineering-instructions Skill

    1★

    Use this skill to create, revise, evaluate, or standardize prompts and agent instructions using role, goal, context, examples, constraints, and reliability tests. Trigger when the user asks for prompt engineering, system or developer instructions, few-shot examples, prompt templates, agent behavior guidance, or prompt refinement. Do not use it for policy bypassing, hidden instruction extraction, unsafe automation, or unrelated copywriting.

  • Pg extension lab

    ysys143/pg-extension-lab/skills/pg-extension-lab Skill

    1★ repo

    Develop, test, benchmark, and operate PostgreSQL extensions with reusable harnesses and reference protocols. Use for C/PGXS or Rust/pgrx extension work, planner hooks, CustomScan or index AM design, pg_regress/pg_isolation_regress TDD, filtered ANN/vector benchmarks, matched-recall and pages-per-query analysis, bounded parameter-space exploration, Pareto curves, hypothesis/evidence/report management, accelerator-vs-CPU crossover, resource Pareto tuning, Shape B microservice extensions, Shape C sidecar daemons, service-boundary contracts, async outbox workers, and SECURITY hardening. Balances docs, code evidence, and execution results. Includes copy-ready test, benchmark, contract, and ops assets. Not for projects without a PostgreSQL extension layer.

  • Architecture blueprint

    yiyaw-lab/agent-armor/architecture-blueprint Skill

    1★ repo

    Maintains an Architecture Blueprint so builders track what agents built across sessions. In Continuum repos, defer to X-3 (`.continuum/blueprint/`, BlueprintPanel) — do not duplicate. In other repos, use markdown `ARCHITECTURE.md` + append-only change feed. Invoke explicitly when the user mentions schema drift, lost track of architecture, what agents built, mental model sync, or architectureImpact.

  • Skillforge repo to skill

    xiaokillua/skillforge/skills/skillforge-repo-to-skill Skill

    1★ repo

    Use this skill when the task is to turn a GitHub repository or local codebase into a portable agent skill for Claude, Codex, GitHub Copilot, OpenClaw, Hermes, or other Agent Skills compatible runtimes.

  • Codex project memory

    Retourflow/project-memory-for-codex/skill/codex-project-memory Skill

    1★ repo

    Maintain a minimal, token-aware, verified project memory for Codex repositories. Use when initializing project context files, resuming work across sessions, changing architecture or project goals, recording decisions, updating current state after implementation, or reducing bloated and stale agent documentation.