Context & AI engineering
25,815 rows, by stacks then stars
1,865 of these skill files have been read, by 1,328 distinct authors, and what they tell an agent counted. What Context & AI engineering authors agree on, and what they forbid
sergebulaev/threads-skills/skills/threads-hook-extractor Skill
19★ repoReverse-engineer the hook from a viral Threads post or thread URL. Identifies which of the 10 canonical 2026 Threads formulas it uses (warm contrarian, data-point, build-in-public, quote-post, mini-list, relatable, listicle, story, curiosity-gap, how-I teardown), explains why it worked, and returns a blank template mapped to your topic with its primary goal (replies, reposts, likes, quotes). Use to learn from a post you admire. Not for writing your own (use threads-post-writer).
ChronoAIProject/Ornn/examples/text-summarizer Skill
19★ repoSummarise a chunk of text down to roughly `length` words using the agent's configured LLM provider. Input shape `{ text: string, length?: number }` on stdin, JSON; output shape `{ summary: string }` on stdout, JSON. Minimal: ~50 lines, no streaming, no retries — a deliberate baseline so the wiring is visible. For a production summariser, fork this and add retries, prompt-injection sanitisation, length validation, and per-model cost tracking.
CodingCossack/agent-skills-library/skills/subagent-driven-development Skill
no license19★ repoSequential subagent execution with two-stage review gates for implementation plans. Use when executing multi-task plans in current session, when tasks need fresh subagent context to avoid pollution, when formal review cycles (spec compliance then code quality) are required between tasks, or when you need diff-based validation of each task before proceeding.
The same file is in 8 other repositories
livlign/claude-skills/plugins/repo-visuals/skills/repo-visuals-retro Skill
19★ repoRetrospective meta-skill for the `repo-visuals` skill. Reads accumulated evaluation logs from past runs, spots patterns (recurring low-score criteria, repeated iteration failures, unsatisfied requests), consults other expert skills (skill-creator, frontend-design, etc.) where relevant, and proposes concrete edits to `repo-visuals/SKILL.md` as a reviewable diff. Runs on-demand, not per run.
pilotspace/ADD/add-method/skill/add/persona-author Skill
19★ repoAuthor or improve an ADD-method persona file (a .add/personas/ slug.md) — the project-fit requirements LENS the ADD engine validates and the design/build/verify/advisor surfaces load. Use when adding a domain expert to the ADD roster, when the add-worker persona mode must DRAFT a persona because none fits the task kind, or when folding a retrospective into an existing persona. Produces a schema-valid persona (Identity, Critical Rules, Default Requirement, Success Metrics, plus recommended frontmatter and Abilities/Anti-patterns/Playbook) that carries the judgment layer of strong agent design: earned-perspective identity, bold-lead rules, the qualification gate, read-before-you-assert, failure-mode-aware metrics, defended budgets, and per-flow stances. Seeds a first draft from the teacher library or a sample subagent when a near-fit source exists, instead of a blank page.
pilotspace/ADD/add-method/src/add_method/_bundled/skill/add/persona-author Skill
19★ repoAuthor or improve an ADD-method persona file (a .add/personas/ slug.md) — the project-fit requirements LENS the ADD engine validates and the design/build/verify/advisor surfaces load. Use when adding a domain expert to the ADD roster, when the add-worker persona mode must DRAFT a persona because none fits the task kind, or when folding a retrospective into an existing persona. Produces a schema-valid persona (Identity, Critical Rules, Default Requirement, Success Metrics, plus recommended frontmatter and Abilities/Anti-patterns/Playbook) that carries the judgment layer of strong agent design: earned-perspective identity, bold-lead rules, the qualification gate, read-before-you-assert, failure-mode-aware metrics, defended budgets, and per-flow stances. Seeds a first draft from the teacher library or a sample subagent when a near-fit source exists, instead of a blank page.
travsteward/openwriter/skills/beat-writer Skill
19★ repoChannel-agnostic writer for any piece of content that doesn't yet belong to a specific channel. Use when you have something to say but don't know where it goes — could become a blog post, X thread, newsletter section, web copy, journal entry, or just stay as a plain doc. Runs the beat extraction + shaping discipline, pours prose via /authors-voice (with the operator's default anchor — personal voice), polishes, and leaves a clean draft in OpenWriter. The draft can later be refactored into a specific channel via /blog-writer, /x-writer, or /newsletter-writer. Use when: "/beat-writer", "write this", "draft something", "I have an idea but don't know where", "extract beats", "write me a draft", "pour this in voice", "I want to think this through in writing", "plain doc", "just open a doc", "uncommitted draft", "I'll figure out where it goes later". NOT for: known-channel work (use the channel-master directly — /blog-writer for blogs, /x-writer for tweets, /newsletter-writer for emails, /book-writer for chapters). Requires: OpenWriter MCP server configured + /authors-voice set up with at least Tier 1 anchor.
travsteward/openwriter/skills/blog-writer Skill
19★ repoChannel-master writer for long-form blog posts. Owns the SHAPE of a post — beat structure, title/preview/slug commitments, per-post container layout, per-site voice anchor discovery — and delegates VOICE (prose generation) to /authors-voice and PUBLISH mechanics to the openwriter github plugin (`add_blog_site` + `post_to_blog`). Use when: "/blog-writer", "write a blog post", "blog draft", "brainstorm blog topics", "blog beats", "extract beats from this post", "write about this feature", "draft a post", "blog title", "preview text", "OG description", "blog image", "featured image", "OG image", "integrate", "create the files", "wire up the blog post", "publish to blog", "post to blog", "set up blog repo", "register blog site". Requires: OpenWriter MCP server configured + github plugin enabled + `gh auth login` set up locally. Project SHOULD have a `## Blog` section in its CLAUDE.md for writing-rules / image-style overrides (optional after setup).
travsteward/openwriter/skills/newsletter-writer Skill
19★ repoChannel-master writer for email newsletter. Weekly pipeline: scaffold structure, gather data, query the author, synthesize in their voice, review, send. Companion doc workflow. Voice-matched via the authors-voice skill. Works for any behind-the-scenes weekly newsletter built on proven content. Use when: "/newsletter-writer", "newsletter", "draft newsletter", "scaffold newsletter", "newsletter gather", "newsletter review", "newsletter send", "newsletter status", "newsletter to blog", "convert newsletter". Requires: OpenWriter MCP server configured.
travsteward/openwriter/skills/openwriter Skill
19★ repoOpenWriter — the writing surface for AI agents. A markdown-native rich text editor where agents write via MCP tools and users accept or reject changes in-browser. 40 core MCP tools for document editing, multi-doc workspaces, and organization, plus 21 publish platform tools for newsletter, social posting, and scheduling. Tweet compose mode for drafting replies/QTs with pixel-accurate X/Twitter UI. Plain .md files on disk — no database, no lock-in. Use when user says: "open writer", "openwriter", "write in openwriter", "edit my document", "review my writing", "check the pad", "write me a doc", "compose tweet", "reply to tweet", "quote tweet", "author's voice", "authors voice", "voice plugin". Requires: OpenWriter MCP server configured. Browser UI at localhost:5050.
aroyburman-codes/pm-skills/skills/ai-product-teardown Skill
19★ repoStructured teardown of AI products (ChatGPT, Claude, Gemini, Perplexity, Copilot, etc.). Analyzes product decisions, UX patterns, technical architecture, business model, and competitive positioning.
kdr/overcast/skills/overcast-skill-creator Skill
19★ repoCreate small, installable agent skills that wrap focused Overcast workflows. Use when the user asks to make an Overcast skill for a specific investigation, media analysis, recon, monitoring, or case-memory workflow.
event4u-app/agent-config/dist/agent-src/skills/agent-docs-writing Skill
19★ repoUse when reading, creating, or updating agent documentation, module docs, roadmaps, or AGENTS.md. Understands the full .augment/, agents/, and copilot-instructions structure.
event4u-app/agent-config/dist/agent-src/skills/agent-security-review Skill
19★ repoUse for an adversarial red-team / blue-team / auditor review of an AI agent's CONFIG + behaviour (rules, skills, MCP, hooks, permissions) — attack-chain → defensive-gap list, not a code audit.
event4u-app/agent-config/dist/agent-src/skills/agents-md-thin-root Skill
19★ repoUse when editing AGENTS.md (package root) or templates/AGENTS.md (consumer) — enforces Thin-Root contract: hard char ceilings, ≥40% pointer ratio, mandatory emergency-triage block.
event4u-app/agent-config/dist/agent-src/skills/condense-memory Skill
19★ repoUse when shrinking always-loaded memory files (AGENTS.md, CLAUDE.md, .cursorrules) exceeding ~150 lines or ~4,000 chars — telegraph grammar, refuses sensitive paths, .original.md round-trip.
event4u-app/agent-config/dist/agent-src/skills/copilot-agents-optimization Skill
19★ repoUse when optimizing AGENTS.md or copilot-instructions.md — deduplicates against .augment/ content, enforces line budgets, and focuses each file on its audience.
event4u-app/agent-config/dist/agent-src/skills/copilot-config Skill
19★ repoTune the GitHub Copilot AI — `copilot-instructions.md`, PR-review patterns, suggestion behavior, output verbosity. NOT for dev-environment setup (use `devcontainer`).
event4u-app/agent-config/dist/agent-src/skills/evaluate-llm-feature Skill
19★ repoBlack-box evaluation of a shipped LLM feature — adversarial probes for hallucination, prompt-injection, and cost-runaway vs stated expectations. Not RAG/embedding. Triggers 'review my chatbot'.
event4u-app/agent-config/dist/agent-src/skills/llm-provider-knowledge Skill
19★ repoBefore stating any specific fact about an LLM provider's product — models, pricing, limits, context windows, SDK/API — for OpenAI, Gemini, Claude & others, verify against official docs, not memory.
event4u-app/agent-config/dist/agent-src/skills/markitdown Skill
19★ repoConvert PDF, DOCX, XLSX, PPTX, EPUB, images, or audio to Markdown via the markitdown-mcp server — 'extract this PDF', 'OCR this image', 'transcribe this audio'.
event4u-app/agent-config/dist/agent-src/skills/mcp-builder Skill
19★ repoUse when building an MCP server in Python (FastMCP) or Node/TypeScript (MCP SDK) — agent-centric tool design, input schemas, error handling, and the 10-question evaluation harness.
event4u-app/agent-config/dist/agent-src/skills/mcp Skill
19★ repoUse when working with MCP (Model Context Protocol) servers — their tools, capabilities, and best practices for effective agent workflows.
event4u-app/agent-config/dist/agent-src/skills/memory-consolidation Skill
19★ repoUse when consolidating session signals into curated memory — four-phase loop ORIENT → GATHER → CONSOLIDATE → PRUNE. Triggers on 'mine my sessions', 'consolidate memory', 'review intake signals'.
event4u-app/agent-config/dist/agent-src/skills/prompt-engineering-image Skill
19★ repoTranslate an image brief into provider-specific prompt grammar per model. Use when writing or refining an image-generation prompt for Ideogram, Flux, Gemini, GPT Image 2, or Recraft.
event4u-app/agent-config/dist/agent-src/skills/prompt-engineering-patterns Skill
19★ repoUse when designing production-LLM prompts — few-shot, chain-of-thought, system prompts, templates, self-verification — distinct from prompt-optimizer and refine-prompt.
event4u-app/agent-config/dist/agent-src/skills/prompt-optimizer Skill
19★ repoUse when the user wants a prompt optimized for ChatGPT, Claude, Gemini, or another AI — 'make this prompt better', 'optimize for ChatGPT', 'rewrite my prompt' — even without saying 'optimize'.
event4u-app/agent-config/dist/agent-src/skills/prompt-validator Skill
19★ repoPre-spend contradiction gate for AI-video runs: checks every prompt in the batch, blocks on style / character / physics mismatch. Triggers 'validate the prompts', 'check the storyboard'.
event4u-app/agent-config/dist/agent-src/skills/reasoning-orchestrator Skill
19★ repoUse for multi-step / ambiguous / end-to-end work — refactor a whole module, drive a vague ticket to a verified result, plan+build+verify a migration; coordinates the reasoning chain across skills.
event4u-app/agent-config/dist/agent-src/skills/refine-prompt Skill
19★ repoReconstruct a free-form prompt into actionable AC + assumptions + confidence band before the engine plans — '/work "…"', 'baue X', 'ist der Prompt klar genug für die Engine?'.
event4u-app/agent-config/dist/agent-src/skills/subagent-orchestration Skill
19★ repoUse when orchestrating implementer/judge subagents — form gate + nine modes (do-and-judge ±two-stage, steps/parallel/worktrees, competitively, debate, live-app-judge, adversarial-council).
event4u-app/agent-config/dist/agent-src/skills/worktree-lifecycle Skill
19★ repoUse when governing a worktree across its whole life — scope-lock declaration, merge-readiness status, scoped verification, and safe cleanup that refuses while unique unmerged commits exist.
event4u-app/agent-config/src/skills/agent-docs-writing Skill
19★ repoEvery claim machine-checked, including "zero runtime daemon" — governed skills, rules and replayable state. One contract, every host agent.
event4u-app/agent-config/src/skills/agent-security-review Skill
19★ repoEvery claim machine-checked, including "zero runtime daemon" — governed skills, rules and replayable state. One contract, every host agent.
event4u-app/agent-config/src/skills/agents-md-thin-root Skill
19★ repoUse when editing AGENTS.md (package root) or templates/AGENTS.md (consumer) — enforces Thin-Root contract: hard char ceilings, ≥40% pointer ratio, mandatory emergency-triage block.
event4u-app/agent-config/src/skills/condense-memory Skill
19★ repoUse when shrinking always-loaded memory files (AGENTS.md, CLAUDE.md, .cursorrules) exceeding ~150 lines or ~4,000 chars — telegraph grammar, refuses sensitive paths, .original.md round-trip.
event4u-app/agent-config/src/skills/copilot-agents-optimization Skill
19★ repoUse when optimizing AGENTS.md or copilot-instructions.md — deduplicates against .augment/ content, enforces line budgets, and focuses each file on its audience.
event4u-app/agent-config/src/skills/copilot-config Skill
19★ repoTune the GitHub Copilot AI — `copilot-instructions.md`, PR-review patterns, suggestion behavior, output verbosity. NOT for dev-environment setup (use `devcontainer`).
event4u-app/agent-config/src/skills/evaluate-llm-feature Skill
19★ repoBlack-box evaluation of a shipped LLM feature — adversarial probes for hallucination, prompt-injection, and cost-runaway vs stated expectations. Not RAG/embedding. Triggers 'review my chatbot'.
event4u-app/agent-config/src/skills/llm-provider-knowledge Skill
19★ repoBefore stating any specific fact about an LLM provider's product — models, pricing, limits, context windows, SDK/API — for OpenAI, Gemini, Claude & others, verify against official docs, not memory.
event4u-app/agent-config/src/skills/markitdown Skill
19★ repoConvert PDF, DOCX, XLSX, PPTX, EPUB, images, or audio to Markdown via the markitdown-mcp server — 'extract this PDF', 'OCR this image', 'transcribe this audio'.
event4u-app/agent-config/src/skills/mcp-builder Skill
19★ repoUse when building an MCP server in Python (FastMCP) or Node/TypeScript (MCP SDK) — agent-centric tool design, input schemas, error handling, and the 10-question evaluation harness.
event4u-app/agent-config/src/skills/mcp Skill
19★ repoUse when working with MCP (Model Context Protocol) servers — their tools, capabilities, and best practices for effective agent workflows.
event4u-app/agent-config/src/skills/memory-consolidation Skill
19★ repoUse when consolidating session signals into curated memory — four-phase loop ORIENT → GATHER → CONSOLIDATE → PRUNE. Triggers on 'mine my sessions', 'consolidate memory', 'review intake signals'.
event4u-app/agent-config/src/skills/prompt-engineering-image Skill
19★ repoTranslate an image brief into provider-specific prompt grammar per model. Use when writing or refining an image-generation prompt for Ideogram, Flux, Gemini, GPT Image 2, or Recraft.
event4u-app/agent-config/src/skills/prompt-engineering-patterns Skill
19★ repoUse when designing production-LLM prompts — few-shot, chain-of-thought, system prompts, templates, self-verification — distinct from prompt-optimizer and refine-prompt.
event4u-app/agent-config/src/skills/prompt-optimizer Skill
19★ repoUse when the user wants a prompt optimized for ChatGPT, Claude, Gemini, or another AI — 'make this prompt better', 'optimize for ChatGPT', 'rewrite my prompt' — even without saying 'optimize'.
event4u-app/agent-config/src/skills/prompt-validator Skill
19★ repoPre-spend contradiction gate for AI-video runs: checks every prompt in the batch, blocks on style / character / physics mismatch. Triggers 'validate the prompts', 'check the storyboard'.
event4u-app/agent-config/src/skills/reasoning-orchestrator Skill
19★ repoUse for multi-step / ambiguous / end-to-end work — refactor a whole module, drive a vague ticket to a verified result, plan+build+verify a migration; coordinates the reasoning chain across skills.
event4u-app/agent-config/src/skills/refine-prompt Skill
19★ repoReconstruct a free-form prompt into actionable AC + assumptions + confidence band before the engine plans — '/work "…"', 'baue X', 'ist der Prompt klar genug für die Engine?'.
event4u-app/agent-config/src/skills/subagent-orchestration Skill
19★ repoUse when orchestrating implementer/judge subagents — form gate + nine modes (do-and-judge ±two-stage, steps/parallel/worktrees, competitively, debate, live-app-judge, adversarial-council).
event4u-app/agent-config/src/skills/worktree-lifecycle Skill
19★ repoUse when governing a worktree across its whole life — scope-lock declaration, merge-readiness status, scoped verification, and safe cleanup that refuses while unique unmerged commits exist.
kpab/claude-fable-5-skills/skills/grounded-progress Skill
19★ repoMake Claude Fable 5 progress reports verifiable against actual tool results during long autonomous runs. Use for any multi-hour or overnight agent session, scheduled pipelines, CI agents, or whenever the user has been burned by status updates claiming work that wasn't done. Apply before launch, not after a fabricated report appears.
kpab/claude-fable-5-skills/skills/markdown-memory Skill
19★ repoA file-based lesson memory that Claude Fable 5 reads and maintains across sessions. Use for any recurring agent (daily jobs, long projects, team assistants) where the same corrections keep being re-made, and when bootstrapping a new agent from past session history. Fable 5 benefits from recorded lessons noticeably more than prior models did.
kpab/claude-fable-5-skills/skills/regrounding-summary Skill
19★ repoMake Claude Fable 5's final report readable to someone who saw none of the work. Use for long agentic sessions, overnight runs, and multi-tool tasks — whenever summaries come back as arrow-chain shorthand, invented abbreviations, or references to reasoning the reader never saw. Pair with grounded-progress for status content; this skill governs the prose.
kpab/claude-fable-5-skills/skills/skill-refactorer Skill
19★ repoAudit and rewrite existing agent skills, system prompts, and CLAUDE.md files for Claude Fable 5. Use whenever the user mentions migrating, upgrading, porting, or "fixing" a skill or prompt for Fable 5, complains that a previously good skill now produces worse output, or asks why Fable 5 ignores or over-follows old instructions. Also trigger when reviewing any skill written before June 2026.
kpab/claude-fable-5-skills/skills/subagent-orchestration Skill
19★ repoPatterns for delegating work to parallel subagents with Claude Fable 5 — when to split tasks, async coordination, long-lived workers, and fresh-context verifiers. Use when designing multi-agent harnesses, when a large task has independent parts, when runs bottleneck on sequential steps, or when self-review keeps missing its own mistakes.
paulnsorensen/easy-cheese/skills/easy-cheese-setup Skill
19★ repoRegister and repair the durable cheese hallouminate corpus and the per-repo tenant. Use when the user says "set up cheese corpus", "repair hallouminate corpus", "register durable corpus", "my specs aren't searchable across sessions", "fix cheese-global drift", or invokes /easy-cheese-setup. Runs a detect → report → confirm → fix loop over two legs — a global durable-corpus registration/repair and a local per-repo tenant registration. Do NOT use for general hallouminate wiki authoring (that is the wiki skills) or for MCP server installation (that is scripts/install.sh).
s-hiraoku/synapse-a2a/.agents/skills/post-impl-claude Skill
no license19★ repo'Workflow: Post-implementation workflow for Claude Code agents: docs/simplify/sync in parallel, then release, commit all changes, create PR, and autofix with /autofix-pr.
s-hiraoku/synapse-a2a/.agents/skills/skill-creator Skill
no license19★ repoCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update 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.