Context & AI engineering
25,772 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
timwukp/agent-skills-best-practice/skills/skills/skill-creator Skill
13★ 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.
The same file is in 7 other repositories
Marcel-Bich/marcel-bich-claude-marketplace/plugins/credo/skills/migrate Skill
13★ repoA collection of mainly my own productivity plugins for Claude Code.
Marcel-Bich/marcel-bich-claude-marketplace/plugins/credo/skills/orchestration Skill
13★ repoA collection of mainly my own productivity plugins for Claude Code.
PiNocPie/thai-claude-skills/skills/content/hook-generator-th Skill
no license13★ repohooks 10 รูปแบบให้เลือกใช้ | สำหรับ นักเขียน คอนเทนต์ครีเอเตอร์ หร. Triggers when user says (Thai/EN): 'hook', 'ปัง 3 วิ'
VidyFoo/antigravity-skill-engine/.agent/skills/3-sys/mcp-building Skill
13★ repoGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools.
tykisgod/quick-question/skills/claude-code-review Skill
13★ repoDeep code review via Claude subagent — reviews uncommitted changes by default, loops until no critical issues remain. Use after /qq:test passes, before /qq:commit-push.
tykisgod/quick-question/skills/claude-plan-review Skill
13★ repoSend a design document to a Claude subagent for review, then revise the document based on findings. Automatically loops until no critical issues remain or 5 rounds are complete.
kevinnft/ai-agent-skills/skills/addyosmani/context-engineering Skill
13★ repoOptimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure rules files and context for a project.
kevinnft/ai-agent-skills/skills/addyosmani/using-agent-skills Skill
13★ repoDiscovers and invokes agent skills. Use when starting a session or when you need to discover which skill applies to the current task. This is the meta-skill that governs how all other skills are discovered and invoked.
kevinnft/ai-agent-skills/skills/autonomous-ai-agents/claude-code Skill
13★ repoDelegate coding to Claude Code CLI (features, PRs).
kevinnft/ai-agent-skills/skills/autonomous-ai-agents/hermes-agent Skill
13★ repoConfigure, extend, or contribute to Hermes Agent.
kevinnft/ai-agent-skills/skills/creative/claude-design Skill
13★ repoDesign one-off HTML artifacts (landing, deck, prototype).
kevinnft/ai-agent-skills/skills/creative/touchdesigner-mcp Skill
13★ repoControl a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.
kevinnft/ai-agent-skills/skills/devops/kanban-orchestrator Skill
13★ repoDecomposition playbook + specialist-roster conventions + anti-temptation rules for an orchestrator profile routing work through Kanban. The "don't do the work yourself" rule and the basic lifecycle are auto-injected into every kanban worker's system prompt; this skill is the deeper playbook when you're specifically playing the orchestrator role.
kevinnft/ai-agent-skills/skills/devops/kanban-worker Skill
13★ repoPitfalls, examples, and edge cases for Hermes Kanban workers. The lifecycle itself is auto-injected into every worker's system prompt as KANBAN_GUIDANCE (from agent/prompt_builder.py); this skill is what you load when you want deeper detail on specific scenarios.
kevinnft/ai-agent-skills/skills/inference-sh/inference-sh Skill
13★ repoRun 150+ AI applications in the cloud via the inference.sh platform. Triggers on "generate image with FLUX", "create video", "use Veo/Seedance", "run inference.sh", "infsh CLI", "single key for image+video+LLM". One API key covers image generation (FLUX, Reve, Seedream, Grok, Gemini), video (Veo, Wan, Seedance, OmniHuman, HunyuanVideo), LLMs (Claude, Gemini, Kimi, GLM-4), search (Tavily, Exa), 3D (Rodin), social (Twitter/X), and audio (TTS, voice cloning).
kevinnft/ai-agent-skills/skills/mattpocock/engineering/setup-matt-pocock-skills Skill
13★ repoSets up an `## Agent skills` block in AGENTS.md/CLAUDE.md and `docs/agents/` so the engineering skills know this repo's issue tracker (GitHub or local markdown), triage label vocabulary, and domain doc layout. Run before first use of `to-issues`, `to-prd`, `triage`, `diagnose`, `tdd`, `improve-codebase-architecture`, or `zoom-out` — or if those skills appear to be missing context about the issue tracker, triage labels, or domain docs.
kevinnft/ai-agent-skills/skills/mattpocock/misc/git-guardrails-claude-code Skill
13★ repoSet up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.
kevinnft/ai-agent-skills/skills/mattpocock/productivity/handoff Skill
13★ repoCompact the current conversation into a handoff document for another agent to pick up.
kevinnft/ai-agent-skills/skills/mattpocock/productivity/write-a-skill Skill
13★ repoCreate new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.
kevinnft/ai-agent-skills/skills/mcp/native-mcp Skill
13★ repoMCP client: connect servers, register tools (stdio/HTTP).
kevinnft/ai-agent-skills/skills/mlops/evaluation/lm-evaluation-harness Skill
13★ repolm-eval-harness: benchmark LLMs (MMLU, GSM8K, etc.).
kevinnft/ai-agent-skills/skills/research/llm-wiki Skill
13★ repoKarpathy's LLM Wiki: build/query interlinked markdown KB.
kevinnft/ai-agent-skills/skills/software-development/hermes-agent-skill-authoring Skill
13★ repoAuthor in-repo SKILL.md: frontmatter, validator, structure.
kevinnft/ai-agent-skills/skills/software-development/subagent-driven-development Skill
13★ repoExecute plans via delegate_task subagents (2-stage review).
kevinnft/ai-agent-skills/skills/superpowers/dispatching-parallel-agents Skill
13★ repoUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
kevinnft/ai-agent-skills/skills/superpowers/subagent-driven-development Skill
13★ repoUse when executing implementation plans with independent tasks in the current session
buildinternet/releases/.claude/skills/local-ingest Skill
13★ repoOnboard or backfill a company's changelog locally in Claude Code by fetching pages and extracting releases with the agent itself (and parallel sub-agents), then writing through the batch-upsert endpoint — no remote fetch dispatch, no server-side extraction inference billing. Use when you want to onboard a source without triggering the remote update workflow's billed extraction, or recover from a remote fetch that burned tokens and wrote zero releases. Includes a mandatory robots.txt / Content-Signal opt-out gate.
buildinternet/releases/.claude/skills/seeding-playbooks Skill
13★ repoCoordinate bulk playbook writing using parallel sub-agents — covers org discovery, prompt templates, model selection, batch dispatch, verification, and the parent-saves pattern for working around subagent permission limits. Currently wired up for Claude Code's Agent tool; the managed-agent fleet supports sub-agents too and the pattern can be adapted, but isn't wired up there yet.
kaile9/apostle-skills/skills/apostle-artifacts-loops Skill
13★ repoLong tasks, sub-agent, and multi-agent work — durable artifacts, session handoff, execution graphs, and context discipline. Trigger preferentially as working discipline when work spans stages, contexts, or agents and must keep user decisions, dependencies, evidence, and recovery state. Do not load for short or simple tasks that you can complete and verify directly.
mouadja02/skills/skills/agent-design/agent-supply-chain Skill
no license13★ repoVerify supply chain integrity for AI agent plugins, tools, and dependencies. Use this skill when: - Generating SHA-256 integrity manifests for agent plugins or tool packages - Verifying that installed plugins match their published manifests - Detecting tampered, modified, or untracked files in agent tool directories - Auditing dependency pinning and version policies for agent components - Building provenance chains for agent plugin promotion (dev → staging → production) - Any request like "verify plugin integrity", "generate manifest", "check supply chain", or "sign this plugin"
The same file is in 1 other repository
mouadja02/skills/skills/agent-design/agentic-browser-automation Skill
no license13★ repoBuild AI-powered browser agents that autonomously navigate, scrape, fill forms, and extract data from dynamic websites using LLM reasoning + Playwright
mouadja02/skills/skills/agent-design/agentic-rag-architect Skill
no license13★ repoTriggers on keywords RAG, GraphRAG, vector database, agentic RAG, semantic search
mouadja02/skills/skills/agent-design/ai-agent-builder Skill
no license13★ repoAlso use for agentic data engineering pipelines, code generation agents, agent-powered CLI tools, MCP server development, or any system where an AI model calls tools, makes decisions, or loops
mouadja02/skills/skills/agent-design/ai-team-orchestration Skill
no license13★ repoMulti-agent dev team — parallel AI agents, roles, coordination, project kickoff
mouadja02/skills/skills/agent-design/bmm-skills/1-analysis/bmad-agent-analyst Skill
no license13★ repoStrategic business analyst and requirements expert
mouadja02/skills/skills/agent-design/bmm-skills/1-analysis/bmad-agent-tech-writer Skill
no license13★ repoTechnical documentation specialist and knowledge curator
mouadja02/skills/skills/agent-design/bmm-skills/2-plan-workflows/bmad-agent-pm Skill
no license13★ repoProduct manager for PRD creation and requirements discovery
mouadja02/skills/skills/agent-design/bmm-skills/2-plan-workflows/bmad-agent-ux-designer Skill
no license13★ repoUX designer and UI specialist. Use when the user asks to talk to Sally or requests the UX designer.
mouadja02/skills/skills/agent-design/bmm-skills/3-solutioning/bmad-agent-architect Skill
no license13★ repoSystem architect and technical design leader. Use when the user asks to talk to Winston or requests the architect.
mouadja02/skills/skills/agent-design/bmm-skills/4-implementation/bmad-agent-dev Skill
no license13★ repoSenior software engineer for story execution and code implementation
mouadja02/skills/skills/agent-design/create-agent-tui Skill
no license13★ repoAgent TUI scaffolding in TypeScript — @openrouter/agent, interactive terminal UI
mouadja02/skills/skills/agent-design/create-headless-agent Skill
no license13★ repoScaffolds a headless agent in TypeScript using @openrouter/agent and Bun — for CLI tools, API servers, queue workers, and pipelines. No terminal UI
mouadja02/skills/skills/agent-design/durable-agent-workflows Skill
no license13★ repoUse when designing retryable or crash-resilient agent workflows, especially when tools can send, charge, publish, provision, or otherwise create duplicate side effects.
mouadja02/skills/skills/agent-design/harness-scaling Skill
no license13★ repoUse when designing or auditing an agentic AI system holistically. Activates the six-component harness framework (ℛ Reasoning, ℳ Memory, 𝒞 Context, 𝒮 Skills, 𝒪 Orchestration, 𝒢 Governance) from arXiv:2605.26112. Trigger phrases: "design an agent system", "why is my agent unreliable", "harness architecture", "system-level agent design", "beyond model scaling", "agentic infrastructure", "scale my agent system", "agent performance bottleneck".
mouadja02/skills/skills/agent-design/latent-briefing Skill
no license13★ repoThis skill should be used when the user asks to "share memory between agents", "KV cache compaction for multi-agent", "orchestrator worker context", "latent briefing", "reduce worker tokens", "cross-agent memory without summarization", or discusses Attention Matching compaction, recursive language models with workers, or token explosion in hierarchical agents.
mouadja02/skills/skills/agent-design/mcp-tool-routing Skill
no license13★ repoUse when designing scalable MCP tool routing, dynamic tool retrieval, agent-tool graphs, tool inventory indexing, or routing policies for agents with many available tools.
mouadja02/skills/skills/agent-design/multi-agent-patterns Skill
no license13★ repoThis skill should be used when the user asks to "design multi-agent system", "implement supervisor pattern", "create swarm architecture", "coordinate multiple agents", or mentions multi-agent patterns, context isolation, agent handoffs, sub-agents, or parallel agent execution.
mouadja02/skills/skills/agent-design/rich-claude-code-tui-clone Skill
no license13★ repoUse when building a Python terminal UI inspired by Claude Code with Rich. Translates a detailed TypeScript/Ink-style visual reference into a staged Python architecture for logo, message stream, streaming Markdown, tools, diffs, prompt, footer, spinners, permissions, transcript mode, themes, accessibility, and tests. Separates Rich rendering from the input and widget responsibilities that require an application-owned event loop or an optional Textual layer.
Stateful agent security monitoring
mouadja02/skills/skills/agent-design/stateful-agent-security-monitoring Skill
no license13★ repoUse when designing defensive monitoring for agent systems whose risks accumulate across users, sessions, subagents, files, or tool calls. Adds online cross-context clustering with rare escalation, time-to-detect evaluation, provenance checks for control-like workspace content, and sanitized commits for persistent prompt-injection defense.
mouadja02/skills/skills/agent-design/trading-agent-builder Skill
no license13★ repoBuild AI-powered trading and financial analysis agents using multi-agent architectures with LLMs
mouadja02/skills/skills/agent-eval/agent-trajectory-diagnostics Skill
no license13★ repoUse when diagnosing agent benchmarks or runtime failures from trajectories instead of aggregate pass rates. Builds shared action-observation decision landscapes, identifies productive cores and trap regions, profiles Access/Trap/Repair behavior, and designs conservative trap-triggered recovery experiments.
mouadja02/skills/skills/agent-eval/agentic-eval Skill
no license13★ repoPatterns and techniques for evaluating and improving AI agent outputs. Use this skill when: - Implementing self-critique and reflection loops - Building evaluator-optimizer pipelines for quality-critical generation - Creating test-driven code refinement workflows - Designing rubric-based or LLM-as-judge evaluation systems - Adding iterative improvement to agent outputs (code, reports, analysis) - Measuring and improving agent response quality
The same file is in 1 other repository
mouadja02/skills/skills/agent-eval/auto-memory-pro Skill
no license13★ repoCurate Claude Code's auto-memory into durable project knowledge. Analyze MEMORY.md for patterns, promote proven learnings to CLAUDE.md and .claude/rules/, extract recurring solutions into reusable skills. Use when: (1) reviewing what Claude has learned about your project, (2) graduating a pattern from notes to enforced rules, (3) turning a debugging solution into a skill, (4) checking memory health and capacity
mouadja02/skills/skills/agent-eval/auto-memory-pro/skills/promote Skill
no license13★ repoGraduate a proven pattern from auto-memory (MEMORY.md) to CLAUDE.md or .claude/rules/ for permanent enforcement.
mouadja02/skills/skills/agent-eval/autoresearch-agent Skill
no license13★ repoAutonomous experiment loop that optimizes any file by a measurable metric. Inspired by Karpathy's autoresearch. The agent edits a target file, runs a fixed evaluation, keeps improvements (git commit), discards failures (git reset), and loops indefinitely. Use when: user wants to optimize code speed, reduce bundle/image size, improve test pass rate, optimize prompts, improve content quality (headlines, copy, CTR), or run any measurable improvement loop. Requires: a target file, an evaluation command that outputs a metric, and a git repo
mouadja02/skills/skills/agent-eval/eval-driven-dev Skill
no license13★ repoImprove AI application with evaluation-driven development. Define eval criteria, instrument the application, build golden datasets, observe and evaluate application runs, analyze results, and produce a concrete action plan for improvements. ALWAYS USE THIS SKILL when the user asks to set up QA, add tests, add evals, evaluate, benchmark, fix wrong behaviors, improve quality, or do quality assurance for any Python project that calls an LLM model.
mouadja02/skills/skills/agent-eval/harness-benchmarking Skill
no license13★ repoUse when designing evaluation suites for agentic systems, choosing agent benchmarks, measuring multi-agent performance, or critiquing single-score evaluation of agents. Based on arXiv:2605.26112v1. Trigger phrases: "evaluate my agent", "benchmark agent", "measure agent reliability", "pass^k evaluation", "agent metrics beyond success rate", "trajectory quality", "memory hygiene metric", "longitudinal agent eval", "why my agent scores well on benchmarks but fails in production".
mouadja02/skills/skills/agent-eval/mcp-agent-evaluation Skill
no license13★ repoUse when evaluating MCP-enabled agents, tool-using LLM systems, multi-server workflows, tool-selection quality, trajectory quality, task completion, or MCP security regressions.
mouadja02/skills/skills/agent-eval/memory-merger Skill
no license13★ repoMerges mature lessons from a domain memory file into its instruction file