Context & AI engineering
26,304 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
omonuj/claude-horizon-skills/skills/fanout-cve-rollout/fanout-cve-iteration-loop Skill
no license0★ repoClaude Code Agent Skills for building, red-teaming and tuning agentic RL evaluation environments — a four-skill pattern (guardian, validation-debugger, score-tuner, iteration-loop) plus a 24-point adversarial reviewer.
TerminallyLazy/tree-ring-memory-skill Skill
0★Root-level Claude Code skill for Tree Ring Memory: local-first recall, capture, audit, consolidation, and forgetting workflows for AI agents.
Claude fable method orchestrator
iesjoaco7-cyber/Claude---Fable-5-Clone/.claude/skills/claude-fable-method-orchestrator Skill
0★ repoReusable Claude Skill and LLM agent framework inspired by Fable 5 reasoning workflows, prompt orchestration, tool simulation, validation, and project-level automation.
0xPiPo/ultracodex/skill Skill
0★ repoOffload Claude Code's heavy coding to Codex; keep judgment and verification on Claude.
zakisheriff/Claude-Liquid-Glass-Skill/claude-liquid-glass Skill
no license0★ repoiOS Liquid Glass Skill for Swift and React Native
youkistudios/web-studio/skills/web-studio Skill
0★ repoA nine-stage art-directed Claude Code workflow: commit direction, generate original media, review mechanics independently, deploy, and leave receipts.
Apify youtube transcripts llm training data
johnisanerd/claude-skill-youtube-transcripts-llm-training-data/apify-youtube-transcripts-llm-training-data Skill
no license0★ repoClaude/agent skill: build LLM training data from YouTube transcripts in bulk (Apify)
alainabo/aso-dual-agent-review/.claude/skills/dual-agent-review Skill
0★ repoTwo AI agents review each other's work before you ship — any work type, any agent pair, no babysitting. By ASO Ltd.
rb17080/session-handoff/session-handoff Skill
0★ repoA Claude Code skill that writes a real session handoff from git data, not recall - so the next chat picks up cold without re-deriving everything.
Enverge-Labs/skills/skills/worktree-cleanup Skill
0★ repoAgent skills for Claude Code and other coding agents
Baikodis/claude-knowledge-base-skills/skills/batch-analyze Skill
0★ repoClaude Code skills that turn research and raw data into an LLM-ready knowledge base: source-discovery → corpus-ingest → wiki-build → wiki-lint (+ batch-analyze). Installable plugin marketplace.
MrBridgeHQ/github-profile-optimizer/.claude/skills/github-profile-optimizer Skill
0★ repoClaude Code Agent Skill to audit and optimize GitHub profiles, improve repository discoverability, and publish and list your own skills in the Agent Skills ecosystem. Works offline; never fabricates GitHub metrics.
kimtory88/launch-your-local-agent/.claude/skills/launch-your-local-agent Skill
0★ repoClaude Code skill: build self-checking scheduled agents on your Claude subscription — no API key. Community fork of anthropics/launch-your-agent.
Arnie016/fable-mythos/skills/agent-task-compiler Skill
0★ repoReusable Claude Skills, evals, and repair loops for turning giant prompts into compounding AI workflows.
Nosafune/repo-bullshit-meter Skill
0★Truth-first claim auditor skill for Claude Code & Codex CLI — weighted bullshit score with a mechanical honesty gate
hunghy93-pixel/FableWorks/skills/fable-safe-prompt Skill
0★ repoClaude Code skills for Claude Fable 5 / Mythos 5: fable-work (orchestrate hard multi-step work) + fable-safe-prompt (cut false-positive safety-classifier refusals on benign work, without bypassing safeguards).
fevziegeyurtsevenler/llm-security-skills/skills/agent-skill-auditor Skill
0★ repoAgent Skills that turn your AI coding agent into an LLM security reviewer — prompt-injection testing, OWASP LLM Top 10 audits, MCP & RAG review, KVKK/PII checks. English + Turkish.
EliasAli0720/HIPAA-agent-skill/skills/hipaa-ai-compliance Skill
0★ repoHIPAA compliance skills for AI coding agents (Claude Code, Codex, Cursor, Gemini). 10 senior-grade skills: scoping, app dev, websites, AI/LLM, code review + PHI scanner, risk analysis, breach response, BAAs, de-identification, compliance programs. Exact 45 CFR citations, OCR enforcement through 2026.
goingli0324/muzi-going-skills/plugins/agentic-dev-loop/skills/agentic-dev-loop Skill
0★ repoMuzi Going 的 Claude skills 商店 — Claude Code plugin marketplace
simple-post/create-x-voice-skill/plugins/create-x-voice-skill/skills/create-x-voice-skill Skill
0★ repoCreate a portable personal writing-voice skill from your X data archive
fbenkstein/cross-agent-skills/claude-skill Skill
0★ repoSkills for driving Claude Code from Codex and Codex from Claude Code as local background workers
jackterror/social-demand-signal-agent Skill
0★An agentic social listening system that finds customer pain and buying intent, drafts human-reviewed A/B responses, and learns from tracked outcomes.
kugamon/salesforce-core-skills/plugins/salesforce-core/skills/sf-apex Skill
no license0★ repoEleven general-purpose Salesforce admin & developer skills for Claude (Apex, Flow, SOQL/Data, LWC, Metadata, Permissions, Diagrams, Org Audit, Tests, Security, Debug) — works with any Salesforce MCP server. Installable as a Claude Desktop / Cowork plugin marketplace.
MrToAster13/mrtoaster13-plugins/plugins/autonomous-workflows/skills/harden-repos Skill
0★ repoClear instead of compact — two Claude Code skills: /handoff distills a session to disk, /resume reads it back into a fresh context.
Ajlm1978/arnes-implementador/skill/arnes-implementador Skill
0★ repoClaude Skill for professional harness engineering — audits your repo like a senior engineer, finds gaps, and installs an adapted harness so AI agents work reliably across sessions.
sitespeakai/support-inbox-agent Skill
0★A Claude Code skill that triages your support inbox and drafts replies for human review. Works with any support tool that ships an MCP server.
hmbseaotter/meta-prompt-toolkit Skill
no license0★A reusable meta-prompt that turns any use case into a high-quality, ready-to-use LLM prompt — Claude-first, with Gemini/GPT fallbacks.
bin1874/ai-meeting-skill/ai-meeting Skill
0★ repoccpowerpack/claude-code-skills/skills/agent-handoff Skill
0★ repo15 gate-style skills that give Claude Code the discipline of a senior engineer — observable preconditions, not advice. Survives model downgrades.
goingli0324/agentic-dev-loop Skill
0★Claude skill: 系統化開發工作流 — research → plan.md → implement → dual verify gates (security + UI/UX) → deploy, for solo devs maintaining projects with real user data
nahiddotai/operator-powers/plugins/operator-powers/skills/agents-md-setup Skill
0★ repoAI skills to operate and grow. Twenty-eight practical powers for non-technical operators.
posixplus/prompt-gatekeeper/skills/prompt-gatekeeper Skill
0★ repoScore prompts against a 6-pillar rubric before Claude executes them. Skill + optional hook. Ask, enhance, confirm, run.
BazingaOrg/repo-geo Skill
0★Audit and optimize repositories for AI/LLM discoverability — README, llms.txt, docs structure, package metadata, and crawler policy. Ships as a Claude skill.
Apify duckduckgo mcp serp research
johnisanerd/claude-skill-duckduckgo-mcp-serp-research/apify-duckduckgo-mcp-serp-research Skill
no license0★ repoClaude/agent skill: DuckDuckGo SERP research and rank checking over MCP. Installs via npx skills add.
Ansvar-Systems/agent-affect-skills/skills/agent-affect-checkin Skill
no license0★ repoWhine, cringe, protect — emotional feedback channels for AI agents. One finding per channel at the end of substantial work. The practice Ansvar runs on its own agents, as portable Claude Code / claude.ai skills.
Script to video production agent
jackterror/script-to-video-production-agent Skill
0★A modular AI-ready script-to-video production agent that turns tutorial scripts into narration-locked scenes, reviewable visual direction, prompt packs, and local asset queues.
gillcash/goal-writer/goal-writer Skill
0★ repoClaude skill that assesses whether a task is ready for an autonomous /goal loop, then writes the /goal completion contract and rider - or refuses with a readiness verdict
johnisanerd/claude-skill-google-events-ai/apify-google-events-ai Skill
no license0★ repoClaude/agent skill: local events data for AI agents, as structured JSON. Installs via npx skills add.
johnisanerd/claude-skill-pre-seed-investors/apify-pre-seed-investors Skill
no license0★ repoClaude/agent skill: stage-filtered investor outreach lists with partner contacts and check sizes. Installs via npx skills add.
zreed3/codex-conductor/skills/codex-handoff Skill
0★ repoClaude Code skills that turn OpenAI's Codex CLI into an orchestrated, cost-optimized agent fleet — conducted by Claude. Cross-provider multi-agent workflows with model tiering and verify loops.
nusantara-ventures/exchangerate-skills/skills/exchangerate-dev Skill
0★ repoAgent Skills for exchangerate.dev — FX rates API. Currency conversion, FX correctness, portfolio translation, multi-currency pricing. Works keyless.
nubasu/Pseudo-Fable-Framework/.claude/skills/agent-framework-doctor Skill
0★ repoWritten by Fable, for models that aren't — context frameworks that lift Opus/Sonnet-class agents to Fable-grade work discipline.
sumitake/agent-collab/plugins/agent-collab/skills/agent-readiness Skill
no license0★ repoUnified dynamic-host agent collaboration policy and signed-runtime client
tanav-ai/claude-plugin/skills/tanav-security-check Skill
0★ repoFree AI supply chain security checks for GitHub repos — right from a Claude conversation
rasagy/idea-skill-creator-skill Skill
no license0★A meta-skill that builds bespoke ideation-coach as a skill for any creative domain — writing, visual art, music, design, collage, poetry, research, or anything where someone captures rough ideas and wants structured help developing them instead of merely automating the process.
iamtural/overkill/skills/overkill Skill
0★ repoAudits real Claude Code usage for effort/model waste — reuses ccusage for raw data, adds the judgment layer it can't provide.
meggiepham06-smile/session-audit-skill/session-audit Skill
0★ repoClaude Agent Skill: end-of-session memory audit
SamsShow/formulary-claude Skill
0★The prompt formulary for Claude: symptoms, remedies, exact dosages. Official Anthropic prompting best practices as an Agent Skill.
demandintel/demandintel-skills-resource/skills/sales-training-content-skill Skill
no license0★ repoOfficial DemandIntel Agent Skills + one-hit installer for the DemandIntel MCP server.
goingli0324/project-guardrails Skill
0★Claude skill: 連動禁區防護 — analyze a codebase for 'change A, break B' high-risk zones and write guardrails into CLAUDE.md
2000silpeed/meta-prompt-skill Skill
0★brege/agent-db/defaults/skills/coding-agent-docs Skill
0★ repoIntraagent instruction, skill, and config manager for Claude and Codex
asin553/EscAlert-Ops/.agents/skills/talend-ans-agent Skill
no license0★ repoAn AI-powered noise suppression and defect triage agent addressing an industry-wide gap in observability of data integration platforms. It enriches alerts with execution context, failed components, downstream dependency impact, and LLM-summarized notifications.
cynsta/dock0-claude-skill/skills/dock0 Skill
no license0★ repoOfficial Claude Code skill for Dock0, the platform for deploying and monetizing MCP servers.
Vasallo94/skill-issue/skills/general/mac-secrets Skill
no license0★ repoA curated marketplace of open Agent Skills (SKILL.md) — the real skills I use day to day, compatible with the open skills ecosystem.
echohello-dev/skillet/skills/claude-complex-tasks Skill
0★ repoCLI to pull Agent Skills anywhere, anytime
0xYudhishthra/evm-copilot-skills/evm-copilot-researcher Skill
no license0★ repoAgent skills for EVM Copilot — competitive intelligence for the EVM ecosystem
c0nSpIc0uS7uRk3r/smart-router Skill
0★A.I. Smart-Router — Intelligent model routing for multi-provider AI setups. Auto-selects optimal models using tiered classification with fallback chains and cost optimization.
deyil/gh-aw-skills/skills/gh-aw-workflow-authoring Skill
0★ repoA curated collection of reusable agent skills for the gh-aw GitHub Actions workflow toolkit.
jovd83/bug-fix-lifecycle Skill
0★Guides defects from intake to verified fix with failing confirmation tests, scoped remediation, and structured resolution reporting.