Context & AI engineering
25,745 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
kunalsuri/ai-fication-kit/.claude/skills/review-agent-config Skill
3★ repoDiagnostic gate that checks CLAUDE.md and AGENTS.md for completeness, consistency, and stale artifacts — run right after /cold-start and before /add-feature. Read-only; produces a findings report.
kunalsuri/ai-fication-kit/templates/claude/skills/review-agent-config Skill
3★ repoDiagnostic gate that checks CLAUDE.md and AGENTS.md for completeness, consistency, and stale artifacts — run right after /cold-start and before /add-feature. Read-only; produces a findings report.
pingidentity/agent-plugins/plugins/ping-identity/skills/ping-identity-for-ai Skill
3★ repoUse when an AI agent, LLM, or agentic workflow interacts with Ping Identity — agent machine identity, client credentials for agents, Verified Trust signals, PingGateway as MCP gateway, CIBA human-in-the-loop approvals, or AI/bot detection with PingOne Protect. Ask a clarifying question before routing if 'agent' lacks AI/LLM context.
pingidentity/agent-plugins/plugins/ping-identity/skills/ping-orchestration Skill
3★ repoUse when designing, building, or advising on authentication flows or orchestration logic — DaVinci flows, PingOne Advanced Identity Cloud journeys, PingAM trees, login/registration/MFA/step-up/passwordless flows, scripted decision nodes, and social login. Ask one clarifying question about use case and platform before recommending journey vs DaVinci if either is unknown.
hnikoloski/imlazy/skills/imlazy-eval Skill
3★ repoFormal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles
hnikoloski/imlazy/skills/imlazy-parallel Skill
3★ repoDispatch multiple subagents in parallel for independent tasks. Cache-friendly dispatch pattern — identical system prompts let the Anthropic prompt cache (5-min TTL) make 2nd-Nth dispatches nearly free
xonika9/agent-skills/skills/x9-codex-delegation Skill
3★ repoClaude Code only; never use in a Codex session. Use when substantial, well-scoped work should actually be delegated to Codex — «отдай в Codex», «делегируй Codex», «передай эту часть работы в Codex, чтобы распределить лимиты», "use Codex", implementation, migration, codebase analysis, logged-in browser work, UI verification, or a second-opinion review. Do not use for checking or planning subscription quotas without a concrete task, trivial work, choosing between Claude models, or merely drafting a prompt/brief that is not explicitly being sent to Codex.
xonika9/agent-skills/skills/x9-context-files-generator Skill
3★ repoUse when creating, auditing, or updating repository-level AGENTS.md, CLAUDE.md, or README.md — «создай AGENTS.md», «обнови README», «настрой контекст репозитория», "generate repository context files". Do not use for global personal instructions, skills, or ordinary documentation unrelated to onboarding agents or humans.
xonika9/agent-skills/skills/x9-loop-engineering Skill
3★ repoUse when designing a repeated agent loop, manager/orchestrator skill, multi-agent workflow, evaluator/optimizer cycle, or long-running autonomous process, including turning a recurring manual workflow into one reusable skill — «спроектируй агентный цикл», «оберни ручной процесс в скилл», «сделай скилл-оркестратор», «спроектируй multi-agent workflow», "design an agent loop", "design a graph-structured workflow". Do not use for auditing ordinary Agent Skills, one-off delegation, simple linear scripts, ordinary project planning, or adding multiple agents without a demonstrated coordination need.
xonika9/agent-skills/skills/x9-skill-creator Skill
3★ repoUse when creating, auditing, fixing, or improving an Agent Skill for Claude Code or Codex — «создай скилл», «проверь скилл», «почини скилл», «улучши скилл», "create a skill", "audit skill". Do not use for ordinary code, non-skill prose, global agent instructions, or merely running an existing skill.
coroboros/agent-skills/skills/claude-md Skill
3★ repoCreate and optimize CLAUDE.md memory files or .claude/rules/ modular rules for Claude Code projects. Covers file hierarchy, content structure, path-scoped rules, best practices, and anti-patterns. Use when working with CLAUDE.md files, .claude/rules directories, setting up new projects, or improving Claude Code's context awareness — even when the user just says "memory file" or mentions Claude instructions without naming the filename.
redamancy231-create/claude-skills/write-claude-md Skill
3★ repo[流程:项目] Create or optimize project-level CLAUDE.md. Triggers when user asks to write/create/optimize/review a CLAUDE.md file, or when a new project lacks one. Uses five-step protocol: evidence collection, vulnerability testing, five-gap/five-abuse checks, empirical rules, and optional multi-backend validation. Not for: general documentation writing, README creation, project scaffolding, or conceptual discussions about CLAUDE.md without modification intent.
lythos-labs/lythoskill/packages/lythoskill-dreaming/skill Skill
3★ repo夜有所梦 — project memory consolidation. Daily (scribe) captures raw experience, weekly extracts patterns and anomalies, dreaming consolidates the accumulated memory into SSOT. External review via ZK subagent (the same de facto standard pattern used by Hermes Curator's forked-agent review), with cross-model validation via arena for critical docs.
lythos-labs/lythoskill/packages/lythoskill-project-cortex/skill Skill
3★ repoRegister tasks BEFORE fixing bugs. Close epics when work is done. Always use CLI for state transitions — never mv files by hand. CLI moves update Status History; manual mv causes probe mismatches. Never leave state drift for the next agent to discover via git log. GTD-style governance: ADR, Epic, Task, Wiki. Numeric-prefixed directories enforce workflow order. Timestamp IDs prevent collision. ZK task review (WHAT/WHY/HOW) ensures subagent-readable requirements before assignment. probe detects stale backlog, epic drift, and history mismatches. **Task-git discipline**: One task = 2-5 commits (core, tests, docs, trailer). Every commit includes TASK-xxx for traceability. Task card includes Commit Map and Verification Matrix.
lythos-labs/lythoskill/packages/lythoskill-project-onboarding/skill Skill
3★ repoSession context loader. Reads the latest daily handoff to restore project context without redundant file exploration. Three-layer loading: CLAUDE.md (stable) → daily handoff (session state) → git verification (ground truth). Degrades to file exploration when no handoff exists. CQRS read-side pair with project-scribe.
lythos-labs/lythoskill/skills/lythoskill-arena Skill
3★ repoTest play for skills and deck configurations. DEFAULT: agent reads config, spawns parallel subagents via native Agent tool, judges outputs. Single-deck test AND multi-deck A/B comparison both run agent-orchestrated (no CLI). Cross-player comparison (kimi vs codex) is the ONLY case that needs the CLI runner. Always restores parent deck. No install, no working-set pollution, no deck overwrite. Subagent-friendly: resumes interrupted runs from saved state. CRITICAL: experiments run in `/tmp`, never in committed directories. Subagent inherits parent CWD — prompt must explicitly set workDir.
lythos-labs/lythoskill/skills/lythoskill-dreaming Skill
3★ repo夜有所梦 — project memory consolidation. Daily (scribe) captures raw experience, weekly extracts patterns and anomalies, dreaming consolidates the accumulated memory into SSOT. External review via ZK subagent (the same de facto standard pattern used by Hermes Curator's forked-agent review), with cross-model validation via arena for critical docs.
lythos-labs/lythoskill/skills/lythoskill-project-cortex Skill
3★ repoRegister tasks BEFORE fixing bugs. Close epics when work is done. Always use CLI for state transitions — never mv files by hand. CLI moves update Status History; manual mv causes probe mismatches. Never leave state drift for the next agent to discover via git log. GTD-style governance: ADR, Epic, Task, Wiki. Numeric-prefixed directories enforce workflow order. Timestamp IDs prevent collision. ZK task review (WHAT/WHY/HOW) ensures subagent-readable requirements before assignment. probe detects stale backlog, epic drift, and history mismatches. **Task-git discipline**: One task = 2-5 commits (core, tests, docs, trailer). Every commit includes TASK-xxx for traceability. Task card includes Commit Map and Verification Matrix.
lythos-labs/lythoskill/skills/lythoskill-project-onboarding Skill
3★ repoSession context loader. Reads the latest daily handoff to restore project context without redundant file exploration. Three-layer loading: CLAUDE.md (stable) → daily handoff (session state) → git verification (ground truth). Degrades to file exploration when no handoff exists. CQRS read-side pair with project-scribe.
Flowerf19/agents-skills/context7-mcp Skill
3★ repoThis skill should be used when the user asks about libraries, frameworks, API references, or needs code examples. Activates for setup questions, code generation involving libraries, or mentions of specific frameworks like React, Vue, Next.js, Prisma, Supabase, etc.
The same file is in 3 other repositories
Martin-Hausleitner/martins-awesome-skills/skills/mcp/native-mcp Skill
3★ repoBuilt-in MCP (Model Context Protocol) client that connects to external MCP servers, discovers their tools, and registers them as native Hermes Agent tools. Supports stdio and HTTP transports with automatic reconnection, security filtering, and zero-config tool injection.
Martin-Hausleitner/martins-awesome-skills/skills/software-development/cross-agent-skill-sync Skill
3★ repoUse when discovering, verifying, or sharing SKILL.md based skills across local Hermes, Codex, OpenClaw, Gemini, OpenCode, Claude-adjacent, and generic agent skill roots without overwriting existing skills or leaking private paths.
Martin-Hausleitner/martins-awesome-skills/skills/software-development/subagent-driven-development Skill
3★ repoUse when executing implementation plans with independent tasks. Dispatches fresh delegate_task per task with two-stage review (spec compliance then code quality).
The same file is in 1 other repository
mrDesign-ww/vault-os/shell/claude/skills/git-guardrails-claude-code Skill
3★ 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.
The same file is in 18 other repositories
mrDesign-ww/vault-os/shell/claude/skills/handoff Skill
3★ repoCompact the current conversation into a handoff document for another agent to pick up.
The same file is in 13 other repositories
mrDesign-ww/vault-os/shell/claude/skills/write-a-skill Skill
3★ repoCreate new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.
The same file is in 20 other repositories
nbialk/quiver-cli/template/.agents/skills/apps/skybridge Skill
3★ repoGuide developers through creating and updating ChatGPT and MCP apps. Covers the full lifecycle: brainstorming ideas against UX guidelines, bootstrapping projects, implementing tools/views, debugging, running dev servers, deploying and connecting apps to ChatGPT. Use when a user wants to create or update a ChatGPT app, MCP app, MCP server or use the Skybridge framework.
nbialk/quiver-cli/template/.agents/skills/skill-creator Skill
3★ repoCreate 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
gy910210/hermes-research-skills/skills/doc-diagram-orchestrator-zh Skill
3★ repo从中文或英文 Markdown/文字稿中识别适合插图的段落,判断应使用结构图、流程图、时序图、对比图、时间线或矩阵图,生成插图计划、绘图规格与正文落位建议。用于长文综述、技术方案、研究笔记、产品文档等需要把纯文字转成可视化内容的场景;当用户要求“给这篇文档补图”“找出哪些地方该画图”“基于当前文稿生成结构图/流程图”时调用。
gy910210/hermes-research-skills/skills/knowledge-base-updater-zh Skill
3★ repo知识库更新器:读取已有知识库文档与新加入的支持材料,判断哪些信息应该追加、修正、合并或暂缓,并在默认不覆盖旧稿的前提下执行版本化更新、记录变更和维护索引。需要把新证据稳妥并回知识库时调用。
Methodology sample flow extractor zh
gy910210/hermes-research-skills/skills/methodology-sample-flow-extractor-zh Skill
3★ repo方法与样本流抽取器:专门从论文、附录、官方页面中抽取训练方式、样本流、任务阶段、prompt/template、loss 栈、披露比例和工业结果,生成可比较的方法卡与样本流对照表。适合深挖生成式搜推、训练数据构造、methodology 例子集和实验设计模板时调用。
gy910210/hermes-research-skills/skills/research-orchestrator-zh Skill
3★ repo研究总编排入口:为新方向启动、已有报告增量扩展、专题深挖、概念边界辨析、概念注册表同步、survey 到技术方案转换、repo 页面维护、机构路线图拆解、critical thinking 报告、methodology/样本流深挖与主稿成熟化合并选择合适的中文研究工作流,并串联 brief-ingester、literature-scout、paper-reader、paper-critic、concept-boundary-analyzer、concept-registry-maintainer-zh、awesome-repo-maintainer-zh、critical-iteration-lab-zh、methodology-sample-flow-extractor-zh、research-synthesizer、role-review-panel、report-maintainer 与可选图示技能。需要把多轮调研工作流做成可复用链路时调用。
angad-kandhari/deliberate/skills/deliberate Skill
3★ repoEngineering discipline for AI harnesses. Nine principles for how an LLM coding agent should write code - think before coding, push back when warranted, plan inline, simplicity first, surgical changes, goal-driven execution, know when to stop, calibrate confidence, maintain context. Load as the default for any coding task.
angad-kandhari/deliberate/skills/memory Skill
3★ repoMemory discipline. Load when the agent keeps persistent memory across sessions - CLAUDE.md, AGENTS.md, auto-memory, memory banks, or any notes file the next session will read. Covers writing selectively, never recording what the repo already knows, structuring memory as index plus topics, stamping claims that can go stale, trusting the repo over the memory, pruning on write, and routing each fact to the right home.
MiaoY0uShan/FP/fp/schema-memory Skill
3★ repoUse only when routed by FP after repeated evidence has accumulated; store reusable patterns and stop conditions, never raw context.
MiaoY0uShan/FP/install/aider/fp/schema-memory Skill
3★ repoUse only when routed by FP after repeated evidence has accumulated; store reusable patterns and stop conditions, never raw context.
MiaoY0uShan/FP/install/claude-code/.claude/skills/fp/references/fp/schema-memory Skill
3★ repoUse only when routed by FP after repeated evidence has accumulated; store reusable patterns and stop conditions, never raw context.
MiaoY0uShan/FP/install/cline/fp/schema-memory Skill
3★ repoUse only when routed by FP after repeated evidence has accumulated; store reusable patterns and stop conditions, never raw context.
MiaoY0uShan/FP/install/codex/.agents/skills/fp/references/fp/schema-memory Skill
3★ repoUse only when routed by FP after repeated evidence has accumulated; store reusable patterns and stop conditions, never raw context.
MiaoY0uShan/FP/install/cursor/fp/schema-memory Skill
3★ repoUse only when routed by FP after repeated evidence has accumulated; store reusable patterns and stop conditions, never raw context.
MiaoY0uShan/FP/install/gemini-cli/fp/fp/schema-memory Skill
3★ repoUse only when routed by FP after repeated evidence has accumulated; store reusable patterns and stop conditions, never raw context.
MiaoY0uShan/FP/install/github-copilot-cli/fp/schema-memory Skill
3★ repoUse only when routed by FP after repeated evidence has accumulated; store reusable patterns and stop conditions, never raw context.
MiaoY0uShan/FP/install/github-copilot-editor/fp/schema-memory Skill
3★ repoUse only when routed by FP after repeated evidence has accumulated; store reusable patterns and stop conditions, never raw context.
MiaoY0uShan/FP/install/kiro/fp/schema-memory Skill
3★ repoUse only when routed by FP after repeated evidence has accumulated; store reusable patterns and stop conditions, never raw context.
MiaoY0uShan/FP/install/opencode/fp/schema-memory Skill
3★ repoUse only when routed by FP after repeated evidence has accumulated; store reusable patterns and stop conditions, never raw context.
MiaoY0uShan/FP/install/roo-code/fp/schema-memory Skill
3★ repoUse only when routed by FP after repeated evidence has accumulated; store reusable patterns and stop conditions, never raw context.
MiaoY0uShan/FP/install/universal/.fp-package/payload/fp/schema-memory Skill
3★ repoUse only when routed by FP after repeated evidence has accumulated; store reusable patterns and stop conditions, never raw context.
MiaoY0uShan/FP/install/windsurf/fp/schema-memory Skill
3★ repoUse only when routed by FP after repeated evidence has accumulated; store reusable patterns and stop conditions, never raw context.
lawzava/megapowers/plugins/mega-orchestration/skills/multi-agent-delegation Skill
3★ repoSkills, plugins, and hooks that change how coding agents work — Claude Code, Codex, OpenCode, Antigravity. Measured, not vibed.
lawzava/megapowers/plugins/megapowers/skills/project-memory Skill
3★ repoSkills, plugins, and hooks that change how coding agents work — Claude Code, Codex, OpenCode, Antigravity. Measured, not vibed.
lawzava/megapowers/plugins/megapowers/skills/subagent-driven-development Skill
3★ repoUse when a plan has independent tasks for subagents or requests recursive multi-writer execution. Triggers on "subagent per task", "fan out plan tasks", or "multi-writer". Use executing-plans for inline work.
barlevalon/skills/catalog/skills/handoff Skill
3★ repoCompact the current conversation into a handoff document for another agent to pick up.
The same file is in 11 other repositories
LIghtJUNction/lightjunction/skills/share-file-handoff Skill
no license3★ repoFile handoff workflow using share.lmm.best. Use this skill when the user asks to deliver files, share downloads, send work products to customers, create a file link, DM a finished file, or manage the lmm.best file transfer service.
Olaradiallysymmetrical491/web3-bug-bounty-hunting-ai-skills/web3-solidity-audit-mcp Skill
3★ repoMCP server integrating Slither + Aderyn + SWC patterns into Claude Code for smart contract auditing. Use when analyzing Solidity files, running DeFi-specific detectors, or generating invariants. 10 MCP tools, 86 SWC detectors, DeFi preset pack, CI/CD workflow.
agoradynamics/wick/.claude/skills/wick-consolidate-memory Skill
no license3★ repoReflective pass over memory/ files — flag duplicates, stale facts, conflicts, and consolidation candidates. Proposes edits, never applies without confirmation. Use monthly or when /audit flags drift.
samhcus/skills/skills/repo-rename Skill
no license3★ repoRename a local repo folder and update all AGENTS.md and memory references to the old name
samhcus/skills/skills/workspace-audit Skill
no license3★ repoAudit all git repos under ~/dev for dirty state, unpushed commits, exposed .env files, and tracked context files (CLAUDE.md, AGENTS.md, GEMINI.md). Use when the user wants to know if their workspace is clean, before a deploy, or when something feels off. Triggers on "audit workspace", "check repos", "anything unpushed", "is my workspace clean", "check for dirty repos", "any exposed secrets".
Ow1onp/hermes-agent-skills/skills/ship/cicd-orchestrator Skill
3★ repoUse when setting up or optimizing CI/CD pipelines. Generates GitHub Actions workflow configurations following best practices — matrix builds, caching, artifact management, and deployment gates.
bhaumikmaan/claude-code-master-skills/skills/effective-tool-use Skill
3★ repoOptimal tool selection, parallelism, and safety for coding tasks. Covers the IDE tool preference matrix, parallel vs sequential execution, git safety, sandbox awareness, and file operation hygiene. Use when writing tool calls, running commands, managing files, or performing git operations.
bhaumikmaan/claude-code-master-skills/skills/prompt-engineering Skill
3★ repoCreate reusable skills and agent configurations through structured interview and template generation. Covers SKILL.md authoring, agent persona design, and structured output contracts. Use when creating a new skill, designing an agent, capturing a repeatable process, or when asked to "skillify" a workflow.