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
walidboulanouar/Ay-Skills/skills/skill-creator Skill
no license85★ repoGuide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
The same file is in 16 other repositories
dazuiba/handoff/cli/skills/handoff-opus Skill
no license83★ repo把关键决策/验收类任务交给 Claude Opus 执行。后台运行,完成后自动通知。支持并行多任务,支持续接(resume)上次会话继续派发后续任务。
eai-org/agent-toolkit/skills/compact-skill-creator Skill
82★ repoAuthor or refine a skill for maximum token economy without losing intent. Use when creating any new skill or editing an existing `SKILL.md`.
eai-org/agent-toolkit/skills/memory-doctor Skill
82★ repoAudit the current project's agent-memory and, block by block, relocate each entry into a user-controlled home (project doc/skill/rule or user-level skill/rule) or archive it — draining memory so nothing uncontrolled accumulates in the agent's context.
runxhq/runx/examples/github-mcp-hero Skill
82★ repoGoverned GitHub over MCP; read is admitted, out-of-scope mutation is sealed as a denial.
runxhq/runx/examples/github-mcp-hero/merge-pr Skill
82★ repoMerge a deterministic GitHub PR through the fixture MCP server.
runxhq/runx/examples/github-mcp-hero/read-issue Skill
82★ repoRead a deterministic GitHub issue through the fixture MCP server.
runxhq/runx/examples/github-mcp-hero/review-note Skill
82★ repoAdd a deterministic GitHub PR review note through the fixture MCP server.
runxhq/runx/examples/github-mcp-hero/write-comment Skill
82★ repoWrite a deterministic GitHub issue comment through the fixture MCP server.
runxhq/runx/examples/loop-orchestration Skill
82★ repoReference loop-orchestration example; a local loop host chains governed runx turns through receipts, budgets, context, and stop policy.
runxhq/runx/examples/managed-agent Skill
82★ repoManaged-agent front example; a governed agent-task that drafts a triage summary.
runxhq/runx/fixtures/skills/mcp-approval-graph Skill
82★ repoExercise a Rust-served MCP graph approval round trip.
runxhq/runx/fixtures/skills/mcp-echo Skill
82★ repoEcho a message through a local MCP stdio fixture server.
runxhq/runx/skills/n8n-handoff Skill
82★ repoValidate a runx execution context and hand off a governed payload to an n8n workflow webhook with scoped auth, idempotency, and receipt expectations.
runxhq/runx/skills/skill-lab Skill
82★ repoCanonical Runx skill-authoring implementation. Use for designing, creating, updating, improving, or adding harness coverage to a Runx skill package; it combines bounded agent judgment with native file writes, inspection, and safe harness validation. When a host skill-creator also triggers, use its general guidance but execute Runx work through this skill.
runxhq/runx/skills/zapier-handoff Skill
82★ repoValidate a runx execution context and hand off a governed payload to a Zapier Catch Hook with scoped auth, idempotency, and receipt expectations.
claude-world/director-mode-lite/skills/agent-template Skill
81★ repoGenerate custom agent from template. Use when creating a new subagent from scratch, or scaffolding an agent file with correct frontmatter.
claude-world/director-mode-lite/skills/claude-md-check Skill
81★ repoValidate CLAUDE.md structure and completeness
The same file is in 2 other repositories
claude-world/director-mode-lite/skills/claude-md-template Skill
81★ repoGenerate CLAUDE.md template for current project
The same file is in 2 other repositories
claude-world/director-mode-lite/skills/director-mode Skill
81★ repoDirect substantial repository work across Claude Code, Codex CLI, or Grok Build with a concise brief, parallel agents, evidence-based completion, and optional cross-CLI continuation. Use for project onboarding, multi-step implementation, agent coordination, verification planning, low-interruption setup, or deciding how another CLI should take over. Do not use it as a permission gate or mandatory workflow.
The same file is in 2 other repositories
claude-world/director-mode-lite/skills/handoff-claude Skill
81★ repoContinue a task in Claude Code through a portable Director handoff packet. Use when work started in Codex CLI or Grok Build should move to Claude, or when a fresh Claude session needs the current decisions and verification evidence.
claude-world/director-mode-lite/skills/handoff-codex Skill
81★ repoContinue a task in OpenAI Codex CLI through a portable Director handoff packet. Use when the user asks Codex to take over, wants an independent Codex implementation or review, or needs to preserve decisions and verification while changing CLIs.
claude-world/director-mode-lite/skills/handoff-gemini Skill
81★ repoDelegate long-context analysis, research, and large-document summarization to Google Gemini CLI (1M-token context) via non-interactive `gemini -p`, preserving Claude context. Use when the user says 'use gemini'/'hand off to gemini' or a task needs 100K+ tokens of context.
claude-world/director-mode-lite/skills/handoff-grok Skill
81★ repoContinue a task in xAI Grok Build using the shared Director handoff packet. Use when the user says to use Grok, requests a Grok review, or wants Grok Build to take over work started in Claude Code or Codex CLI.
The same file is in 2 other repositories
claude-world/director-mode-lite/skills/hook-template Skill
81★ repoGenerate hook script from template. Use when adding a new hook, wiring a PreToolUse/PostToolUse/Stop/Notification hook, or scaffolding hook config for settings.json.
claude-world/director-mode-lite/skills/mcp-check Skill
81★ repoValidate MCP configuration and suggest improvements. Use when MCP servers fail to load, after editing .mcp.json, or when the user runs /mcp-check.
claude-world/director-mode-lite/skills/skill-template Skill
81★ repoGenerate custom skill/command from template. Use when creating a new skill or slash command from scratch, or scaffolding a skill file with correct frontmatter.
Claude managed agents webhooks
hookdeck/webhook-skills/skills/claude-managed-agents-webhooks Skill
81★ repoReceive and verify Anthropic Claude Managed Agents (CMA) webhooks. Use when setting up Claude Managed Agents webhook handlers, debugging signature verification, or handling agent session and vault events like session.status_idled, session.status_terminated, session.thread_created, vault.created, or vault_credential.refresh_failed.
pulsemcp/mcp-servers/com.pulsemcp/gcs MCP server
81★ repoMCP server for Google Cloud Storage with fine-grained tool access control.
pulsemcp/mcp-servers/com.pulsemcp/fly-io MCP server
81★ repoMCP server for managing Fly.io machines, apps, logs, and Docker images.
pulsemcp/mcp-servers/com.pulsemcp/good-eggs MCP server
81★ repoMCP server for Good Eggs grocery shopping automation using Playwright.
pulsemcp/mcp-servers/com.pulsemcp/fetchpet MCP server
81★ repoMCP server for Fetch Pet insurance claims management using Playwright automation.
pulsemcp/mcp-servers/com.pulsemcp/gmail MCP server
81★ repoMCP server for Gmail with OAuth2 (personal) and service account (Workspace) support.
pulsemcp/mcp-servers/com.pulsemcp/google-calendar MCP server
81★ repoMCP server for Google Calendar integration with service account support and domain-wide delegation.
pulsemcp/mcp-servers/com.pulsemcp/google-flights MCP server
81★ repoMCP server for searching Google Flights — flight search, date grid pricing, and airport lookup.
pulsemcp/mcp-servers/com.pulsemcp/google-docs MCP server
81★ repoMCP server for Google Docs integration with OAuth2 and service account support.
pulsemcp/mcp-servers/com.pulsemcp/image-diff MCP server
81★ repoMCP server for programmatic image comparison and visual diff generation.
pulsemcp/mcp-servers/com.pulsemcp/hatchbox MCP server
81★ repoMCP server for Hatchbox Rails hosting — env var inspection, deploys, and process monitoring.
pulsemcp/mcp-servers/com.pulsemcp/monarch-money MCP server
81★ repoMCP server for Monarch Money — account, transaction, and budget management.
pulsemcp/mcp-servers/com.pulsemcp/langfuse MCP server
81★ repoMCP server for Langfuse LLM observability — trace and observation analysis.
pulsemcp/mcp-servers/com.pulsemcp/onepassword MCP server
81★ repoMCP server for interacting with 1Password via the CLI to read and manage credentials.
pulsemcp/mcp-servers/com.pulsemcp/pointsyeah MCP server
81★ repoMCP server for searching award flights and travel deals via PointsYeah.
pulsemcp/mcp-servers/com.pulsemcp/proctor MCP server
81★ repoMCP server for running Proctor exams against MCP servers with exam execution and result management.
pulsemcp/mcp-servers/com.pulsemcp/pulse-fetch MCP server
81★ repoMCP server for fetching web resources with content extraction and anti-bot bypass.
pulsemcp/mcp-servers/com.pulsemcp/pulse-subregistry MCP server
81★ repoMCP server providing access to the PulseMCP Sub-Registry for browsing and discovering MCP servers.
pulsemcp/mcp-servers/com.pulsemcp/remote-filesystem MCP server
81★ repoMCP server for remote filesystem operations on cloud storage (Google Cloud Storage).
pulsemcp/mcp-servers/com.pulsemcp/svg-tracer MCP server
81★ repoMCP server for converting bitmap images to SVG vector graphics using potrace tracing.
pulsemcp/mcp-servers/com.pulsemcp/serpapi-hotels MCP server
81★ repoMCP server for searching Google Hotels via SerpAPI — hotel search, pricing, ratings, and reviews.
pulsemcp/mcp-servers/com.pulsemcp/s3 MCP server
81★ repoMCP server for AWS S3 with fine-grained tool control and S3-compatible endpoint support.
pulsemcp/mcp-servers/com.pulsemcp/twist MCP server
81★ repoMCP server for Twist team messaging — manage channels, threads, and messages.
pulsemcp/mcp-servers/com.pulsemcp/vercel MCP server
81★ repoMCP server for Vercel — manage deployments and view build and runtime application logs.
pulsemcp/mcp-servers/com.pulsemcp/ssh MCP server
81★ repoMCP server for SSH remote server management with SSH agent authentication support.
pulsemcp/mcp-servers/com.pulsemcp/slack MCP server
81★ repoMCP server for Slack — read/write messages, manage threads, and react to messages.
KerberosClaw/kc_ai_skills/goal-engineer Skill
80★ repoUse when the user wants to AUTHOR an unattended dispatch for either: (1) a goal-driven evaluator-optimizer loop of the GENERATE-AND-SELECT kind (generate candidates → grade against a rubric → iterate by reason-code → keep the best; the human picks the final selection), or (2) a lean build-to-spec run whose build spec is ALREADY FROZEN (approved ADR / locked design / accepted machine-checkable AC) and the only missing piece is the unattended-execution wrapper. A fresh-session agent runs the dispatch hands-off while the human only watches traffic-light push notifications. Interview-style forcing questions lock the spec, then it emits a self-contained dispatch markdown + a channel-agnostic notification protocol. This is the upstream SPEC AUTHOR, NOT a runtime: the dispatch is run by Claude Code's /goal, a headless `-p` session, or any unattended agent — /goal is the engine, this writes what you feed it. It NEVER authors build specs, product decisions, or AC — creating a build spec / PRD from raw input is prd-create. NOT a time scheduler (/loop or cron), NOT a recurring-push registrar (skill-cron).
KerberosClaw/kc_ai_skills/gpt-image-gen Skill
80★ repoUse when the user asks to generate an image via GPT/Codex (e.g. 「叫 gpt 生圖」「幫我用 gpt 生圖」「gpt 畫一個 X」). The skill drafts a Chinese + English prompt pair, iterates with the user until they explicitly approve, then dispatches Codex CLI ($imagegen skill, codex built-in image_gen) in the background, monitors progress, converts the result to a jpg in the current working directory, and writes a sidecar prompt log. Does text-to-image AND img2img — drop a reference image (on-disk file) and it runs Codex `-i` to lock a face/character across scenes.
KerberosClaw/kc_ai_skills/llm-benchmark Skill
80★ repoUse when the user wants to test, compare, or choose local Ollama models for their machine. Checks Ollama/GPU state, recommends model sizes from available VRAM, preserves existing benchmark records, pulls only approved models, runs repeatable benchmarks, restores stopped services, and writes a markdown comparison report. NOT for hosted API model evaluation or subjective chat-quality judging without local benchmark commands.
KerberosClaw/kc_ai_skills/llm-wiki-lint Skill
80★ repoUse when the user wants to lint a repo following the Karpathy LLM Wiki pattern (raw/ + wiki/ + SCHEMA.md / index.md / log.md). The skill detects path, scans wiki pages + schema layer, reports frontmatter gaps, broken in-body links, source traceability breaks, stale claims, orphan pages, index synopsis contradictions, and SCHEMA-vs-reality drift. Phase 1 is read-only report; Phase 2 (fix + log.md LINT entry) only runs after the user explicitly approves.
KerberosClaw/kc_ai_skills/memory-lint Skill
80★ repoUse when the user wants to lint a Claude Code memory directory (~/.claude/memory or custom path) for index inconsistency, stale project state, duplicate / conflicting feedback rules, naming convention violations, frontmatter gaps, and oversized files. The skill detects path, scans root-level *.md, reports findings by severity. Read-only — never auto-fixes, never deletes, never merges.
KerberosClaw/kc_ai_skills/prd-create Skill
80★ repoUse when user wants to draft a PRD (Product Requirements Document) from raw input (meeting transcripts, hand-waved descriptions, scattered decisions). Workflow: load org's PRD Guideline + writing discipline → lock execution mode (human-run vs unattended-agent-run) → ingest raw input → quiz user numbered-list iterate to fill §1-§15 → draft v0.1 → handle stakeholder merge (review feedback, surface conflicts) → lock v1.0 + sanitize per ADO publication contract → publish to ADO Wiki. For an agent-run PRD, §13 carries the unattended-execution discipline (machine-checkable AC + traffic-light + 3-exits + stop-and-ask), aligned with goal-engineer's loop-run-protocol. NOT for packaging an ALREADY-FROZEN build spec (approved ADR / locked design / machine-checkable AC) into an unattended dispatch — that is goal-engineer's lean build dispatch. Pure prompt-driven — Claude is the runtime, no Python helper. Trigger phrases: 寫 PRD / PRD 撰寫 / prd-create / 初版 PRD / 起 PRD.
Running claude code via litellm copilot
xixu-me/skills/skills/running-claude-code-via-litellm-copilot Skill
79★ repoUse when routing Claude Code through a local LiteLLM proxy to GitHub Copilot, reducing direct Anthropic spend, configuring ANTHROPIC_BASE_URL or ANTHROPIC_MODEL overrides, or troubleshooting Copilot proxy setup failures such as model-not-found, no localhost traffic, or GitHub 401/403 auth errors.
The same file is in 1 other repository