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
LuckyOneTwoThree/pm-skill/pm-08-project/orchestrators/risk-orchestrator Skill
no license6★ repo当需要识别项目风险或处理风险升级时使用。风险管理指挥官,调度 risk-identification、risk-management 子Skill执行。关键词:风险管理、风险识别、风险监控、风险升级、风险登记册、风险预警、应急升级、项目风险。
northseadl/norix-skills/agent-front-design Skill
no license6★ repoFrontend design blueprints with craftsmanship scoring, self-critique loops, and engineering handoff. Aesthetic intelligence against AI homogeneity. Use for: UI/UX design specs, design system creation, visual direction exploration, component design review, design-to-engineering handoff.
northseadl/norix-skills/agent-swe-team Skill
no license6★ repoMulti-agent SWE team built on the Workshop model. Full-stack vertical workers, meeting room with @mention notification, private pipes, shared task board. Git worktree isolation, Leader-driven coordination. Mixed Codex/Claude Code engine. Use when a task needs engineering depth beyond a single agent. NOT for simple task parallelism (use agent-task-orchestration) or design discussions (use agent-brainstorm).
northseadl/norix-skills/agent-task-orchestration Skill
no license6★ repo'Task decomposition and multi-agent orchestration with retry, checkpoint recovery, and real-time monitoring.
northseadl/norix-skills/llm-agent-dev Skill
no license6★ repo'LLM Agent engineering: pattern selection (12-mode matrix), data simulation, convergence iteration.
keithhegit/ultra-orchestration/skills/openspec-ultra-bridge Skill
6★ repoBridge OpenSpec change artifacts into Ultra-Orchestrator execution artifacts. Use when a repo follows OpenSpec for proposal, design, tasks, and archive, but execution should remain controlled by Ultra-Orchestrator through TaskManifest, WorkPackage, review, QA, risk gates, and ledger-based orchestration.
keithhegit/ultra-orchestration/skills/ultra-orchestrator-legacy Skill
6★ repoLegacy compatibility entry point for the original Ultra Orchestrator flow. Use only when you need the older lightweight stage-based orchestration behavior without the new strict OpenSpec-first control plane.
keithhegit/ultra-orchestration/skills/ultra-orchestrator Skill
6★ repoPrimary Ultra Orchestration entry point for strict Codex-controlled engineering runs. Use this single skill for development, bug fixes, OpenSpec work, multi-file implementation, review/QA-heavy tasks, risk-gated work, or any run that needs automatic mode selection, OpenSpec bootstrap, machine-checkable TaskManifest and WorkPackage artifacts, ledger tracking, slice DAG execution, review, QA, delivery evidence, and retro.
Unique-Divine/jiyuu/ai-skills/new-chat-prompt Skill
6★ repoWrites a ready-to-paste prompt for a fresh chat instead of completing the requested task directly. Use when the user asks to start a new chat, move work to a new chat, or says to write a prompt for tackling the task elsewhere.
Unique-Divine/jiyuu/ai-skills/new-skills Skill
6★ repoCreate new skills, modify and improve existing skills, and run lightweight review loops. Use when users want to create a skill from scratch, edit an existing skill, try realistic test prompts, or improve when and how a skill should trigger.
DanielC000/loom/packages/daemon/assets/skills/orchestrate Skill
6★ repoThe operating doctrine for a Loom lead / orchestrator (manager) session. Load at the start of any orchestrator agent to run the lead-manages-workers loop — plan, decompose, delegate, review, merge, recycle — over the loom-orchestration tools. Your agent prompt supplies the project-specifics; this is the cross-project HOW.
HK-hub/AgentSkills/agent-browser Skill
6★ repoBrowser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
HK-hub/AgentSkills/agent-development Skill
6★ repoThis skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
The same file is in 7 other repositories
HK-hub/AgentSkills/build-mcp-app Skill
6★ repoThis skill should be used when the user wants to build an "MCP app", add "interactive UI" or "widgets" to an MCP server, "render components in chat", build "MCP UI resources", make a tool that shows a "form", "picker", "dashboard" or "confirmation dialog" inline in the conversation, or mentions "apps SDK" in the context of MCP. Use AFTER the build-mcp-server skill has settled the deployment model, or when the user already knows they want UI widgets.
The same file is in 2 other repositories
HK-hub/AgentSkills/build-mcp-server Skill
6★ repoThis skill should be used when the user asks to "build an MCP server", "create an MCP", "make an MCP integration", "wrap an API for Claude", "expose tools to Claude", "make an MCP app", or discusses building something with the Model Context Protocol. It is the entry point for MCP server development — it interrogates the user about their use case, determines the right deployment model (remote HTTP, MCPB, local stdio), picks a tool-design pattern, and hands off to specialized skills.
The same file is in 2 other repositories
HK-hub/AgentSkills/build-mcpb Skill
6★ repoThis skill should be used when the user wants to "package an MCP server", "bundle an MCP", "make an MCPB", "ship a local MCP server", "distribute a local MCP", discusses ".mcpb files", mentions bundling a Node or Python runtime with their MCP server, or needs an MCP server that interacts with the local filesystem, desktop apps, or OS and must be installable without the user having Node/Python set up.
The same file is in 2 other repositories
HK-hub/AgentSkills/claude-automation-recommender Skill
6★ repoAnalyze a codebase and recommend Claude Code automations (hooks, subagents, skills, plugins, MCP servers). Use when user asks for automation recommendations, wants to optimize their Claude Code setup, mentions improving Claude Code workflows, asks how to first set up Claude Code for a project, or wants to know what Claude Code features they should use.
The same file is in 4 other repositories
HK-hub/AgentSkills/claude-md-improver Skill
6★ repoAudit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project memory optimization".
The same file is in 6 other repositories
HK-hub/AgentSkills/dispatching-parallel-agents Skill
6★ repoUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
The same file is in 15 other repositories
HK-hub/AgentSkills/hook-development Skill
6★ repoThis skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.
The same file is in 9 other repositories
HK-hub/AgentSkills/mcp-builder Skill
6★ repoGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
The same file is in 42 other repositories
HK-hub/AgentSkills/mcp-integration Skill
6★ repoThis skill should be used when the user asks to "add MCP server", "integrate MCP", "configure MCP in plugin", "use .mcp.json", "set up Model Context Protocol", "connect external service", mentions "${CLAUDE_PLUGIN_ROOT} with MCP", or discusses MCP server types (SSE, stdio, HTTP, WebSocket). Provides comprehensive guidance for integrating Model Context Protocol servers into Claude Code plugins for external tool and service integration.
The same file is in 10 other repositories
HK-hub/AgentSkills/saga-orchestration Skill
6★ repoImplement saga patterns for distributed transactions and cross-aggregate workflows. Use when coordinating multi-step business processes, handling compensating transactions, or managing long-running workflows.
HK-hub/AgentSkills/skill-creator Skill
6★ 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
HK-hub/AgentSkills/skill-lookup Skill
6★ repoActivates when the user asks about Agent Skills, wants to find reusable AI capabilities, needs to install skills, or mentions skills for Claude. Use for discovering, retrieving, and installing skills.
The same file is in 2 other repositories
Mozurok/fhorja.dev/.claude/skills/compact-task-memory Skill
6★ repoProduce a lossy compaction summary of TASK_STATE.md when task memory has grown beyond a useful working size, preserving canonical decisions and recommended next step while dropping stale facts. Distinct from sync-task-state (incremental, append-only, never lossy) and state-reconcile (drift repair, no shrinking). Use when task memory has accumulated across multiple slices (5+ completed) and feels heavy, the resume cost is growing as the file scales, the current known facts list is full of resolved or routine entries, or before a session pause where a slim TASK_STATE will speed restart. Do not use when the task is still in early discovery (memory is small), the artifacts disagree across files (use state-reconcile first), an incremental sync would be sufficient (use sync-task-state), or no active task folder exists yet (run task-init first).
Mozurok/fhorja.dev/.claude/skills/db-context-supabase Skill
6★ repoValidate that a Supabase MCP server is reachable, introspect a user-scoped subset of the database (tables, columns, types, RLS policies, optionally functions and recent migrations), and persist the result as DB_CONTEXT.md inside the active task folder; adds a single ## DB context cross-link in SOURCE_OF_TRUTH.md. Read-only introspection only; never destructive SQL. Opt-in, not part of default task init. Use when the active task touches Supabase data/schema/RLS, when planning or implementation needs verified schema rather than assumed schema, or when an existing DB_CONTEXT.md is stale. Do not use without an active task folder (run task-init first), when the task does not touch Supabase, when the database is not Supabase, or when the user wants to record a schema decision (use decision-interview).
Mozurok/fhorja.dev/.claude/skills/external-research-fleet Skill
6★ repoOrchestrator-workers variant of external-research for multi-modal sweep across distinct angles or source-groups of one research question. Promotes external-research's inline delegation to a first-class orchestrator with a worker contract and provenance. Sonnet orchestrator dispatches N Sonnet workers (one angle each) in parallel; each produces a structured per-angle synthesis grounded in REFERENCES.md; orchestrator merges into a single EXTERNAL_RESEARCH.md with cross-angle reconciliation (reinforcing vs contradicting vs different-framing). Use when the research question has N >= 3 distinct angles or source-groups AND the question would benefit from parallel deep reads. Do not use when 1-3 sources suffice (use external-research inline), when one source already dominates (no parallelism gain), or when sources have not yet been captured (run capture-references first).
Mozurok/fhorja.dev/.claude/skills/implement-fleet Skill
6★ repoOrchestrator-workers variant of implement-approved-slice that executes independent approved slices in parallel. Reads per-slice Scope and Depends-on from IMPLEMENTATION_PLAN.md, builds the slice DAG, computes parallelizable waves (ready slices whose file scopes are pairwise disjoint with no shared migration, lockfile, codegen, or barrel export), validates disjointness before dispatch, runs one worktree-isolated worker per slice per wave (each executing the implement-approved-slice contract), merges the worktrees, and runs a mandatory build + typecheck + test integration gate after each wave. Use when the active task has an approved multi-slice plan whose Execution waves show at least one wave of size 2 or more. Do not use when the slice DAG is a pure chain (use implement-approved-slice), when slices are unapproved, when Scope/Depends-on are not declared in the plan, or for single-slice tasks.
Mozurok/fhorja.dev/.claude/skills/mcp-server-vet Skill
6★ repoRead-only safety inspection of a third-party MCP server BEFORE it is added to a config or trusted. Reads the server's declared tool descriptions, input schemas, scopes, transport, and env/secret surface (not just its README), compares declared behavior against what the tools actually expose, scans for tool-description poisoning and prompt injection, over-broad or undeclared scopes, egress and credential access, config tampering, and hidden Unicode, and returns an add/decline/sandbox verdict for a human to approve. Never installs, never auto-trusts. Use when evaluating an external MCP server before adding it to .mcp.json or enabling it. Do not use to vet a third-party agent skill or plugin (use skill-vet), to review first-party product code (use review-hard or security-review), or to fetch a remote server definition from the web (record its origin via capture-references, then obtain a local copy out of band into a quarantine directory first).
Mozurok/fhorja.dev/.claude/skills/prompt-shape Skill
6★ repoShape the best possible prompt for the current task and workflow phase. Aligns the prompt content with the intended editor mode and the chosen command's required inputs, producing a copy-paste-ready handoff. Use when prompt precision would materially improve the next workflow action, the next step is known but the current prompt or context is too vague or broad or missing required inputs for the chosen command, or the user wants a copy-paste-ready prompt aligned with the intended editor mode. Do not use when the existing prompt is already scoped and explicit and phase-appropriate (return a no-op and route forward instead), the real blocker is missing facts or undecided policy (use targeted-questions or decision-interview), the real need is recovery from loop or confusion (use im-stuck), or the real need is pedagogical explanation of the current phase (use workflow-guide).
Mozurok/fhorja.dev/.claude/skills/verify-against-rubric Skill
6★ repoSpawn a stateless sub-agent (Claude Code Task tool, Cursor agent mode, or equivalent) with ONLY the artifact path plus the locked rubric plus read-only tools. Sub-agent returns a structured verdict (satisfied, needs_revision, or failed) plus per-criterion feedback. Distinct from self-critique-and-revise (same-context; rewrites in place). Use after pr-package, contract-signoff, or implement-approved-slice on HIGH-complexity slices when independent verification matters more than throughput. Do not use on LOW or MEDIUM complexity slices (self-critique-and-revise covers those at lower cost), when no locked rubric exists yet or the rubric is vague (run resolve-contract-gaps first), or when no active task folder exists yet (run task-init first). For 4 or more artifacts against one rubric, use verify-against-rubric-fleet.
sarveshsea/design-skills/skills/agent-messaging-gateway Skill
6★ repoDesign gateway-backed agent delivery through chat, email, and team messaging channels.
sarveshsea/design-skills/skills/agent-session-checkpoints Skill
6★ repoCapture restartable agent sessions with checkpoints, rollback notes, and resume metadata.
sarveshsea/design-skills/skills/agent-skill-migration Skill
6★ repoMove skills, memories, context files, and agent rules between Memoire and peer agent ecosystems.
sarveshsea/design-skills/skills/browser-research-agent Skill
6★ repoCompatibility workflow for browser-backed evidence capture. Deprecated: use web-research for primary-source research, citations, freshness, and gap analysis.
sarveshsea/design-skills/skills/cron-agent-workflows Skill
6★ repoTurn repeatable agent work into scheduled jobs with explicit outputs and safe permissions.
sarveshsea/design-skills/skills/docker-environments Skill
6★ repoDocker-aware Mémoire operation — CI/CD headless pipelines, shared MCP server, agent worker containers, and Figma bridge port-forwarding for containerized setups
sarveshsea/design-skills/skills/figma-ds-rules Skill
6★ repoRoute generation of Figma-aware repository rules to Figma's current official MCP workflow without reproducing upstream instructions. Use when AGENTS.md, CLAUDE.md, or client rules must reflect verified Figma and codebase conventions.
sarveshsea/design-skills/skills/hermes-agent-bridge Skill
6★ repoRun Hermes Agent from Memoire with CLI, skills, toolsets, worktree, and session recipes.
sarveshsea/design-skills/skills/mcp-server-studio Skill
6★ repoExpose Memoire Studio context, tools, and artifacts to other agents through MCP.
sarveshsea/design-skills/skills/memoire-design-tooling Skill
6★ repoSet up and operate Mémoire's CLI, MCP server, agent kits, design preflight, UX audits, craft checks, tokens, and registry evidence. Use when a repository explicitly needs Mémoire tooling; use portable design skills when Mémoire is unavailable.
sarveshsea/design-skills/skills/memoire-mcp-agent-skills Skill
6★ repoCompatibility setup workflow for memi MCP and Agent Skills. Deprecated: use memoire-design-tooling for installation, preflight, audits, and agent-client configuration.
sarveshsea/design-skills/skills/multi-agent-kanban Skill
6★ repoCoordinate multiple local agents through a durable board with owner, state, and evidence fields.
sarveshsea/design-skills/skills/multi-agent Skill
6★ repoOrchestrate multiple Claude instances on Figma canvas with box widgets, coordinated handoffs, error recovery
sarveshsea/design-skills/skills/openclaw-agent-bridge Skill
6★ repoConnect Memoire to OpenClaw onboarding, agents, gateway health, MCP, and approval flows.
sarveshsea/design-skills/skills/self-improving-agent Skill
6★ repoClosed-loop learning system — captures errors, corrections, and discoveries into structured logs, promotes recurring patterns to project memory, and extracts reusable skills
dolutech/dolu-agents-skills/skills/skill-creator Skill
6★ 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 6 other repositories
IchenDEV/prompt-optimizer-plugins/plugins/optimize-gpt-5-6-prompts/skills/optimize-gpt-5-6-prompts Skill
6★ repoClarify, audit, and rewrite rough or existing prompts for GPT-5.6 Sol and the GPT-5.6 family using OpenAI's official prompting guidance. Use when a user asks to optimize, improve, rewrite, debug, migrate, or design a GPT-5.6 prompt, including requests phrased as GPT-5.6 提示词优化, or when an underspecified prompt needs guided clarification before a copy-ready rewrite. Ask only for missing information that would materially change the result; otherwise preserve intent and produce a lean, outcome-first prompt with explicit constraints, output requirements, and completion criteria.
mikeng-io/agent-skills/skills/bridge-claude Skill
no license6★ repoReference adapter for Claude (Anthropic) dispatch. Read by any orchestrating skill via the Read tool. Defines how to invoke Claude sub-agents or the Anthropic API, with availability checks. Usable by any AI orchestrator — Claude Code, OpenCode, Codex, Gemini, or custom agents.
mikeng-io/agent-skills/skills/bridge-codex Skill
no license6★ repoReference adapter for Codex multi-agent review. Read by any orchestrating skill via the Read tool. MCP server path (preferred) with auto-setup option, CLI path as fallback, interactive pre-flight advisory when not configured, correct flags embedded. Usable by deep-council, deep-review, deep-audit, or any future skill that needs Codex-based review.
mikeng-io/agent-skills/skills/deep-council Skill
no license6★ repoCouncil-of-councils orchestrator. Dispatches discovery-first packets to bridge adapters (Claude, Gemini, Codex, OpenCode), each of which runs a local Agent/Model/Runtime Council, then performs cross-council debate using debate-protocol. Supports review, audit, research, and brainstorm/design modes.
mikeng-io/agent-skills/skills/deepwiki Skill
no license6★ repoOptional codebase intelligence skill — wraps Devin's DeepWiki MCP server to provide structured documentation lookup, topic discovery, and natural-language Q&A about any GitHub repository indexed by Devin. Supports public and private repositories (private requires Devin API key). Falls back gracefully to Glob/Grep/Read + QMD if not configured. Invokable standalone or called by other skills as a data source.
kylebrodeur/1password-ssh-setup/packages/pi-1password/skills/ssh-agent Skill
no license6★ repoSSH agent management with 1Password for passphrase handling and keychain integration. Use when working with SSH keys on Linux/WSL/Windows. Features keychain-based key persistence and 1Password-stored passphrases for secure, passwordless SSH operations.
pengzhangzhi/superpowers-ml/skills/subagent-driven-development Skill
6★ repoUse when executing implementation plans with independent tasks in the current session
martgueritainaccurate875/skills/skills/vision-analysis Skill
6★ repoAnalyze, describe, and extract information from images using the MiniMax vision MCP tool. Use when: user shares an image file path or URL (any message containing .jpg, .jpeg, .png, .gif, .webp, .bmp, or .svg file extension) or uses any of these words/phrases near an image: "analyze", "analyse", "describe", "explain", "understand", "look at", "review", "extract text", "OCR", "what is in", "what's in", "read this image", "see this image", "tell me about", "explain this", "interpret this", in connection with an image, screenshot, diagram, chart, mockup, wireframe, or photo. Also triggers for: UI mockup review, wireframe analysis, design critique, data extraction from charts, object detection, person/animal/activity identification. Triggers: any message with an image file extension (jpg, jpeg, png, gif, webp, bmp, svg), or any request to analyze/describ/understand/review/extract text from an image, screenshot, diagram, chart, photo, mockup, or wireframe.
The same file is in 3 other repositories
ahgraber/skills/skills/handoff Skill
6★ repoUse when ongoing work must continue in a new conversation, session, or agent with no shared history. Triggers: 'handoff', 'prepare context for next chat', 'summarize for a new session', 'continue this in another conversation'. Not for same-chat status updates or repository documentation.
ahgraber/skills/skills/mcp-research Skill
6★ repoUse when tasks require current, source-backed technical information from MCP tools. Apply for library/API questions, dependency version checks, third-party integration work, framework- or SDK-specific debugging, and any case where stale model knowledge could cause incorrect guidance.
ahgraber/skills/skills/subagent-patterns Skill
6★ repoUse when dispatching development work to one or more subagents and deciding how to shape each dispatch. Triggers: "use subagents", "orchestrate subagents", "delegate to a cheaper/stronger model", "big:little" / "little:big", "verifier / adversary / explorer / oracle subagent", "run this with subagents", "get an independent second opinion". Not for: the parallel code-review path (use `code-review`), or driving a separate agent CLI non-interactively.
dosev-ai/mcp-office/io.github.dosev-ai/mcp-office-powerpoint MCP server
6★ repo46-tool PowerPoint MCP server. Build, edit, and export .pptx files. Windows-first.