Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Agent workflows
When the user wants to build or improve a sales bot's ability to keep exchanges natural while progressing toward outcomes. Also use when the user mentions "conversation design," "dialog flow," "bot conversations," "natural conversations," or "guided conversations."
Write, rewrite, or refresh an AGENTS.md (repo root or one package/module) from the actual codebase — Always / Ask First / Never / Validation Commands rules, task checklists, real paths and commands. Follows a repo template when present, else a built-in default. Use for "write AGENTS.md for this package", "rewrite our AGENTS.md", "refresh AGENTS.md".
Connects and configures the Render MCP server for AI coding tools—setup per tool (Cursor, Claude Code, Codex), authentication, workspace selection, capability discovery, and troubleshooting. Use when MCP is not configured, list_services() fails, the user asks about Render MCP setup, or an action skill needs MCP but it's not connected yet. Trigger terms: MCP, Render MCP, list_services, MCP setup, MCP server, OAuth, API key, Bearer token, mcp.render.com, workspace selection.
Check and update installed Claude Code skills from multiple sources (Claude plugins and npx skills). Scans for available updates, supports batch or individual updates with intelligent local change merging, and recommends popular skills from skillsmp.com and skills.sh marketplaces. Use when users want to update skills, check for new versions, discover trending skills, or manage their skill collection.
Installs, configures, audits, and operates Agent Package Manager (APM) in repositories. Use when initializing apm.yml, installing or updating packages, validating manifests, managing lockfiles, compiling agent context, browsing MCP servers, setting up runtimes, or packaging resolved context for CI and team distribution. Don't use for writing a single skill by hand, generic package managers like npm or pip, or non-APM agent configuration systems.
Authors and structures professional-grade agent skills following the agentskills.io spec. Use when creating new skill directories, drafting procedural instructions, or optimizing metadata for discoverability. Don't use for general documentation, non-agentic library code, or README files.
Make the agent report results to the user by the ASD-STE100 (Simplified Technical English) principles, in Chinese: key information first, one word one meaning, one fact per sentence, fixed status words, honest verification state, short sentences. Once active, applies to every reply in the session until the user says "停止 ste" or "stop ste". 让 Agent 按 ASD-STE100 原则用中文向用户汇报结果. Trigger: "/ste", "用 STE 规范输出", "按 ASD-STE100 汇报", "简化技术中文", "report in STE style".
Cangjie · Cognitive implantation: Drop in materials (books/interviews/articles/PDFs) to automatically distill a person's thinking Skill. It extracts not “what they said,” but “why they think that way”—belief-formation stories, real decisions, lessons from failure, and inner contradictions. Trigger phrases: “Cangjie,” “distill XX,” “make a thinking Skill for XX,” “extract with Cangjie,” “help me distill.” Trigger whenever the user uploads someone's materials (books/speeches/interviews) and wants to extract their way of thinking.
Installs, configures, audits, and operates Agent Package Manager (APM) in repositories. Use when initializing apm.yml, installing or updating packages, validating manifests, managing lockfiles, compiling agent context, browsing MCP servers, setting up runtimes, or packaging resolved context for CI and team distribution. Don't use for writing a single skill by hand, generic package managers like npm or pip, or non-APM agent configuration systems.
Deepgram API reference for speech-to-text, text-to-speech, voice agents, audio intelligence, and account management. Use whenever building with Deepgram APIs — REST or WebSocket. Covers authentication, all endpoints, query parameters, request/response schemas, and WebSocket message formats. Reference files are organized by domain: listen (STT — Nova and Flux STT), speak (TTS — Aura and Flux TTS), agent (voice agents), read (text/audio intelligence), models, projects, auth, and self-hosted
Update skills, migrate skill copies left in the working repository, and compare canonical skills, symlinks, and the skill list. Defines how to check and update home skills with npx skills, suggest removing philtzjp/skills copies, handle local modifications, and check consistency between repository-specific skills and philtzjp/skills. Use when starting work, pulling skills from upstream again, finding a skill in .agents/skills or .claude/skills with the same name as one in philtzjp/skills, or adding, deleting, or renaming skills.
This skill should be used when the user asks to "analyze skill quality", "evaluate this skill", "review skill quality", "check my skill", or "generate quality report". Evaluates local skills across description quality, content organization, writing style, and structural integrity.
Browser 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. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.
Authors, reviews, installs, and debugs GitHub Agentic Workflows in repositories, including workflow markdown, frontmatter, gh aw compile and run flows, safe outputs, security guardrails, and operational patterns. Use when creating or maintaining GH-AW automation. Don't use for standard deterministic GitHub Actions YAML, generic CI pipelines, or non-GitHub automation systems.
Authors and structures professional-grade agent skills following the agentskills.io spec. Use when creating new skill directories, drafting procedural instructions, or optimizing metadata for discoverability. Don't use for general documentation, non-agentic library code, or README files.
Decompose a PRD and/or SPEC into implementable, vertically sliced Issues with real blocking edges, then create them in your chosen platform (GitHub or Local). Use after /prd (and optionally /prd-to-spec) to turn requirements into agent-ready tickets. Triggers on: create issues, to-issues, 创建issue, 拆解issue, 生成卡片, 创建卡片, generate issues from PRD, issues from spec.
Turn a real agent failure into one reproducible eval-harness case plus the smallest knowledge change — failing case first, one knowledge owner, semantic assertions, before/after evidence through the repo's configured harness commands. Use for "add harness case", "agent got this wrong", "extend the harness", "rozszerz harness".
Build AI agents that interact with computers like humans do - viewing screens, moving cursors, clicking buttons, and typing text. Covers Anthropic's Computer Use, OpenAI's Operator/CUA, and open-source alternatives. Critical focus on sandboxing, security, and handling the unique challenges of vision-based control. Use when: computer use, desktop automation agent, screen control AI, vision-based agent, GUI automation.
Read-only router for "which skill should I use?", "what do I do next?", "how do I do X here?". Builds the answer at run time from the repo's AGENTS.md Task Router, the skills actually installed, optional repo workflow data, and knowledge sources — then recommends and hands back control. Never runs the pipeline itself.
LLM-as-judge for a coding-agent session or an eval-harness result — checks controller attestations first, then project guards, code review, and the repo's design contract, and names the smallest harness owner to fix. Read-only; never executes session content. Use for "judge this session", "analyze this eval", "oceń sesję/agenta".
Publicly share a sanitized coding-agent session plus a ZIP of the files it generated, then file a harness-feedback issue at the configured destination — local sanitization, full privacy review, exact fresh consent first. Use for "share this session", "report this agent run", "udostępnij tę sesję". Never for telemetry or without consent.
Use when creating or editing skills, before deployment, to verify they work under pressure and resist rationalization. Applies the RED-GREEN-REFACTOR cycle to process documentation by running a baseline without the skill, writing to address failures, and iterating to close loopholes.
A contract for what the agent does when a long, messy, stream-of-consciousness ramble arrives (usually voice dictation): act on nothing until the echo brief is approved. The echo audits the entire transfer, mission, locked decisions and constraints, open questions, flips and parked tangents, with the model's inferences and guesses quarantined away from the user's own phrasing, so the user verifies what the model believes, not just what it doubts. Use when the user says "let me think out loud" or wants to ramble a bit before building anything, when a message opens with a speech-to-text preamble like "switching to voice, sorry for typos", when input is a long weakly punctuated stream with restarts and mid-message reversals ("actually no, wait, scrap that idea entirely"), or when the user asks to be interviewed about a fuzzy half-formed idea. Includes an optional capture mode for rambles spread across several messages and an optional targeted interview
Use when creating or editing any prompt (commands, hooks, skills, subagent instructions) to verify it produces desired behavior. Applies the RED-GREEN-REFACTOR cycle to prompt engineering using subagents for isolated testing.
Create, validate, and enrich Open Knowledge Format (OKF) bundles — the open spec for representing organizational knowledge as markdown files with YAML frontmatter. Use when the user mentions 'OKF', 'Open Knowledge Format', 'knowledge bundle', 'OKF bundle', 'create a knowledge base for agents', 'validate OKF', 'convert to OKF', 'enrich knowledge docs', 'agent-readable knowledge', 'LLM wiki', 'knowledge catalog', 'kcmd', or wants to structure knowledge as markdown files for AI agent consumption. Also use when the user has a directory of markdown files and wants to make them interoperable or conformant with the OKF standard. Even for simple requests like 'make this folder OKF conformant' — the skill has critical structural rules the agent needs.
Propose skill improvements to the canonical repository. Defines how to proceed when a skill does not work as expected, web searches or other sources provide conflicting or newer information, or strict adherence to the skill’s conditions would not produce the best result. Covers not editing skills installed in the home directory directly, routing proposals, and Issue title and body templates. Use when questioning skill content or proposing improvements.
Decide which skills to install. Defines default skills for everyone, skills to add based on the work, installing and removing home skills with npx skills, deciding not to install superseded skills that have been integrated, and whether to include repository-specific skills. Use when installing skills for the first time, when a new skill is added to philtzjp/skills, when a required skill is missing, or when removing an unneeded skill.
Use when the user asks about WordPress codebases (plugins, themes, block themes, Gutenberg blocks, WP core checkouts) and you need to quickly classify the repo and route to the correct workflow/skill (blocks, theme.json, REST API, WP-CLI, performance, security, testing, release packaging).
Design, implement, and debug autonomous AI agents and multi-agent systems using the Google Antigravity (AGY) SDK. ACTIVATE this skill when the user wants to create, configure, or orchestrate Google Antigravity agents.
Generate a HANDOFF.md that captures the goal, current state, files touched, failed attempts, and next steps so a fresh Claude session can continue exactly where this one left off. Use when sessions are getting long, Claude keeps retrying the same broken solution, or the user wants to step away and resume later.
Use quando uma spec em draft, defined, planned, in-progress ou review precisar de conversa para resolver lacunas, recalibrar Effort ou registrar respostas confirmadas antes da próxima transição. Não use para capturar Inbox sem perguntas, executar implementação, aprovar gates ou mover pastas diretamente.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.