Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Agent workflows
Author a working Claude Code hook from a plain-English description of what it should guarantee or do. Describe the behavior (“never let the agent edit my migrations,” “don't stop until the tests pass,” “log every command”); this skill picks the right lifecycle event, writes the hook script, and wires it into .claude/settings.json. Use when you want a deterministic guarantee or automation in your AI Layer and don't want to write the hook by hand. The meta-tool for the hooks primitive.
Use this skill when an agent needs to write reusable code, store it in the configured Hermes Code folder, run it directly through local code execution, or host it behind a Make-managed E2B Code Shell scenario. Use for tool building, generated business automation scripts, and nested flows where hosted code calls Make API shell scenarios for SaaS access without receiving raw OAuth, Make, or E2B secrets.
Master orchestrator for a full SEO audit suite powered by the Ahrefs MCP. Use this skill when running a comprehensive SEO audit, scoping a quarterly health check, doing pre-acquisition SEO due diligence, or post-migration verification. Triggers on full SEO audit, comprehensive SEO review, SEO health check, audit my site, SEO due diligence, audit suite, comprehensive audit, end-to-end SEO. Also triggers when a stakeholder wants the complete picture rather than a single-dimension audit
Expert guide for designing and building high-quality skills from scratch through structured conversation. Use when someone wants to create a new skill, build a skill, design a skill, or asks for help making Agents do something consistently. Also use when someone says “turn this into a skill”, “I want to automate this workflow”, “how do I teach my Agent to do X”, or mentions creating SKILL.md files. Covers standalone skills and MCP-enhanced workflows. Do NOT use for creating subagents (use subagent-creator) or technical design documents (use create-technical-design-doc).
Expert project manager orchestrating backlog-curator, work-delegator, workstream-coordinator, and roadmap-strategist sub-skills. Coordinates complex software projects through delegation and strategic oversight. Activates when managing projects, coordinating work, or tracking overall progress.
Use when auditing or adapting newly created, downloaded, forked, installed, or community Agent Skills to the user's tools, habits, directories, session history, and preferred workflows, especially when triggers feel wrong, noisy, or too generic.
Advanced and operational chat.agent capabilities for Trigger.dev, loaded on demand. Load this when working on the raw Sessions primitive (sessions / SessionHandle), a custom chat transport or the realtime wire protocol, durable sub-agents (AgentChat, chat.stream.writer), human-in-the-loop, steering, actions, background injection (chat.defer / chat.inject), fast starts (preload, Head Start via @trigger.dev/sdk/chat-server), context resilience (compaction, recovery boot, OOM, large payloads), chat.local run-scoped state, offline testing with mockChatAgent, or prerelease/version upgrades. For the everyday chat.agent({...}) definition and the useTriggerChatTransport happy path, use the trigger-authoring-chat-agent skill instead.
**ANALYSIS SKILL** — Analyze any repository and generate AI-ready configuration — a canonical AGENTS.md, thin per-tool pointer files, skills, CI workflows, issue templates. WHEN: \"make this repo ai-ready\", \"set up AI config\", \"add copilot instructions\", \"prepare this repo for AI contributions\", \"generate AGENTS.md\". INVOKES: glob, grep, view, create, edit for repo analysis and file generation. FOR SINGLE OPERATIONS: use create/edit directly for individual config files.
Use this skill when building agent evaluation systems: deterministic checks, regression suites, multi-dimensional rubrics, quality gates, production monitoring, baseline comparison, and outcome measurement for agent pipelines
Meta-skill that generates new design language skills. Works on Claude Code and Codex. Use when the user says 'create a design skill', 'generate design language', 'new design system skill', 'design skill inspired by X', 'design skill from this screenshot', '/hue', or 'use hue'. Also triggers for 'remix my design skill' or 'make my skill more X'.
Determine which workflow recipe to run. Invoke before any of these: audits (docs vs. code, design vs. code, root cause, project direction); triaging or resolving review findings; PR review comments; turning a feature brief into a plan; getting a second-model verdict on a plan; implementing a spec; research or price comparisons that may take several rounds; “跑一輪審查,” “幫我找資料／比價,” “幫我 plan,” or “把 findings 處理掉.” After any audit finishes, invoke again to route its findings to triage. Invoke even if there is only a 1% chance it applies.
Deploy a 2-layer parallel agent hierarchy for large, parallelizable work — big refactors, multi-file migrations, codebase-wide audits, bulk generation. A top-tier commander (Fable or Opus) orchestrates the swarms; the user picks a power level (Max Power / Heavy / Balanced / Economy) that sets the Opus/Sonnet/Haiku model mix per layer. Layer 1 is 3-50+ specialist agents, each with its own full context window; Layer 2 is 2+ sub-agents per member. Includes git safety, tiered sizing, a pre-deploy gate, phantom-completion checks, and multi-wave follow-up.
Installs 425 bioinformatics skills covering sequence analysis, RNA-seq, single-cell, variant calling, metagenomics, structural biology, and 56 more categories. Use when setting up bioinformatics capabilities or when a bioinformatics task requires specialized skills not yet installed.
Design enterprise-grade agent systems with Microsoft's agent framework patterns: role separation, workflow control, policy boundaries, and observability. Use when users need robust organizational agent workflows, governance, and maintainable multi-agent architecture.
Check whether your rules file (CLAUDE.md or AGENTS.md) still matches the codebase after recent changes — run before a merge, or fold into your code-review pass. Reports stale/now-false rules, drifted architecture-map entries, and any new invariant worth adding, each with the minimal edit. Advisory and anti-bloat: it keeps the rules file true, never longer than it needs to be.
Which design skill, in what order. Invoke BEFORE any visual output: web page, landing page, dashboard, product UI, mobile screen, HTML report, diagram, chart, plan page, artifact, motion, redesign, 「做個頁面」, 「畫圖」, 「報告做成網頁」, plus module or API interface design. Picks one direction authority and an executor per stage, closes with an evidence check. Even a 1% chance means invoke it.
Read/write brain files (Obsidian vault at brain/). Use for any task that persists knowledge — reflection, planning, or direct edits. Triggers after debugging sessions, mistakes, corrections, architectural decisions, or any insight worth preserving across sessions. Use on 'add to brain', 'remember this', 'write a note', or brain/ modifications.
Use for vague whole-app design system asks on an app that already ships UI, like "our UI is a mess, fix it", "we need a design system", "we hardcode colors everywhere", "make the buttons consistent for an upstream PR", "document our whole design system" or "check the app before I ship". Triages the app, then runs the design.how skills in order. One named screen goes to ui-review, one component to component-docs, an empty repo to build-design-system
Create ShinkaEvolve task scaffolds from a target directory and task description, producing `evaluate.py` and `initial.<ext>` (multi-language). Use when asked to set up new ShinkaEvolve tasks, evaluation harnesses, or baseline programs for ShinkaEvolve
Create, manage, and query Databricks Genie Agents — curated, per-data natural-language agents (formerly Genie Spaces): build, export/import, migrate across workspaces, and ask questions of a specific Agent via the Conversation API. For general data questions or finding data across your workspace, use databricks-data-discovery (Genie One) instead
A constructive, evidence-based dialogue mode that avoids sycophancy. Use when the user wants balanced multi-perspective analysis, critical feedback, or rigorous challenge of their ideas. Triggered by “/balanced” or requests for honest, critical, or balanced feedback. Supports passive, interactive, tldr, steelman, and decision modes.
Write the canonical ai-env blueprint plan for a multi-step task (Step 3 of /task). Runs one brainstorming round, uses ai-workspace/plans/TEMPLATE.md, and writes ai-workspace/plans/<name>.md. Skipped for one-sentence scope. Does not review—that is /review (Step 4).
Build, edit, validate, publish, and deploy a MuleSoft Agent Broker (Agent Network V2) project end-to-end. Use whenever the user asks to build, create, scaffold, configure, edit, validate, publish, or deploy an Agent Broker, agent network V2, AgentScript, `.agent` file, or `agentNetwork: 2.0.0` project. Do NOT trigger for V1→V2 migration (use the converter skill).
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Comprehensive Mastra framework guide. Teaches how to find current documentation, verify API signatures, and build agents and workflows. Covers documentation lookup strategies (embedded docs, remote docs), core concepts (agents vs workflows, tools, memory, RAG), TypeScript requirements, and common patterns. Use this skill for all Mastra development to ensure you're using current APIs from the installed version or latest documentation.
Build and operate multi-tenant AI agent platforms on Neon. Use this skill whenever the user is designing an agent/app builder, provisioning a Neon project or database per user/app/agent run, managing thousands of tenant projects, separating sponsored free users from paid customers, moving projects between orgs, choosing `@neon/sdk` vs `@neon/tools`, choosing personal vs organization vs project-scoped API keys, tracking fleet consumption or Agent Plan costs, creating compound checkpoints that combine DB snapshots with source revisions/secrets/deploy metadata, or orchestrating snapshot/restore flows for generated apps. Also use it for Neon Agent Program, Agent Plan, org/project limits, HIPAA, co-marketing, support, or neondatabase/neon-for-agent-platforms examples.
ASD-STE100 Simplified Technical English, and a reply structure a reader with ADHD can act on. A standing style rule, not an on-request tool. Layer 1 governs the words of every text a human reads — chat replies, docs, READMEs, commit messages, PR text, code comments, error messages, release notes, tool descriptions, task trackers, wiki pages. Layer 2 governs the order of a reply to a person — the next action first, numbered steps, no preamble and no closer. Neither layer touches code, identifiers, or command syntax. Load it before writing prose, and also when asked to remove “AI slop”, make writing clear or plain, enforce a controlled style, or review text for STE violations. Two word modes — strict (procedures, runbooks, safety text, error messages) and STE-flavored (general prose, the default).
Use when planning software development tasks, before writing code or implementation plans — refines rough technical ideas into fully formed designs through collaborative questioning, alternative exploration, and incremental validation. For software architecture, components, data flow, and technical design decisions. Don't use during clear 'mechanical' coding processes.
5-dimension harness readiness scorecard from `metaharness score <path>`. Returns harnessFit / compileConfidence / taskCoverage / toolSafety / memoryUsefulness + estCostPerRunUsd + scaffoldReady. Read-only; invokes a subprocess; degrades gracefully when MetaHarness is absent (ADR-150 architectural constraint).
Original prompt for collaboration using the Johari Window. Use when the user wants to define how AI should collaborate, says responses don't meet their needs, complains about too many questions or guesses made without asking, or wants the AI to assess the state of information before responding. Trigger phrases include Johari Window, window, open area, blind spot, hidden area, unknown area, collaboration mode, don't guess what I need, and clarify before answering. Attach the full prompt at the beginning of a session or task to guide all subsequent collaboration.
Break a one-line idea into a task brief that an AI agent can execute independently. Use it when users say "write a goal for the agent", "break down this goal in detail", "write a brief for the agent", "write a goal prompt", "let the agent run this project", or "split the work across several agents in parallel". Test in the codebase, research online when needed, ask all questions in one go (≤5), and produce a ≤4000-character brief that can be pasted into /goal and run, including measured numbers, whitelist boundaries, anti-cheat acceptance criteria, and checkpoint resumption. Execution-type and exploration-type (research/selection/solution search) tasks are routed automatically
Knowledge and governance closeout: reconcile project docs, rule files (CLAUDE.md/AGENTS.md), authorized agent memory, and workspace residue with what the code and runtime actually do, so the next session or the next person starts from one current answer. Trigger when the user names "neat-freak", "洁癖", or "/neat" — and also on clear knowledge-closeout intent without the name: syncing or tidying project docs/rules/memory after development ("把文档和记忆整理一下", "收尾时把文档同步掉", "docs 和代码对不上了"), stale or conflicting CLAUDE.md/memory, a clean handoff to a teammate or a fresh session, or auditing whether workspace rules are actually followed. Do not trigger for pure coding/refactoring/debugging tasks, tidying data or prose (JSON, 周报, changelog announcements), or a bare "整理" with no project-knowledge context.
This skill should be used when the user asks to "share memory between agents", "KV cache compaction for multi-agent", "orchestrator worker context", "latent briefing", "reduce worker tokens", "cross-agent memory without summarization", or discusses Attention Matching compaction, recursive language models with workers, or token explosion in hierarchical agents.
Original prompt for direct, no-fluff output. Use when the user complains that AI is long-winded or goes in circles, wants a more direct, actionable answer, or tends to lose focus when reading long text. Trigger phrases include “cut the fluff,” “get to the point,” “give me the conclusion,” “don’t beat around the bush,” “be direct,” “no empty talk,” “start with what to do,” “no fluff,” “ADHD-friendly,” and “I have trouble focusing.” Add the whole prompt at the start of the conversation to constrain the structure of all subsequent answers; turn it off when asked to return to normal mode.
Systematic planning for medium-to-large tasks. Gathers context, identifies domain skills, and writes phased plans to brain/plans/. Does NOT implement. Use for new features, multi-file refactors, or architectural changes—not small fixes. Triggers: “plan this”, “break this down”.
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.