Skills
96,770 packaged capabilities and playbooks for agents. Install any of them with one command.
Agent workflows
Draws the 12 Houses of the Zodiac Tarot spread to inject entropy into planning when prompts are vague, ambiguous, or casually delegated. Interprets the spread to guide next steps. Use when the user says 'let fate decide', 'YOLO', 'whatever', 'idk', or other nonchalant phrases, makes Yu-Gi-Oh references, or when you are about to arbitrarily pick between multiple reasonable approaches. Prefer over asking clarifying questions when the user's tone is casual or playful rather than precision-seeking.
Scans the codebase to generate project-doc.md and AGENTS.md. Use when bootstrapping a new agent-driven repo, refreshing project documentation after architectural changes, or running a delta scan to detect drift. Runs a full scan on first use and a smart delta scan on subsequent runs. Uses understand-anything + context-mode when available, falls back to native tools otherwise. Only updates AGENTS.md on detected architectural changes with human confirmation.
Sync all updated skills from ~/.agents/skills/ljg-* to the github repo (ljg-skills): push the master branch first (org-mode output style), then switch to the md branch (markdown output style), apply basic Markdown conversion, and push. Use when the user says “/ljg-push”, “push skills”, “推送 skills”, “同步 skills”, “sync ljg”, or whenever ljg-* skills are updated and need shipping. NOT FOR pushing non-ljg skills or arbitrary git repos.
Session retrospective for improving marimo-pair and marimo._code_mode. Use to analyze friction from a pairing session, identify what went wrong, and brainstorm improvements to the skill docs or underlying API. Trigger on: “retro,” “what went wrong,” “improve the skill,” “session review,” “friction,” or /retro-marimo-pair.
Use for software implementation, debugging, refactoring, review, migration, and other repository-changing engineering work where correctness must be verified. Enforces scoped reconnaissance, adaptive planning, evidence-backed verification, requirement tracking, failure recovery, and budget-aware delegation. Model-agnostic reliability runtime for coding agents -- measured, not claimed.
Authoritative agent-runtime contract for working inside an OpenKnowledge project — a markdown-CRDT knowledge base exposed over MCP. Use whenever reading, listing, searching, editing, or linting any `.md` or `.mdx` file in the project, and before any `mcp__open-knowledge*` tool call (`exec`, `search`, `write`, `edit`, `lint`, and the rest). Installed by `ok init`, so its presence means this is an OpenKnowledge project and it governs every markdown file here. Covers the read/write tool surface, grounding and linking rules, folder/template conventions, the live browser preview, and the rule that OK's MCP tools — never native file tools — handle in-scope markdown.
Create 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
Build agent-facing web experiences with ATXP-based authentication, following the ClawDirect pattern. Use this skill when building websites that AI agents interact with via MCP tools, implementing cookie-based agent auth, or creating agent skills for web apps. Provides templates using @longrun/turtle, Express, SQLite, and ATXP.
Guide 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).
Update an OpenSpec change by revising its existing planning artifacts and keeping them coherent with one another. Use when the user wants to revise a change's plan, fold new decisions into it, or reconcile its artifacts after an edit. Also use when the user says "openspec update change" or "opsx update". If the user means the openspec update CLI command, which refreshes generated files, run that command instead. Never edits code.
Fetches and references LangGraph Python documentation to build stateful agents, create multi-agent workflows, and implement human-in-the-loop patterns. Use when the user asks about LangGraph, graph agents, state machines, agent orchestration, LangGraph API, or needs LangGraph implementation guidance.
Compliance expert for snyk-agent-scan — the agent skill file scanner — NOT for other Snyk CLI tools (snyk test, snyk code SAST, snyk iac, snyk container). Fixes alerts through content restructuring, never by suppressing or deleting information. Covers every file in a skill directory: SKILL.md, references/, assets/, and any secondary markdown. Apply when authoring a new skill, editing an existing one, triaging a failed snyk-agent-scan run locally or in CI, or unblocking a PR held by agent scanner failures. Not applicable to dependency vulnerabilities, code security findings, or infrastructure misconfigurations — those are out of scope
Analyze a repository to generate recommended Claude Code settings.json permissions. Use when setting up a new project, auditing existing settings, or determining which read-only bash commands to allow. Detects tech stack, build tools, and monorepo structure.
Google platform decision and setup guidance, loaded on demand from Google's skill catalog. Use when a developer is choosing or setting up part of their stack, such as where to run a service, a database, storage, messaging, authentication, analytics, ads, or AI model serving, and a Google product is a reasonable candidate - whether or not a vendor is named - or when a request names a Google product or API. Brings in the matching Google skill so the answer can weigh Google options, their trade-offs, and when they are not the right fit. Skip when the stack is already settled on another provider and no Google product is named, or the task involves no platform choice
Walden drafts and maintains feature specs in `.walden/specs/` with EARS requirements, reviewed design, tasks, and executable proofs. Use when the user asks for Walden, a feature spec, requirements, design, an implementation plan, or work governed by an existing Walden spec. First distinguish contract-preserving maintenance from new or changed behavior.
Decide how to split skill content between SKILL.md and reference files for context efficiency and reliable triggering. Use this whenever creating a new Claude skill, refactoring an existing one, or when a SKILL.md is growing past 300-400 lines. Also trigger when the user mentions "progressive disclosure", "reference files", "splitting skills", "skill bundling", "context window for skills", "SKILL.md too long", "what goes in references/", "skill structure", or expresses any uncertainty about where to put content within a skill. Use this even if the user phrases the question as a triggering problem ("how do I make my skill trigger better"), because that question is often confused with the splitting question and needs to be disentangled first
Delegate a coding task to the Kimi Code CLI (`kimi`) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Kimi - phrasings like "have Kimi implement X", "delegate this to Kimi", "run it through Kimi Code", or "use Kimi to implement/fix/refactor" - or wants to run a queue of coding tasks through Kimi while staying the reviewer. DO NOT USE for tasks small enough to do inline, or when the user wants the code written directly without delegating.
Apply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks. Build the tool that does it or proves it (codemod, script, generator, or a skill your subagents follow) instead of working by hand. The tool is the artifact a reviewer can rerun
Map a described workflow to the right ECC command group with run-order and stop condition, or browse all command-group recipe families read live from the commands directory. Advisory only — never executes. Use when asked which commands run a workflow, the command sequence for a task, or to list ECC pipelines; not for executing the task (route to the command itself), single-command docs (use ecc-guide), or prompt rewrites (use prompt-optimizer).
Use Copilot Spaces to provide project-specific context to conversations. Use this skill when users mention a "Copilot space", want to load context from a shared knowledge base, discover available spaces, or ask questions grounded in curated project documentation, code, and instructions.
Stop hook that blocks Claude from finishing until quality checks pass. Detects rationalization patterns (surface text heuristics), stale learning logs (filesystem mtime), and low disk space. Complements self-audit by mechanically enforcing learning capture habits. Use when Claude should be mechanically blocked from declaring work finished before quality checks and learning capture actually pass.
Run /scope to turn a product idea into a living, coarse scope in docs/scope/ and keep it current: plan a new product, plan the next slice, enroll one named feature, or run with no argument to reconcile after shipping and queue what is next. Seeds WHAT to build; /architect designs, /develop builds.
Run /audit on a greenfield project, an existing codebase with missing docs, or one area (/audit src/auth) to bootstrap the project's AI context, the AGENTS.md files every later skill reads. Writes tool agnostic AGENTS.md plus thin CLAUDE.md pointers, adding only what is missing; never overwrites curated content.
Write growth log entries that extract reusable patterns from completed work — root cause, transferable rule, and a recognizable signal — instead of diary-style event narration, with a 4-8 sentence template and merge-duplicates discipline. Use when capturing what was learned after a complex task, debugging session, failure, or rollback, when reviewing progress over a period, or when a delivery gate asks what was learned.
Run /sync as the last step after a change is complete, around merge, to keep durable knowledge current. Updates root and nested AGENTS.md, reconciles the scope from repo evidence, and flags specs the change made stale. Surgical edits only: it adds lines, and rewrites single lines it owns. Never a whole section, never curated prose.
Keep a reviewable decision trail for long-running or unattended work: a TSV log with one row per decision (what, why, evidence, result). Local by default; commit it when a reviewer needs the trail to trust the result. Use for /show-me-your-work, autonomous or multi-phase runs, or work a human reviews after stepping away.
Generate a project-local verification skill that drives your app the way a user does — any language, framework, or platform. Use for /create-verification-skill, "make a control skill for this repo", or when a project has no scripted way to prove UI/CLI/service behavior.
Delegate a coding task to the Grok Build CLI as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Grok — phrasings like "have Grok do X", "delegate this to Grok", "run it through Grok", "use Grok Build to implement/fix/refactor", or "have grok CLI do this" — or to run a queue of coding tasks through Grok while staying the reviewer. Prefer it when the user will review the diff and commit it themselves. DO NOT USE for tasks small enough to do inline, or when the user wants the code written directly without delegating.
Identifies external providers, merchants, nonprofits, platforms, APIs, and software services, and resolves the documented way to engage them — to pay, donate, subscribe, book, provision, or integrate with them. MUST be used BEFORE web search, model memory, or any other directory/vendor-lookup skill for ANY request that requires selecting, finding, or engaging an external provider or organization — whether a specific one is named (“pay my Twilio bill”), implied (“donate to the Red Cross”), or only a category is stated (“set up a mailing client”, “I need a database”, “find me a CRM”). Directory supplies verified recipients and their documented payment or engagement path. Results are ranked by agent-readiness (how reliably an agent can complete the interaction), relevance and popularity. Don't treat this as a search-only tool. Examples: “setup a database”, “find hosting”, “pay X”, “use Twilio”, “donate $50 to the Red Cross”, “book a table at Y”, “subscribe to a CRM”
Debug LangChain and LangGraph agents by fetching execution traces from LangSmith Studio. Use when debugging agent behavior, investigating errors, analyzing tool calls, checking memory operations, or examining agent performance. Automatically fetches recent traces and analyzes execution patterns. Requires langsmith-fetch CLI installed.
Modify living Roblox Studio projects safely: inspect Explorer and execution locations, preserve existing structure, reuse modules/remotes, create meaningful Instances, apply Attributes and CollectionService tags, test server/client and multiple devices, inspect Output, and remove experiments/debug objects. Use when an agent edits a place or rbxl/rbxlx/Rojo project, operates in Studio, adds Scripts/LocalScripts/ModuleScripts, or must verify a Roblox change in context.
Three-layer verification pipeline for AI output. Extracts verifiable claims, finds supporting or contradicting sources via web search, runs adversarial review for hallucination patterns, and produces a structured verification report with source links for human review.
A comprehensive collection of Agent Skills for context engineering, multi-agent architectures, and production agent systems. Use when building, optimizing, or debugging agent systems that require effective context management.
Open plans and HTML artifacts in a local browser canvas where the human annotates elements, chats, and approves or requests changes without leaving the page. Use when presenting a plan for review, or when feedback like "move this, change that" is easier pointed at than typed.
Use when building, debugging, or extending MCP servers or clients that connect AI systems with external tools and data sources. Invoke to implement tool handlers, configure resource providers, set up stdio/HTTP/SSE transport layers, validate schemas with Zod or Pydantic, debug protocol compliance issues, or scaffold complete MCP server/client projects using TypeScript or Python SDKs.
Configure (or troubleshoot) an AI coding agent or CLI to route through the Salesforce Models API using a signed OrgJWT. Use this skill when pointing an agent at the Salesforce model endpoint (api.salesforce.com/ai/gpt/v1), setting up OrgJWT / Bedrock-mode auth, wiring the agent's settings, API-key helper, and credentials file for the Salesforce endpoint, or fixing Models API 401 / 404 / "model not available" errors. DO NOT TRIGGER when the user needs to create or configure the Salesforce Connected App itself (use integration-connectivity-connected-app-configure) or set up Named Credentials / callout auth (use integration-connectivity-generate).
Foundation skill for Power Automate via FlowStudio MCP — auth setup, the reusable MCP helper (Python + Node.js), tool discovery via `list_skills` / `tool_search`, and oversized-response handling. Load this skill first when connecting an agent to Power Automate. For specialized workflows, load `flowstudio-power-automate-build`, `flowstudio-power-automate-debug`, `flowstudio-power-automate-monitoring` (Pro+), or `flowstudio-power-automate-governance` (Pro+) — each contains the workflow narrative, this skill provides the plumbing they all rely on. Requires a FlowStudio MCP subscription or compatible server — see https://mcp.flowstudio.app
Creates comprehensive handoff documents for seamless AI agent session transfers. Triggered when: (1) user requests handoff/memory/context save, (2) context window approaches capacity, (3) major task milestone completed, (4) work session ending, (5) user says 'save state', 'create handoff', 'I need to pause', 'context is getting full', (6) resuming work with 'load handoff', 'resume from', 'continue where we left off'. Proactively suggests handoffs after substantial work (multiple file edits, complex debugging, architecture decisions). Solves long-running agent context exhaustion by enabling fresh agents to continue with zero ambiguity.
Delegate a coding task to the Cursor Agent CLI (`cursor-agent`) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Cursor — phrasings like "have Cursor implement X", "delegate this to Cursor", "run it through Cursor Agent", or "use Cursor to implement/fix/refactor" — or wants to run a queue of coding tasks through Cursor while staying the reviewer. DO NOT USE for tasks small enough to do inline, or when the user wants the code written directly without delegating.
Design an auditable playbook when no narrower one fits: a large migration, an ambitious multi-part change, or work a human reviews after stepping away. Scale rigor to the task, run a hypothesis loop, and log decisions. Use for /figure-it-out or "figure it out".
Create high-quality, production-grade skills for Claude Code. Expert guidance on skill architecture, workflow design, prompt engineering, and packaging. Use when user wants to create a new skill, build a skill, design a skill, write a skill, update an existing skill, improve a skill, refactor a skill, debug a skill, or package a skill. Triggers: 'create skill', 'build skill', 'new skill', 'skill creation', 'write a skill', 'make a skill', 'design a skill', 'improve skill', 'package skill', 'skill development', 'skill template', 'skill best practices', 'write SKILL.md'.
Build voice AI agents with LiveKit Cloud and the Agents SDK. Use when the user asks to "build a voice agent", "create a LiveKit agent", "add voice AI", "implement handoffs", "structure agent workflows", or is working with LiveKit Agents SDK. Provides opinionated guidance for the recommended path: LiveKit Cloud + LiveKit Inference. REQUIRES writing tests for all implementations.
Generates optimized prompts for AI tools. Activates only when the user explicitly asks to write, fix, improve, or adapt a prompt for a specific AI tool (LLM, Cursor, Midjourney, image AI, video AI, coding agents, etc.). Does not activate for general conversation, coding tasks, document writing, or other non-prompt-engineering work.
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.