Skills
97,501 packaged capabilities and playbooks for agents. Install any of them with one command.
Agent workflows
Route Blender asset creation, refinement, procedural systems, rendering, simulations, characters, validation, animation, MCP integration, and agent benchmarking work to the appropriate Blender Agent Studio workflow. Use when an agent needs an end-to-end Blender workflow or when the correct specialist skill is not yet known.
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".
File and directory operations via Claude Code built-in tools, replacing the Filesystem MCP server. Triggers on: “read this file”, “write to file”, “edit file”, “find files matching”, “search for text in files”, “list directory”, “show directory tree”, “rename file”.
Provider-agnostic multi-LLM deliberation. Three phases — independent responses, cross-model anonymized ranking, chairman synthesis. Credentials come from explicit plugin configuration or pro-workflow-specific CLI variables. Persists transcript to a wiki page when --wiki <slug> is passed. Use when the user wants multiple AI perspectives, consensus-building, or the "LLM Council" approach for high-stakes reviews, plan critique, or contested learning rules.
Access Claude, Gemini, Kimi, GLM and 100+ LLMs via inference.sh CLI using OpenRouter. Models: Claude Opus 4.5, Claude Sonnet 4.5, Claude Haiku 4.5, Gemini 3 Pro, Kimi K2, GLM-4.6, Intellect 3. One API for all models with automatic fallback and cost optimization. Use for: AI assistants, code generation, reasoning, agents, chat, content generation. Triggers: claude api, openrouter, llm api, claude sonnet, claude opus, gemini api, kimi, language model, gpt alternative, anthropic api, ai model api, llm access, chat api, claude alternative, openai alternative
Discover and install related skills from inference.sh skill registry. Helps find complementary skills for your AI workflow. Use for: skill discovery, workflow expansion, capability exploration. Triggers: related skills, find skills, skill discovery, complementary skills, expand workflow, more capabilities, similar skills, skill suggestions
Use when the team context did not appear at session start, a skill failed to trigger, the install behaves unexpectedly, or someone asks why a session ran without team rules — walks the failure chain with commands and evidence before any conclusion.
Token usage tracking and cost monitoring specialist. ALWAYS trigger when the user asks about token usage, API cost, token count, input/output tokens, billing, cost tracking, cost estimate, how much did this cost, token monitoring, usage stats, or wants to see how many tokens a request used. For active optimization strategies (model selection, context management, prompt efficiency) use token-optimizer instead
Use when the user asks to execute, implement, continue, or apply an existing implementation plan, specification, acceptance criteria, task plan, or prior planning output. Do not use for plan creation or coding requests with no concrete plan to bind.
Cross-vendor adversarial code review of the current branch. Two different model families (Claude + Codex/GPT) review the diff independently, then try to refute each other's findings; survivors are reported by confidence. Runs from either Claude Code or Codex. Use when the user asks for an adversarial review, a cross-model / second-opinion review, or wants high-confidence findings before merging. Report-only — never auto-applies fixes.
Создаёт memory bank проекта с нуля и выполняет его первичное заполнение. Используй только при явном вызове /bro-init-memory-bank, когда пользователь хочет создать новый банк знаний проекта. Не используй для пополнения существующего memory bank или сохранения отдельного проектного решения.
Configures and verifies an expanded, model-aware context window for OpenAI Codex CLI and Desktop. Use when Codex shows ~258K context, you want 500K or 1M tokens, auto-compaction fires too often, or model_context_window/model_auto_compact_token_limit needs repair. Not for changing the selected model or other Codex settings.
Refresh durable AI context for a Cargo WORKSPACE or package monorepo: a self-contained `CLAUDE.md` per member that Claude lazy-loads, plus a thin project-wide root, so changes in any member have local guidance without bloating the root. Discover each member's actual reachable surface, key files, wiring, and inter-member dependencies, then keep the root project-wide. A user-only maintenance workflow that mutates durable memory across members: it documents the actual exported/reachable surface (not raw `pub`/`export` counts), grounds every claim in code, and preserves locked root decisions. Use to refresh workspace-local context after refactors, member additions, or export changes.
Creates MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Activates on: “build an MCP server”, “create MCP tools”, “integrate API via MCP”, “write a FastMCP server”, “add an MCP server to an agent”, or any request to wrap an external API as LLM-callable tools in Python or Node/TypeScript.
Generate, refine, and optimize production prompts for LLMs with an explicit output contract, completeness criteria, handling of missing context, and concise verification. Use when the user asks to create or improve prompts intended for runtime, or when an SDD design/build flow creates or changes system prompts, pipeline passes, classifiers, synthesizers, edge/worker/runtime prompts, **/prompts/** files, inline system prompts, or templates in _shared. Do not use for human documentation, SDD internal orchestration prompts, emails, notifications, or transactional UI copy.
Propagate one validated learning from this session into durable AGENT guidance: extract the smallest useful rule, classify its scope (Global / Claude Code Only / Agent-Specific), store it once in the central agent-learnings file, and sync the regenerated `## Learnings` section into every live agent definition across the CLI trees present. A user-only maintenance workflow that mutates durable agent prompts: it grounds the rule in what this session actually revealed, never invents, confirms scope and wording first, and keeps “Claude Code Only” learnings out of subagent prompts. Use to record an agent-behavior rule so future agents inherit it.
Surface the user's unknown unknowns before work starts. Use when the user is entering an unfamiliar codebase area, an unfamiliar domain (design, video, infra), or explicitly asks for a “blindspot pass” or to find their “unknown unknowns.”
Search code through the most precise semantic backend—prefer tilth MCP, with AST search (`sg`) for structural patterns. Use when the user asks to find a symbol, definition, caller, import, or text pattern, with phrases like “where is X defined”, “what calls Y”, “find all usages of Z”, “trace this function”, “find the TODO comments”, or “search for this error string”. Use even when the user says “grep”, “rg”, “ripgrep”, “ag”, “ack”, “fd”, or “find”. Do not use for reading whole files (use cheez-read), editing code (use cheez-write), or running tests/builds.
Audit and improve CLAUDE.md files in repositories. Use when the user asks to check, audit, update, improve, or fix CLAUDE.md files. Scan for all CLAUDE.md files, evaluate quality against templates, output a quality report, then make targeted updates. Also use when the user mentions “CLAUDE.md maintenance” or “project memory optimization”.
Create Model Context Protocol (MCP) servers that expose tools, resources, and prompts to Claude. Use when building custom integrations, APIs, data sources, or any server that Claude should interact with via the MCP protocol. Supports both TypeScript and Python implementations.
How to explore and make sense of PostHog Signals scouts — the scheduled agents that scan a project and emit findings into the Signals inbox. Use when a user wants to understand what scouts they have, how each one is behaving, and whether the fleet is actually working. Covers surveying the fleet and its schedules, reading recent scout runs and drilling into a single run's reasoning, inspecting the durable scratchpad memory the fleet has built up, tracing a run to the findings it emitted, and assessing a scout's health and performance over time (cadence, success rate, emit rate, signal-to-noise). Read-only and exploratory — to write or tune a scout, use `authoring-signals-scouts` instead. Trigger on "what are my scouts doing", "how is my <x> scout performing", "show me recent scout runs", "why did this scout find/emit nothing", "what has the fleet learned", "explore scout run <id>", "is my scout working"
Open an HTML file, Markdown file, or localhost page in the browser so the user can edit text directly and leave comments on specific parts, then send all edits and comments back to you. Use after writing or updating something the user will read — specs, plans, reports, newsletter drafts, landing pages, slide decks, and locally running web pages
Build n8n workflows using the Pinecone Assistant node or Pinecone Vector Store node. Use when building RAG pipelines, chat-with-docs workflows, configuring Pinecone nodes in n8n, troubleshooting Pinecone n8n nodes, or asking about best practices for Pinecone in n8n
Proactive goal and task management system. Use when managing goals, breaking down projects into tasks, tracking progress, or working autonomously on objectives. Enables agents to work proactively during heartbeats, message humans with updates, and make progress without waiting for prompts.
Read-only audit of a repository's SDD harness for FAXINA E DERIVA: inventories commands, agents, skills, hooks, settings, and scripts of ANY engine (Claude Code, Codex, Kimi CLI: reads CLAUDE.md and AGENTS.md, .claude/, .agents/, and .codex/), measures references, recency, duplication, and drift between docs and code, and generates a single report AUDITORIA_SDD_<data>.md without changing anything. Invoke when someone says "the harness has grown too much", "what does nobody use here", "do the docs still match the code?", or asks for a harness cleanup (`.claude/`, `.agents/`, or `.codex/`). ⚠️ Boundary: this skill asks WHAT IS LEFT OVER AND WHAT HAS DRIFTED (hygiene). For SECURITY — easter egg, malicious code, backdoor, exfiltration, invisible unicode in third-party material you are about to install — use the rdd-audita-harness skill. Excess is not a threat; both are read-only and complement each other.
Analyze the current conversation or mine historical chat sessions for correction patterns, wrong conclusions, or unnecessary user intervention. Use when the user wants to improve prompts, skills, workflows, or guardrails based on repeated mistakes.
Complete requested work while preventing speculative defenses and scope creep. Use when considering extra hardening, reviewing possible overengineering, resolving repeated verification loops, following explicit task boundaries, or when the user invokes Stop That Shit. Ordinary use of validation, retries, or dependencies alone is not a trigger.
Run the AgentRC readiness assessment on the current repository and produce a static HTML dashboard at reports/index.html. Wraps `npx github:microsoft/agentrc readiness` and hands off rendering to the @ai-readiness-reporter custom agent. Supports policies (--policy) for org-specific scoring. Use when asked to assess, audit, or score the AI readiness of a repo.
Facilitates structured roleplay, debate, and synthesis to resolve decisions with multiple legitimate perspectives and inherent tensions. Surfaces assumptions that single-viewpoint analysis would miss and integrates competing priorities into coherent recommendations. Use when stakeholders have competing priorities (growth vs. sustainability, speed vs. quality), need to pressure-test ideas from different angles, explore tradeoffs between incompatible values, or synthesize conflicting expert opinions into coherent strategy.
Read and list code through the best fresh backend — prefer code-intelligence backends (tilth MCP; LSP for symbol- or type-shaped reads); fall back to native bounded read/list tools only when no code-intel backend covers the shape. Use when the user asks to read, view, show, open, or display a file or directory — phrases like "read src/auth.ts", "show me this file", "what's in this directory", "view lines 44-89", "look at the imports". Use even when the user names a shell viewer/lister or says "open the file" — never blind-shell a source file. Do NOT use for searching symbols or text (use cheez-search), editing code (use cheez-write), or git/gh operations.
Edit code through the safest stale-checking backend — prefer code-intelligence backends (tilth MCP tag-anchored edits, LSP workspace edits, `sg --rewrite` for structural codemods); fall back to native anchored edits only when no code-intel backend matches. Use when the user asks to edit, replace, modify, update, change, delete, or insert code — phrases like "replace this function", "delete lines 44-89", "update validateToken", "add this import", "fix this bug" (when fixing requires editing), or apply a cross-cutting codemod like "rewrite every X to Y". Do NOT use for reading files (use cheez-read), searching code (use cheez-search), or running tests/builds.
Implement one phase of a plan stored as GitHub issues in the repository of the current working directory. Given the URL of a phase (child) issue, it implements that phase; given the parent plan issue, it finds and implements the current phase. Only implements a single phase per invocation, then stops for user review. It opens a pull request that references the phase issue so merging it closes the issue automatically. Never merges the pull request
Compress selected context to a target token budget while preserving decisions, evidence, constraints, and unresolved questions. Use when relevant material is already selected but too long; use context-optimization when selection, deduplication, and ordering are also required.
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.