Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Agent workflows
Operate a BKD kanban board over its REST API. Use when the user wants to manage BKD projects, issue execution workflows, cron jobs, or execution capacity, including three-tier coordination with an event-driven L1, multiple cron-driven L2 workstreams, and L3 execution, multi-repo coordination across several git repos in one workspace directory (trigger phrases like "start BKD multi-repo coordination"), plus multi-subtask orchestration (trigger phrases like "use bkd to start coordination", "start BKD L1"), and the messages system that sends decisions and notifications to BKD's inbox (trigger phrases like "enable the messages system", "启用消息系统", "启用决策系统", "notify me when …", "通知我"). Requires a reachable BKD server ($BKD_URL).
Manage Model Context Protocol (MCP) servers - discover, analyze, and execute tools/prompts/resources from configured MCP servers. Use when working with MCP integrations, need to discover available MCP capabilities, filter MCP tools for specific tasks, execute MCP tools programmatically, access MCP prompts/resources, or implement MCP client functionality. Supports intelligent tool selection, multi-server management, and context-efficient capability discovery.
Plug-in web search, X (Twitter) search, and page fetch for models without native web access. Use whenever the task needs current information, external facts, source links, posts from X, or the content of a specific URL, and the active model/harness has no native search or fetch tool. Runs the modsearch CLI to return structured JSON evidence. Also use when the user asks how to install or configure modsearch, or wants to switch engines or add a key
Coordinate AI agent teams via a Kanban task board with local JSON storage. Enables multi-agent workflows with a Team Lead assigning work and Worker Agents executing tasks via heartbeat polling. Perfect for building AI agent command centers.
Use this by default for non-trivial multi-step work that needs persistent planning, progress tracking, or durable notes on disk. Trigger when a task will likely span multiple tool calls, research steps, verification loops, or enough context that the plan should not live only in transient chat memory.
This skill should be used for improving context efficiency: context budgeting, observation masking, prefix or KV-cache strategy, partitioning, token-cost reduction, retrieval scoping, and extending effective context capacity without lowering answer quality.
Route active project/repo memory requests into one honest packet: memory-layer choice, load-context, search-context, store-conclusions, setup-integration, or repo-packer route-out. Use when agents need searchable decisions, manifests, stable links, handoff notes, and small “read this first” packets across sessions. Route long-lived markdown knowledge bases to `llm-wiki`, structural graph memory to `graphify`, human-authored vault organization to note/vault skills, and one-shot repo packing to tools like Repomix, Gitingest, or Code2Prompt.
Use when the user asks to “test the triage skill,” “run triage tests,” “validate antithesis triage,” “test:triage,” or “smoke test triage.” Orchestrates end-to-end testing of the antithesis-triage skill by running real triage operations via subagents and reviewing results for bugs, skill compliance issues, and papercuts.
Interview the user in rounds about their plan, decision, or idea until the important unknowns surface, then start executing. Works in any domain, not just coding. Use when the user wants to clarify their thinking, stress-test an idea, or says things like: grill me, pick my brain, help me think this through, help me sort this out, poke holes in this, anything I'm missing, stress-test this, interview me.
Use when a builder needs the top-level router for the provisional standard Gear/Vara Sails skill pack across Codex, Claude, or OpenClaw. Covers standard Sails apps and ethexe-specific work via dedicated skills. Do not use for non-Sails programs or broad protocol research.
Make any repo AI-ready — analyzes your codebase and generates AGENTS.md, copilot-instructions.md, CI workflows, issue templates, and more. Mines your PR review patterns and creates files customized to your stack. USE THIS SKILL when the user asks to "make this repo ai-ready", "set up AI config", or "prepare this repo for AI contributions".
Install and configure the DefiLlama MCP server for DeFi analytics. Provides 23 tools for TVL, token prices, yields, protocol metrics, stablecoins, bridges, ETFs, hacks, raises, and more. Supports OAuth login with your DefiLlama account. Use when the user wants to set up DefiLlama MCP, connect to DeFi data, or install DeFi analytics tools.
A skill for refining stock investment research questions. Turns user-provided stock names or tickers into structured eight-stage investment due diligence instructions. Clarifies investment style (value/growth/turnaround), holding period (short/medium/long term), risk tolerance, and research focus through questions, then generates structured research tasks that meet professional investment research standards. Use when users mention stock analysis, investment research, or stock due diligence.
Orchestrate agile development workflows by invoking commands in sequence with checkpoint-based flow control. This skill should be used when the user asks to 'run the workflow', 'continue working', 'what's next', 'complete the task cycle', 'start my day', 'end the sprint', 'implement the next task', or wants guided step-by-step development assistance. Platform-agnostic git-only workflow without PR integration. Keywords: workflow, orchestrate, agile, task cycle, sprint, daily, implement, review, merge, standup, retrospective, git.
Official Dailybot agent skill pack — report progress, check messages, send emails, announce agent status, complete check-ins, give kudos (to users or teams), resolve teams, run the full forms lifecycle (list, submit, update, transition between workflow states), author check-ins and forms from scratch (create/configure questions, workflow states, permissions, reminders, scheduling, AI settings, sharing), send/edit chat messages on the team's Slack/Teams/Discord/Google Chat (including report-style threads, sending as a user's identity, and interactive buttons with approval flows, workflow triggers, modals, and callbacks), open (or reuse) a Slack group DM with the bot and post a report to it, ask the Dailybot AI a question headlessly, browse/read/trigger the workspace (`me` / `org` / `user get`, kudos browsing, workflows), manage organization Labels (`dailybot label` CRUD + assign/batch on forms, check-ins, workflows) and private Featured stars, manage Plan (Beta — boards, backlog, sprint/kanban columns, owners, attachments, bulk with dry run, project updates, milestones, goals, open-org structure for non-guest members, agent-attributed work on a handed task with `task brief` — `dailybot plan tasks` for the workspace and `dailybot plan task` for one task), and manage per-repo API keys through `.dailybot/env.json` (pack baseline `dailybot-cli >= 3.9.0`; Plan needs `>= 3.25.0`). Routes to the right sub-skill based on intent. Use when the developer mentions Dailybot or wants to interact with their team
Integrate installed skill usage guidance into project CLAUDE.md/AGENTS.md based on project context. Use when skills are installed but agents don't know when to use them, when setting up a new project with skills, or when updating guidance after adding skills.
This skill should be used when the user asks about "Bankr API", "Bankr Agent API", "how does Bankr work", "Bankr job status", "Bankr response format", or "building on Bankr". Provides endpoint documentation, job patterns, and TypeScript interfaces.
A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go. Use when the grilling session should also leave ADRs and glossary entries behind. Triggers on: grill with docs, grill and document, grill this and write the ADR.
Nine integrated slash commands for complete project lifecycle: /explore-idea, /plan-project, /plan-feature, /wrap-session, /continue-session, /workflow, /release, /brief, /reflect. Use when starting projects, managing sessions across context windows, capturing learnings, or preparing releases. Saves 35-55 minutes per lifecycle.
You MUST use this when work has to be designed before any code is written - a new feature, a change to product or UX behavior, an architecture change, success criteria that are still unclear, or a choice between two materially different approaches - including a spec revision after a document review. A fully specified mechanical refactor, a localized fix whose expected behavior is known, or a config change with a single possible outcome gets no spec; the skill hands it to implement in one sentence. Turns the request into a spec with checkable acceptance criteria behind an explicit approval. Replaces devflow scope-triage.
You MUST use this when anyone - you, a subagent, or the user - is about to state that work is done, fixed, ready, or mergeable, and before the commit that completes it, a merge, opening a pull request, or a handoff report, including work that has no plan. Covers every promise behind the claim - spec criteria, plan tasks, journal entries, accepted review fixes, and the caller's words - proven with fresh checks on the current tree and given one verdict, without editing code. Not for fixing failures (implement) or reviewing (cr-request). Replaces devflow verification-gate.
Use at the start of any bug bounty hunting session, when switching targets, or when feeling lost about what to do next. Master orchestrator combining the 5-phase non-linear hunting workflow with the critical thinking framework (developer psychology, anomaly detection, What-If experiments). Routes to all other skills based on the current hunting phase. Also use when asking “what should I do next” or “where am I in the process.”
You MUST use this when verified work awaits a decision on how it leaves the branch - merging it, pushing it, opening a pull request (PR), keeping the branch, discarding the branch, or cleaning up a worktree or workspace - in any repository. Not for work that is not verified yet (verify), open review findings (cr-received), a plain commit with no integration decision, or release work with its own checklist. Replaces devflow branch-finish.
You MUST use this when an existing implementation plan is to be executed, either directly in the current session or through subagents, including resuming an interrupted execution from the plan's execution record, or when one or two edits with an obvious approach need doing without a plan. Covers task-by-task execution with evidence, drift handling and blockers, and a resumable execution record. Replaces devflow inline-plan-dev and subagent-plan-dev. Not for writing a plan (plan-craft), checking finished work (verify), acting on review findings (cr-received), or merging, pushing, or opening a pull request (finalize).
You MUST use this when a spec the user approved, an accepted design, or requirements already agreed in the conversation have to be turned into an ordered, multi-step implementation plan before any code is written - including a spec from specify, work with no spec yet, and a plan revision after a document review. Replaces devflow plan-crafting. Covers whether a plan is needed, task order, acceptance-criteria coverage, and the execution choice. Not for open design (specify) or executing a plan (implement).
Write, refine, run, and QA promptfoo evaluation suites: promptfooconfig.yaml, prompts, providers, vars, tests, assertions, model-graded rubrics, transforms, datasets, exports, and CI gates. Use for non-redteam eval coverage, regression tests, or new eval matrices. Do not use for adversarial redteam plugin or strategy setup.
Four slash commands for the documentation lifecycle: /docs, /docs-init, /docs-update, /docs-claude. Create, maintain, and audit CLAUDE.md, README.md, and docs/ structure with smart templates. Use when starting new projects, maintaining documentation, auditing docs for staleness, or ensuring CLAUDE.md matches project state.
Generate a persistent .nexus-map/ knowledge base that lets any AI session instantly understand a codebase's architecture, systems, dependencies, and change hotspots. Use when starting work on an unfamiliar repository, onboarding with AI-assisted context, preparing for a major refactoring initiative, or enabling reliable cold-start AI sessions across a team. Produces INDEX.md, systems.md, concept_model.json, git_forensics.md and more. Requires shell execution and Python 3.10+. For ad-hoc file queries or instant impact analysis during active development, use nexus-query instead.
Analyze a codebase and recommend Claude Code automations (hooks, subagents, skills, plugins, MCP servers). Use when the user asks for automation recommendations, wants to optimize their Claude Code setup, mentions improving Claude Code workflows, asks how to set up Claude Code for a project for the first time, or wants to know which Claude Code features they should use.
Turns product or tech specs into concrete Notion tasks that Claude code can implement. Breaks down spec pages into detailed implementation plans with clear tasks, acceptance criteria, and progress tracking to guide development from requirements to completion
/cs-onboard — Founder interview that populates ~/.claude/company-context.md using the canonical 7-dimension cs-onboard schema. The first command to run when starting with c-level-agents. Use when setting up the virtual C-suite for a new company, or when advisors lack company context — e.g. before a first /c-level-agents:boardroom or after a fundraise changes the numbers.
Isolates profiles for multi-provider setup and switching models in separate terminal windows (Kimi, MiniMax, DeepSeek, GLM, StepFun, Anthropic). Use for provider switching, csk/csd/csg aliases, CLAUDE_CONFIG_DIR, ~/.claude-profiles, profile drift (missing skills/hooks, symlinks, settings), context-window setup ([1m], CLAUDE_CODE_MAX_CONTEXT_TOKENS), or reducing startup context from preloaded MCP tool schemas.
Inspect Skills for a goal and author the complete entry Skill and business Rule for Native extensions, Classic compositions, or standalone applications; after confirmation, the SDK assembles Runtime, connects Hooks, and previews installation. Not for general Skill cleanup or review.
LangGraph 1.x (LTS) Python workflow patterns for state management, delta channels, resilience (node timeouts, error handlers, graceful drain), routing, parallel execution, supervisor-worker, tool calling, checkpointing, human-in-loop, streaming (v2 format), subgraphs, and functional API. Use when building LangGraph pipelines, multi-agent systems, or AI workflows.
Migrates Airflow projects from airflow-ai-sdk to apache-airflow-providers-common-ai 0.4.0+. Use when replacing airflow-ai-sdk with the official Airflow AI provider - migrating LLM decorators (@task.llm, @task.agent, @task.llm_branch, @task.embed), switching from model strings/objects to connection-based LLM configuration, updating imports from airflow_ai_sdk to the new provider, or upgrading an existing common-ai 0.1.x setup to 0.4.x (multimodal prompts, toolsets, embedding operators); also when common-ai provider, AIP-99, a pydanticai connection or migrating away from airflow-ai-sdk come up.
Detect and auto-install missing ToolUniverse research skills. Checks common Claude Code/Cursor/Codex skill directories for the canary file, and installs any missing skills if none found. Use when the plugin's research skills aren't loading, when migrating between clients, or when verifying a skill installation.
Build AI applications with OpenAI Agents SDK: text agents, voice agents, multi-agent handoffs, tools with Zod schemas, guardrails, and streaming. Prevents 11 documented errors. Use when building agents with tools, voice agents with WebRTC, multi-agent workflows, or troubleshooting MaxTurnsExceededError, tool call failures, reasoning defaults, JSON output leaks.
OpenAI Codex (CLI / IDE / cloud / ChatGPT desktop app) reference. GPT-6 series, Fast / Ultrafast mode, codex exec, slash commands, prompting, AGENTS.md, rules, subagents, approvals, auto-review, sandbox, permission profiles, profiles, config.toml, environment variables, roles, MCP configuration, GitHub Action, Codex SDK, App Server (JSON-RPC), Agents SDK integration, Codex skills (.agents/skills), plugins, scheduled tasks, Browser, Computer Use, cloud / local / worktree environments, git worktrees, Record & Replay, cloud delegation, GitHub / GitLab / Linear / Slack integrations, administration, provisioning, analytics API, compliance API, LLM gateway, Codex Security vulnerability scanning (SARIF), deep scan, triage, findings, threat model, security hardening.
Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot learning, creating system prompts with personas and guardrails, building JSON/function-calling schemas, or developing prompt evaluation frameworks to measure and improve model performance.
AWS-curated copy-paste prompts for AI coding agents (MVP scaffolding, RAG chatbot with Claude on Bedrock, security baseline evaluation, cost anomaly detection, GPU quota requests, EKS deployment, Well-Architected review, etc.) plus downloadable installable agents (Multi-Account Transition Advisor, Bill Shock Preventer, Service Quota Agent, Bedrock Model Availability Agent, AWS DB Advisor). Use when the user asks for a prompt to do X on AWS, wants an installable agent for multi-account / cost monitoring / quota management / Bedrock model availability / database selection, or asks how to use AWS prompts. For migration intent (GCP to AWS, Azure to AWS, OpenAI/Gemini to Bedrock), route to the migration skills in this plugin (`gcp-to-aws`, `azure-to-aws`, `heroku-to-aws`, `llm-to-bedrock`). Do not use for: factual AWS Activate / programs / credits questions, learn articles, sample architectures, or for prompts that are not in the bundled `references/prompt-library/` tree.
Secure AI agents against prompt injection, tool abuse, and data exfiltration with defense-in-depth controls. Use when building, deploying, or hardening agentic AI systems that invoke tools, access data, or interact with production infrastructure.
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.