Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Agent workflows
Report this session's output tokens and CO₂ by running the repo's committed EcoLogits port, plus the modelled CO₂/$ saved vs a no-Honey baseline — always labelled with the bench stamp it came from. Use when asked how much Honey saved, the session's carbon/token footprint, or to expand the 🍯 statusline badge into a full breakdown.
Show Honey's benchmark scoreboard — the committed quality and token results per task tier (code, user-facing, agent-to-agent) from bench/. Reports only the reproducible committed figures, never invents per-repo numbers. Use when asked how much Honey saves, how it compares to Caveman / Ponytail / no-skill baseline, or for the headline numbers.
Create and maintain one committed per-project memory file (PROJECT.md) so agents stop re-discovering the same facts every cold session. Stores only the stable, expensive-to-rediscover, not-in-the-code context — architecture + why, build/test/run commands, decisions and dead-ends — as human-readable markdown, versioned with the code so it can't silently rot. Use when asked to set up project memory/context, stop agents re-grepping the codebase, scaffold or refresh a PROJECT.md / CLAUDE.md memory section, or cut cold-start rediscovery cost. Prose context only — never code, config, or data.
Use when the user wants to generate and literature-vet a pool of novel, testable research hypotheses for a question or domain. A multi-agent loop: a Generator proposes candidate hypotheses, a LiteratureScout grounds each in real retrieved literature (already known? closest prior work? what gap does it fill?), and a Judge scores them against a fixed rubric and keeps the strong, non-duplicate ones; rounds repeat — mutating toward the open gaps — until fresh rounds stop adding keepers. Not for sharpening or decomposing a research question (no grounding/scoring there), and not for grading an existing written proposal against the literature.
Scan the host repo a set of agent skills is installed into and reconcile every installed skill's config.json with detected facts — base branch, monorepo package roots, changelog directory, Linear issue-key prefixes, review bots, protected branches — plus the Linear team name and workspace slug fetched via the Linear MCP. Use when first installing these skills into a repo, or to refresh the configs after the skill set or repo layout changes. Also emits a committed `.claude/skills.lock` inventory of installed skill versions, and ensures the preflight skill's `.preflight-summary.json` scratch output is gitignored, and strips erroneous consumer rules that gitignore skill `config.json` (A-812). Idempotent and safe to re-run: it reconciles drift rather than clobbering deliberate manual edits, presents a dry-run diff first, and only writes after confirmation — preserving each config's key order and formatting so a no-op run leaves files byte-identical.
Drive a desktop application from one plain-language goal, or resolve one intent at a time, without ever reading the accessibility tree. Use when automating a desktop app and you want to keep a 150-element JSON tree out of your context. Give `run.mjs` a whole goal and it observes, decides, and acts until the goal is met; give `act.mjs` a single step when you want to keep the plan yourself. Covers which element, which operation, when to look deeper, and when to stop. Requires a clone of the agent-desktop repository and a TYPESAFE_API_KEY.
General-purpose coding-agent discipline based on Andrej Karpathy's observations about LLM coding pitfalls, requiring clarification, success criteria, simplicity, surgical edits, verification, and self-review for software engineering tasks.
Document and refresh a software repository in an OKF knowledge bundle. Use when the user asks to document this repo, codebase, architecture, developer workflows, or operational behavior; create repository knowledge; or bring existing repository documentation up to date after code changes. Treats the repository as live, read-only evidence rather than source material to copy or retire.
First-time bootstrap of the project knowledge base from existing markdown documentation. Surveys docs, follows cross-references, and writes new node files directly under `.ai/kenkeep/nodes/`. Supervised by the user, who reviews each node on disk before accepting or deleting it. Use when the user wants to seed an empty knowledge base from the project's existing docs.
AI Engineering from Scratch 中 Agent Skills Engineering 路线的专注交互 tutor。学习者想创建、发现、调用、保护、评估、打包或迁移 Agent Skills 时，开始或续学此路线。每次调用教学一课，并将证据记录在 AGENT-SKILLS-LEARNING.md。Start or resume this route when a learner wants to create, discover, invoke, secure, evaluate, package, or port Agent Skills.
Discover project conventions and surface security concerns. Use when starting work in a new or unfamiliar project, when asked to "learn the codebase", "check project rules", "what are the conventions", "onboard to this project", or "anything shady in this codebase". Scans agent config files (.claude/, .cursor/, CLAUDE.md, etc.) and runs a security/smell sweep for hardcoded secrets, insecure patterns, suspicious dependencies, and dangerous configurations.
AI Engineering from Scratch 中 Model Context Protocol (MCP) 路线的专注交互 tutor。学习者想创建、发现、调用、保护、评估、打包或迁移 Agent Skills 时，开始或续学此路线。每次调用教学一课，并将证据记录在 AGENT-SKILLS-LEARNING.md。Start or resume this route when a learner wants to create, discover, invoke, secure, evaluate, package, or port Agent Skills.
Proven methodology for building and tracking features, projects, and issues in Linear. Use when the user wants to set up Linear tracking, sync or audit a board, run a Linear health check, finish install after skills add, or keep session discipline honest. Routes to linear-setup / linear-sync / linear-monitor / linear-finish-install as needed; linear-discipline is always-on.
Review the readiness of a plan for an unattended/autonomous loop — checks whether it has enough feedforward guidance and feedback verification to run safely. Use when the user has a plan (or an idea) for a loop/agent that will run multiple iterations without a human checking every step, and wants to know how well-instrumented it is before starting. Works from an existing plan file or from a live conversation.
Routes and coordinates multi-channel marketing work — brand onboarding, SOSTAC routing, and campaign management. Triggers for 'marketing plan', 'brand strategy', 'campaign management', or ambiguous requests that don't map to a single specialist. Does NOT execute specialist work directly.
Use when building, installing or registering a personal MCP server — adding its `[project.scripts]` entry point, installing it with `uv tool install` from a local checkout or straight from git instead of publishing to PyPI, registering it with `claude mcp add` and choosing local/project/user scope, switching between an editable dev install and a released one without re-registering, and the per-repo dev loop (`inv dev-env.setup`, `inv quality.precommit`, why automation needs `uv run inv`) for the repos that produce these servers.
Drive mex (`mex-agent`), persistent project memory and code graphs for AI coding agents. One command scaffolds a living wiki, builds a deterministic code graph, and installs a project anchor file (CLAUDE.md, root AGENTS.md, .cursorrules, .windsurfrules, copilot-instructions.md, or .opencode/opencode.json) that your agent auto-loads as a standing rule document. Use when the user wants to `mex setup` a new project, build a symbol-grounded wiki, keep knowledge connected to implementation, route relevant context to agents, or run drift detection (`mex check`, `mex sync`). Triggers on: "mex setup", "project memory", "code graphs", "codebase documentation", "drift detection", "agent memory", "structured scaffolds", "architectural context", "living wiki", "project anchor file".
Consult external AIs (Gemini 2.5 Pro, OpenAI Codex, fresh Claude) for second opinions when stuck on bugs or making architectural decisions. Use when: debugging attempts have failed, making significant architectural choices, security concerns, or need fresh perspective. Automatically suggests consultation after one failed attempt. Provides synthesis comparing multiple AI perspectives with web research, thinking mode, and repo-aware analysis.
Deploy and configure OpenClaw AI gateway on KASM workspaces or standalone Docker. Multi-provider LLM routing (Anthropic, OpenAI, Gemini, Groq, Bedrock) with multi-channel messaging (WhatsApp, Telegram, Discord, Slack). Covers Docker deployment, security hardening, persistent storage, browser sidecar, and webhook automation. Use when: deploying OpenClaw, configuring AI gateway channels, setting up openclaw container on KASM, troubleshooting "token mismatch" or "EACCES" errors, or securing gateway binding.
Operate Orca-managed worktrees, folder contexts, terminals, repos, automations, artifacts, skill sharing, worktree comments, and Orca's embedded browser through the `orca` CLI. Use when the user says "$orca-cli", "Orca worktree", "child worktree", "spawn codex/claude in a worktree", "read/wait/send Orca terminal", "handoff" / "handover" / "give this to another agent", "Orca browser", "orca artifacts", or "share skills". Prefer it over raw git worktree, ad hoc PTYs, or Computer Use when Orca state is involved. Use Computer Use only when a visible window needs GUI control that a CLI, filesystem, or API cannot do.
Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls. Now with automatic session recovery after /clear.
Create, publish, delete, and submit plugins for coding agents (Claude Code, OpenCode, Devin CLI/Desktop). Use when user wants to (1) create a new plugin with proper structure, (2) create or configure a plugin marketplace, (3) publish plugins to GitHub/GitLab/npm, (4) delete/uninstall plugins, (5) validate plugin structure, or (6) prepare and submit plugins to the official Anthropic directory or the OpenCode ecosystem.
Set up, inspect, link, and deploy Polpo projects using the current .polpo directory layout and CLI. Use for project bootstrap, project files, cloud linking, deployment, or deciding whether behavior belongs to Polpo OSS or Polpo Cloud. For agent design, runtime calls, Channels, integrations, or React UI, use the corresponding specialized Polpo skill.
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 `power-automate-build`, `power-automate-debug`, `power-automate-monitoring` (Pro+), or `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
Conduct a thorough pre-implementation discussion before making significant changes. Use when the user wants to discuss, plan, or evaluate a change before implementing it — especially when they say words like 'discuss', 'evaluate', 'plan', or 'let's talk about'.
Use when managing prompts in production at scale: versioning prompts, running A/B tests on prompts, building prompt registries, preventing prompt regressions, or creating eval pipelines for production AI features. Triggers: 'manage prompts in production', 'prompt versioning', 'prompt regression', 'prompt A/B test', 'prompt registry', 'eval pipeline'. NOT for writing or improving individual prompts (use senior-prompt-engineer). NOT for RAG pipeline design (use rag-architect). NOT for LLM cost reduction (use llm-cost-optimizer).
Engineers prompts into clear, structured, model-optimized instructions using the 4-D methodology (Deconstruct, Diagnose, Develop, Deliver) with architecture-specific tuning. Use when a draft prompt, instruction set, or agent skill description needs refinement for clarity or improved performance.
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.