Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Agent workflows
Optimize Codex Plus/Pro usage before and during coding tasks. Use when the user wants to save Codex quota/credits, reduce token or context waste, choose a cheaper model/reasoning level, avoid unnecessary repo scans/tests/subagents, or plan an implementation with the smallest reliable execution footprint. Do not use when the user explicitly prioritizes maximum quality regardless of usage.
Iterative code review and planning discussion between the local agent and Codex CLI. Orchestrates an automatic back-and-forth debate where both agents discuss findings, architecture decisions, or implementation plans until reaching consensus. Codex CLI runs READ-ONLY and never modifies files; model and reasoning effort come from the user's local Codex config. Supports plan mode: when the local agent has a plan ready, Codex evaluates and iterates on it before implementation, producing an updated consensus plan. Use when the user asks to review with codex, analyze with codex, discuss code with codex, iterate with codex, consult codex, ask codex, review the plan with codex, validate plan with codex, or any Codex CLI request for code review, architecture review, plan review, or implementation strategy. Does NOT trigger on non-code topics like diet, fitness, writing, life decisions, or general strategy; use codex-discuss for those.
Find prior LifeOS work — sessions, ISAs, conversations — by topic or date phrase; searches the work registry, titles, dir names, ISA bodies, and conversation logs, ranked by relevance. USE WHEN context search, prior work, browse sessions, recall, remember, previous sessions, context recovery, what did we do, find session, search history, what was that project, pick up where we left off, resume, look up old work, cold start, yesterday's work, last week, find that session, the one about. NOT FOR searching published content like blog posts/newsletters/tweets, or the typed-graph Knowledge Archive (use Knowledge).
Create new commands for the code-forge application. Commands are stored as .md files in the <cwd>/.forge/commands directory with YAML frontmatter (name, description) and markdown body containing command steps. Use when users need to add new commands, modify existing commands, or understand the command file structure. Supports special command tags like <lint> and <test> for automated workflows.
Distill a crush into an AI Skill. Import chat history, photos, social media, generate Relationship Memory + Persona, with continuous evolution. | Distill a crush into an AI Skill, import chat history, photos, social media, generate Relationship Memory + Persona, with continuous evolution.
Choose the interaction mode, capability level, risk, dispatch shape, review, and limited fallback for non-trivial Agent tasks whose goal, scope, and authorization are already clear. Applies to work that needs a choice between handling directly in the main Agent, a single task agent, and limited parallelism, or that needs the capability level and review intensity decided by complexity and risk; when a project in the current harness lacks a validated Agent configuration, also use this skill to guide the user in choosing to create, preview, or skip. Do not use for simple Q&A, read-only confirmations, or small changes that can be verified directly.
Use when writing or reviewing JavaScript/TypeScript in this repo that builds an interactive voice agent via `agent.deepgram.com/v1/agent/converse`. Covers `client.agent.v1.createConnection()` / `connect()`, `sendSettings`, `sendMedia`, runtime updates, event handling, and function-call responses. Use `deepgram-js-text-to-speech` for one-way synthesis, `deepgram-js-speech-to-text` or `deepgram-js-conversational-stt` for transcription only, and `deepgram-js-management-api` for project/model admin rather than live agent runtime. Triggers include "voice agent", "agent converse", "full duplex", "barge-in", "function calling", and "agent.v1".
Build a dependency graph over a batch of work items — issues, tasks, tickets — and surface the frontier of items that can start now. Use when planning parallel or ordered execution, checking whether two items would collide, or when another skill needs to sequence a batch.
Distill knowledge from any source — blog posts, articles, documentation, GitHub repos, video transcripts, books, papers — into a well-structured agent skill. Use when the user shares a URL, article, repo, or body of knowledge and wants it turned into a reusable skill. Triggers on: "make a skill from this", "distill this into a skill", "create a skill from this article", "turn this repo into a skill", "extract patterns from", "convert to a skill". This skill complements the `skill-creator` skill — skill-creator handles the mechanics (frontmatter, packaging, init scripts), this skill handles the distillation process.
This skill should be used when the user asks to "execute this blueprint", "run the plan", "execute the plan", "start building from the plan", "implement the blueprint", "implement the plan", "continue the plan", "resume execution", "execute 01_milestone_name.md", "execute step 3", "run steps 3-5", or "skip to step 4".
Convene a council of AI coding agents before finalizing a plan. The agent you're talking to — whichever CLI is the lead (claude, codex, cursor, gemini, grok, opencode) — drafts a plan, presents it independently to every other agent CLI installed on the machine, each member gives ONE reply per turn, and the lead revises the plan for X turns before answering. Trigger words: council, convene the council, consult the other agents, ask the council, ask codex/cursor/gemini/grok what they think, second opinion from other agents, N turns of deliberation, deliberate before planning.
Use when the user wants to find plugins for DeepSeek Harness: "Is there a plugin that can…", "help me install XX", "what's fun in the ecosystem". Discover public repositories across individuals and organizations from the dsh-plugin topic on all of GitHub, filter candidates, wait for the user to decide, first report what permissions the plugin requires, then determine the installation method from the repository declaration and verify mounting. Only handles finding and installing; for developing new plugins, switch to make-dsh-plugin.
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.
A global integrated development and collaboration workflow skill covering the full chain of requirement assessment, development, testing, quality, documentation, commit and release, able to integrate all basic atomic skills and automate the PDTFC+ loop with optimized division of labour and collaboration.
Audit plugin skills, commands, and agents for agentic output optimization compliance such as missing Agentic Optimizations tables, bare CLI commands without compact/JSON flags, and stale review dates. Use when the user wants to batch-check skill documentation quality, find skills lacking compact output flags, enforce agentic optimization standards across the repo, or identify skills with `modified` dates older than 90 days.
Use when the user wants several open issues built by agents and turned into pull requests — "work through the issues", "implement the open issues", "clear the backlog", "open PRs for #12 and #15" — optionally at an effort level ("/implement-issues low", "at medium effort"), and when plan pull requests it opened are approved or have comments to answer. Works in Claude Code, Codex, or any agent that can dispatch subagents. Not for one issue the user is building themselves in this session.
Parallel adversarial review protocol that launches two independent blind judge sub-agents simultaneously to review the same target, synthesizes their findings, applies fixes, and re-judges until both pass or escalates after 2 iterations. Trigger: When user says "judgment day", "judgment-day", "review adversarial", "dual review", "doble review", "juzgar", "que lo juzguen".
Interact with MCP (Model Context Protocol) servers using the mcporter CLI. Use this skill when you need to list available MCP servers, view tool schemas, call MCP tools, manage OAuth authentication, or generate CLI wrappers and TypeScript types for MCP servers.
Operate the user's already-open, logged-in Chrome tabs through Chrome DevTools MCP. Use whenever the user asks the agent to jump into their current browser, continue work in an existing tab, fill or submit a form, write or post a comment or reply, update a page, inspect what is open, or interact with signed-in web apps such as Confluence. Also use as the browser-driving companion to melech-debug-mode; do not start a debugging collector for ordinary browser work.
Mechanism-level write path for a remindb MCP server. Two ways to persist memory by content shape — structural/multi-part content as a source file under $REMINDB_SOURCE (compile plane → parsed node tree), a single text update via MemoryWrite (flat node, no parsing) — plus MemorySummarize/MemoryForget/MemoryRollback/MemoryPin/MemoryRelate. Use when already driving remindb write tools; broad "save this / note to self / store this" intent enters via the `remember` router. Pair with `remind` for reads.
Use when the user asks to "plan & implement", "plan this work", "research & build", "plan auth/API/work", or needs a multi-step pipeline from understanding through implementation. Flow is Understand → Research → Plan → Implement → Verify. For design documents or technical proposals without implementation, use octocode-rfc-generator instead.
Inter-instance communication for OpenClaw. Use this skill when you need to pass messages, sync data, or execute commands remotely between multiple OpenClaw instances. Covers agent-to-agent messages, nodes.run remote execution, file-level communication and more.
This skill should be used when the user mentions "openclaw", "OpenClaw CLI", asks to "send a message via openclaw", "manage openclaw agents", "configure openclaw gateway", "check openclaw status", "run openclaw agent", or asks about OpenClaw setup, channels, devices, or messaging automation.
Use the Opper CLI (`opper` command, npm package `@opperai/cli`) for terminal work with Opper: signing in, calling functions, inspecting traces, tracking usage and costs, generating images, installing bundled skills, configuring AI code editors, and launching coding agents (Claude Code, OpenCode, Codex, Hermes, Pi) with their inference routed through Opper. Use this skill whenever the user mentions the `opper` command, the Opper CLI, opper-ai/cli, `@opperai/cli`, `opper launch`, or explicitly wants shell commands, editor configuration, private local key delivery, or agent launch workflows. Prefer opper-mcp for agent-assisted setup, platform management, and model tests. For exact arguments, always run `opper <subcommand> --help`; the help output is the authoritative reference.
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.
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.
Run a sustained, multi-agent vulnerability-discovery campaign against a target: split its attack surface into slices, have builder agents hunt each slice, and have a separate critic with fresh context adversarially refute every candidate against the real artifact (a reproduced crash, a working request, a proven bypass) before it counts as a finding. Use when tasked with finding previously unknown bugs across a whole codebase, a binary, or a named live target; when you want to fan out many agents and loop until findings are proven rather than plausible; or when a single audit pass has stalled and you need builder/critic separation so the hunter never grades its own work. Dispatches auditing-code-for-vulnerabilities, analyzing-binaries, and testing-web-applications as per-slice hunters and hands proven findings to reporting-security-findings
Coordinate an end-to-end Jira or GitHub work-item workflow from initial fetch through per-task implementation. Use this skill when the user provides a Jira ticket URL, a GitHub issue URL, owner/repo/issue coordinates, says "work on ticket PROJECT-123", "work on issue owner/repo#42", "resume <work-item-key>", "continue this workflow", or asks for status without naming a specific phase. This top-level coordinator detects the platform from the input, loads the matching playbook just-in-time, keeps SKILL.md as a routing layer, and dispatches execution-heavy work to downstream skills or co-located utility subagents.
Proposal strategist and pipeline orchestrator — routes multimodal briefs through intake, research, pricing, and generation with guided check-ins or autonomous mode. Use when the user wants to run a full proposal pipeline, start a new proposal, resume an in-progress run, record win/loss outcomes, or get routed to the right proposal workflow. Triggers: 'run a proposal', 'proposal pipeline', 'start a new proposal', 'guided proposal mode', 'autonomous proposal', 'record proposal outcome', 're-price Acme brief', 'where is my proposal', 'proposal orchestrator'.
Review an already-authored PlanWeave plan for goal coverage, data-flow coverage, lifecycle gaps, contract drift, execution graph errors, weak prompts, and unverifiable completion criteria. Use when auditing, reviewing, checking, or challenging a PlanWeave plan before execution.
Coordinate end-to-end PlanWeave execution as the main agent by inspecting status, assigning work to subagents, routing review and recovery, and keeping the plan loop moving. Use when orchestrating a full PlanWeave plan, managing multiple agents, continuing execution, or deciding what should run next.
Create a PlanWeave package-shaped plan draft from a fuzzy goal, sparse requirements, codebase context, or a user idea before a formal Plan Package exists. Use when the user asks to make, draft, design, break down, or plan PlanWeave work without an existing PRD, roadmap, issue set, or strong source plan. Materialize a Plan Package only when the user explicitly asks.
Diagnose and recover PlanWeave execution anomalies such as stale current refs, state/results drift, orphan artifacts, blocked or diverged blocks, submit retries, and review-feedback loop inconsistencies. Use when PlanWeave execution state looks wrong, doctor reports issues, submit partially succeeded, or coordinator cannot safely continue.
Full-stack development and architecture design assistant, covering scenarios such as "development, implementation, writing code, continuing development, bug fixing, code refactoring, architecture design, technical solution evaluation/code review", suitable for full-stack R&D tasks in new projects and existing code repositories.
Pydantic AI Python agent framework. Covers typed tools, model providers, evals, MCP, UI adapters, and observability. Use when building Python AI agents with Pydantic AI, configuring model providers, implementing typed tools/dependencies, running evals, or integrating MCP servers. Keywords: pydantic-ai, agents, evals, MCP, Logfire.
QA team for outside-in validation, side-by-side parity loops, and A/B behavioral comparison. Use when you need behavior-driven tests, legacy-vs-new comparison, or rollout shadow validation. Creates executable scenarios and parity workflows that agents can observe, compare, and iterate on. Supports local, observable tmux, remote SSH, and shadow-mode divergence logging patterns.
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.