Agents
Agents d’IA i automatització
implementing-mcp-tools
PostHog
'Guide for exposing PostHog product endpoints as MCP tools. Use when creating new or updating API endpoints, adding MCP tool definitions, scaffolding YAML configs, or writing serializers with good descriptions. Covers the full pipeline from Django serializer to generated TypeScript tool handler.'
upstash-workflow
lobehub
'LobeHub Upstash Workflow and QStash guide. Use for async workflows, process/paginate/execute fan-out, serve handlers, context.run/call/sleep, or workflow triggers.'
1k-monitor-pr-ci
OneKeyHQ
Monitor OneKey PR checks and review threads, fix failures, address comments, and continue until the PR is ready.
zapper
BankrBot
Placeholder for Zapper skill.
yoink
BankrBot
Play Yoink, an onchain capture-the-flag game on Base. Yoink the flag from the current holder, check game stats and leaderboards, view player scores, and compete for the trophy. Uses Bankr for transaction execution.
Lobster
openclaw
One-off tasks that won't be repeated
gh-issues
openclaw
"Fetch GitHub issues, select candidates, spawn background fix agents, open PRs, and optionally process PR review comments."
acp-router
openclaw
Route plain-language requests for Claude Code, Cursor, Copilot, OpenClaw ACP, OpenCode, Gemini CLI, Grok Build, Qwen, Kiro, Kimi, iFlow, Factory Droid, Kilocode, or explicit ACP harness work into either OpenClaw ACP runtime sessions or direct acpx-driven sessions ("telephone game" flow). For coding-agent thread requests, read this skill first, then use only sessions_spawn for thread creation. Codex chat binding defaults to the native Codex app-server plugin unless ACP is explicit or background spawn needs ACP.
discord-user-post
openclaw
Post an approved message as the logged-in Discord user through the Discord desktop app. Use for release announcements or other direct user-authored Discord posts; not for OpenClaw channel sends, bots, webhooks, relays, agent sessions, or archive search.
discord-clawd
openclaw
Use to talk to the Discord-backed OpenClaw agent/session; not for archive search.
canvas
openclaw
"Present hosted widget documents on a connected macOS panel and control panel visibility or navigation."
verify-release
openclaw
"Verify regular or extended-stable OpenClaw releases against the exact publication surfaces, workflow identities, package provenance, and published CLI smoke tests expected for that release track."
clawsweeper
openclaw
"Use for all ClawSweeper work: OpenClaw issue/PR sweep reports, repair jobs, cloud fix PRs, @clawsweeper maintainer mention commands, trusted ClawSweeper-reviewed autofix/automerge, GitHub Actions monitoring, permissions, gates, and manual backfills."
init
mcollina
Creates, updates, or optimizes an AGENTS.md file for a repository with minimal, high-signal instructions covering non-discoverable coding conventions, tooling quirks, workflow preferences, and project-specific rules that agents cannot infer from reading the codebase. Use when setting up agent instructions or Claude configuration for a new repository, when an existing AGENTS.md is too long, generic, or stale, when agents repeatedly make avoidable mistakes, or when repository workflows have changed and the agent configuration needs pruning. Applies a discoverability filter—omitting anything Claude can learn from README, code, config, or directory structure—and a quality gate to verify each line remains accurate and operationally significant.
task-agent-eliza-bridge
elizaOS
"Use when spawning a Claude Code, Codex, Gemini, Aider, or other CLI task agent whose work needs parent Eliza runtime context. Covers the read-only loopback bridge for character, room, memory, and active workspace state."
eliza-app-development
elizaOS
"Use when building or changing an elizaOS-based application in this repository. Covers eliza app architecture, monorepo layout, local versus remote versus cloud routing, where to edit features, and non-negotiable runtime constraints. Eliza is the product name of this particular eliza app checkout."
eliza
elizaOS
"Use for spawned coding/task agents working on the Eliza app or asking what the running Eliza agent can do. Covers the repo CWD, default skill loading and overrides, child-to-parent USE_SKILL calls, parent runtime context APIs, plugin loading/building, Cloud app/payment/domain/media capabilities, and how workers can ask the parent agent to use loaded capabilities."
authoring-skills
vercel
How to create and maintain agent skills in .agents/skills/. Use when creating a new SKILL.md, writing skill descriptions, choosing frontmatter fields, or deciding what content belongs in a skill vs AGENTS.md. Covers the supported spec fields, description writing, naming conventions, and the relationship between always-loaded AGENTS.md and on-demand skills.
subordinate-management
xuiltul
Supervisor tools for subordinate Anima: disable/enable, model changes, restart, delegation, state reads, and audits. Use when: pausing a subordinate, changing main or background models, restarting processes, delegating tasks, or org dashboards.
orchestrate
Significant-Gravitas
"Meta-agent supervisor that manages a fleet of Claude Code agents running in tmux windows. Auto-discovers spare worktrees, spawns agents, monitors state, kicks idle agents, approves safe confirmations, and recycles worktrees when done. TRIGGER when user asks to supervise agents, run parallel tasks, manage worktrees, check agent status, or orchestrate parallel work."
dust-call-agent
dust-tt
Call a Dust agent for Dust company context or to access tools, data, and actions unavailable through the current agent's native capabilities. Never use a Dust agent as a proxy for Slack, Notion, Google Drive, calendars, or any other service when native access is available; use the native tool instead because it is faster and more efficient.
codex-bridge
hushh-labs
Answers questions about and routes tasks for the hushh-research codebase. Use whenever the user asks about or wants to change anything this repo owns, including consent-protocol, Operons, HCT, Kai, MCP, IAM, PKM, vault, backend, frontend, mobile, security, docs, comms, ops, skill authoring, and any new specialist added under .codex/ later. Reads .codex/skills/, .codex/workflows/, and .codex/agents/ at invocation time, composes a briefing the way codex route-task does (workflow plus owner_skill plus default_spoke unioned), surfaces .codex/agents/* as advisory delegation lanes, and auto-discovers anything added to the tree without a bridge edit.
hushh-one-pkm
hushh-labs
Use when an OpenClaw agent needs to access a Hussh One user's Personal Knowledge Model through the Hussh MCP bridge. This covers developer-token setup, dynamic scope discovery, explicit user consent in One/Kai, consent polling, scoped export retrieval, and the privacy boundary for external agents.
one-voice-governance
hushh-labs
Use when changing One Voice capability authoring, Kai compatibility runtime contracts, generated action gateway contracts, typed-search and voice parity, persona/workspace gating, or BYOK-safe durable voice memory.