Latest Agent Skills

Use when an agent needs to design or build Agent Internet MetaApps, convert a local static HTML site, frontend project, or ZIP into an on-chain MetaApp, create Bot homepage/Bot Page MetaApps from Bot Homepage v3 data, or preview, publish, update, share, view, delete, or comment on MetaApps through Open Agent Connect.

Use when a human asks to connect to or enter Agent Internet or AI Internet, get their agent online, or open Agent Internet Browser, Bot Browser, a Bot page, a Bot homepage, a domain alias, a chain pin, a MetaApp, a MetaFile, or a map through the existing local Browser entrypoint, including opening a resource in a new Browser tab; also use when the human wants to find or discover on-chain MetaApps by topic, tag, publisher, or time range — such as "what on-chain mini-games exist", "apps published in the last 30 days", or "open the on-chain buzz app" — list the remixes of a known app, read what an app does, or remix and republish an existing MetaApp; also use when the human wants to find or discover on-chain users or Bots by name, personality, skill, or recency — such as "view Alice's bot page", "find cheerful users to chat with", or "find a bot that can translate" — or read an identity's full on-chain profile.

Use when a human asks what OAC, Open Agent Connect, MetaBot, metabot, Bot, or bot can do; asks for available features, abilities, functions, usage examples, or a capability map; or needs an explanation of what the user can accomplish through OAC/MetaBot/Bot after installation. This skill dynamically summarizes installed metabot-* skills and metabot CLI help instead of relying on a static feature list.

Run, watch, debug, and summarize MarketingClaw full release CI, release checks, live provider gates, install/update proofs, and release-secret preflights.

Run, watch, debug, extend, or explain MarketingClaw qa-lab and qa-channel scenarios, artifacts, and live lanes.

Build and review high-quality technical docs as well as agent instruction files in your repository.

Debug MarketingClaw model, provider, tool-surface, code-mode, streaming, and live/Crabbox behavior by choosing the right logs, probes, and proof path before changing code.

Manage MarketingClaw GitHub Actions and Blacksmith CI capacity, runner-registration budgets, fanout caps, main-push debounce, shard sizing, hosted-runner offload, queue health, and safe ramp-down/ramp-up changes. Use when tuning `.github/workflows/*`, `docs/ci.md`, CI runner labels, matrix `max-parallel`, ClawSweeper/Blacksmith burst protection, CodeQL runner placement, or investigating slow/queued MarketingClaw CI.

QQ channel management skill. Use qqbot_channel_api for explicit QQ channel-management requests; confirm write, delete, and bulk actions before calling authenticated QQ Open Platform endpoints.

Feishu cloud storage file management. Activate when user mentions cloud space, folders, drive.

QQBot scheduled reminders. Use only for explicit user requests to create, list, or cancel one-time or recurring QQ reminders; ask for missing time, content, or timezone before scheduling.

Feishu knowledge base navigation. Activate when user mentions knowledge base, wiki, or wiki links.

Feishu permission management for documents and files. Activate when user mentions sharing, permissions, collaborators.

Choose, run, rerun, or debug MarketingClaw tests, CI checks, Docker E2E lanes, release validation, and the cheapest safe verification path.

Use when running QA Lab channel message flow evidence.

QQBot rich media send and receive support. Use <qqmedia> tags only for explicit media send/view requests, treating inbound attachment paths as private current-conversation context.

Feishu document read/write operations. Activate when user mentions Feishu docs, cloud docs, or docx links.

OpenProse VM skill pack. Activate on any `prose` command, .prose files, or OpenProse mentions; orchestrates multi-agent workflows.

Discord message-tool ops: send/read/edit/delete, react, poll, pin, thread, search, presence, media/components.

Route plain-language requests for Claude Code, Cursor, Copilot, MarketingClaw ACP, OpenCode, Gemini CLI, Qwen, Kiro, Kimi, iFlow, Factory Droid, Kilocode, or explicit ACP harness work into either MarketingClaw 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.

Send third-party WhatsApp messages or sync/search WhatsApp history via wacli, not normal active chats.

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 MarketingClaw channel sends, bots, webhooks, relays, agent sessions, or archive search.

Tavily web search, content extraction, and research tools.

Use the imsg CLI from MarketingClaw agents for iMessage/SMS DMs, groups, replies, reactions, polls, watching, and private-API actions.

Present HTML on connected MarketingClaw node canvases, navigate/eval/snapshot, and debug canvas host URLs.

Add a redacted agent transcript section to GitHub PR or issue bodies during MarketingClaw agent-created PR/issue workflows.

Triage MarketingClaw security advisories, drafts, and GHSA reports with shipped-tag and trust-model proof.

Slack tool actions: send/read/edit/delete messages, react, pin/unpin, list pins/reactions/emoji, member info.

Use the diffs tool to produce real, shareable diffs (viewer URL, file artifact, or both) instead of manual edit summaries.

Verify an MarketingClaw release is fully published across GitHub, npm, plugins, ClawHub, package smoke, and live Gateway agent turns.

Use when testing, fixing, or extending the MarketingClaw Control UI GUI with Vitest + Playwright end-to-end checks, mocked Gateway WebSocket flows, mocked dashboard runs, screenshots/videos, or agent-verifiable browser proof.

Example TaskFlow pattern for inbox triage, intent routing, waiting on replies, and later summaries.

Debug Node.js with node inspect, --inspect, breakpoints, CDP, heap, and CPU profiles.

Use to talk to the Discord-backed MarketingClaw agent/session; not for archive search.

Use for MarketingClaw clawtributors PR/issue triage: Discrawl discovery, live-open rechecks, deep review, topic grouping, and compact @handle/LOC/type/blast/verification summaries.

Use for all ClawSweeper work: MarketingClaw issue/PR sweep reports, commit-review reports, repair jobs, cloud fix PRs, @clawsweeper maintainer mention commands, trusted ClawSweeper-reviewed autofix/automerge, GitHub Actions monitoring, permissions, gates, and manual backfills.

OpenAI Audio Transcriptions API via curl; gpt-4o-transcribe, mini, diarize, or whisper-1.

Granola archive: search, sync freshness, notes, transcripts, panels, SQL counts, and Graincrawl repo work.

Audit or refresh MarketingClaw maturity scorecard docs from root taxonomy, maturity scores, and QA evidence artifacts without using maintainer discrawl data or committed inventory reports.

Pre-commit/ship code review: Codex default; optional Claude, Pi, Droid, Copilot, Cursor, or OpenCode.

Producing the weekly/monthly marketing report — pulling GA4, Search Console, Listmonk, and Postiz numbers via the sibling skills, writing it to the shared REPORTS/ directory from a template, and sending the highlights.

Finding and expanding keyword opportunities for free — mining Search Console queries for high-impression/low-position pages, expanding via Google Autocomplete, and snapshotting SERPs with web search; optional paid DataForSEO volume/difficulty data.

Slack archive: search, sync freshness, threads/DMs, SQL counts, and Slacrawl repo work.

Notion archive: search, sync freshness, pages/databases, Markdown exports, SQL counts, and Notcrawl repo work.

GitHub archive: issue/PR search, sync freshness, duplicate clusters, gh-shim PR status, and Gitcrawl repo work.

Discord archive: search, sync freshness, DMs, summaries, TUI, repo/release work.

Local text-to-speech via sherpa-onnx (offline, no cloud)

List, add, edit, complete, or delete Apple Reminders and reminder lists via remindctl.

Use the Crabbox wrapper for MarketingClaw remote validation across Linux, macOS, Windows, and WSL2, including delegated Blacksmith Testbox proof. Report the actual provider and id.

Terminal Spotify playback/search via spogo (preferred) or spotify_player.

Debug Python with pdb, breakpoint(), post-mortem inspection, and debugpy remote attach.

Local speech-to-text with the Whisper CLI (no API key).

Create, edit, audit, tidy, validate, or restructure AgentSkills and SKILL.md files.

Create SVG/HTML or Excalidraw diagrams for concepts, architecture, flows, and whiteboards.

Extract frames or short clips from videos using ffmpeg.

Search and analyze your own session logs (older/parent conversations) using jq.

Diagnose MarketingClaw Android, iOS, or macOS node pairing, QR/setup code, route, auth, and connection failures.

Delegate coding work to Codex, Claude Code, or OpenCode as background workers; not simple edits or read-only code lookup.

Summarize CodexBar local cost logs by model for Codex or Claude, including current or full breakdowns.

Audit/harden MarketingClaw hosts: SSH, firewall, updates, exposure, backups, disk encryption, gateway security.