openclaw

Structured Codex, Claude, Amp, Pi, or Kimi code review when explicitly requested.

Manage OpenClaw GitHub Actions and Blacksmith CI capacity, runner-registration budgets, fanout caps, main-push single-flight, shard sizing, hosted-runner offload, queue health, and safe ramp-down/ramp-up changes. Use when tuning `.github/workflows/*`,…

Prove user-visible OpenClaw Telegram behavior on Telegram's Test Server with Convex-leased team credentials; drive real-user turns and record messages, edits, deletions, reactions, typing, or rich content.

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

Prepare or verify OpenClaw stable, beta, and extended-stable releases, including backport discovery, changelogs, release notes, publish commands, and artifacts.

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

Search meme templates, suggest formats, and generate local or hosted image memes.

Test the latest OpenClaw main commit through an isolated OCM copy or an explicitly approved in-place gateway update, then guide structured release feedback.

Structured code review through the shared OpenClaw agent-skills installation.

Use when reviewing, triaging, validating, or discussing ClawHub GitHub issues or pull requests, including author context, CI, UI proof, evidence, labels, close decisions, and maintainer handoff.

Capture, edit, inspect, and attach real ClawHub browser proof directly to a GitHub PR, with captions, focused zooms, and clearly separated before/after results.

Add an AI agent / RAG backend (@convex-dev/agent) to the Convex app.

Audit and harden a Convex app's authorization: identity-from-arg impersonation, missing per-document ownership checks, public queries leaking data by a client-supplied id, and writes into a parent/container the caller doesn't own. Scans for the 4 shapes,…

Builds reusable Convex components with isolated tables and app-facing APIs. Use for new components, reusable backend modules, integrations, or component boundary work.

Design and build reactive, type-safe, production-grade backends on Convex. Covers schema, queries/mutations/actions, indexes, auth, file storage, scheduling, real-time multiplayer, mobile backends, and LLM/agent workflows on Convex's one-platform stack.

Convex backend specialist. Use this agent for any code inside a `convex/` directory — function definitions, schemas, indexes, queries, mutations, actions, HTTP endpoints, cron jobs, file storage, auth wiring, and component installation. Knows the object-form…

Google Photos operations through gog.

Google Contacts operations through gog.

Google Sheets operations through gog.

Google Search Console operations through gog.

Google Slides operations through gog.

Google AdSense operations through gog.

Apps Script operations through gog.

gog CLI: safe Google Workspace automation, JSON, auth, scoped reads/writes.

Select proportional Enterprise validation and diagnose exact CI runs, distinguishing product, harness, infrastructure, and credential failures.

Develop OpenClaw Enterprise changes with proportional verification and source-backed flow documentation for non-trivial behavior.

Draft or update OpenClaw Enterprise RFCs and implementation plans with repository numbering and lifecycle rules.

Run named OpenClaw Enterprise end-to-end integration scenarios against real supported installations. Use only when explicitly invoked.

Write, organize, name, edit, or review Enterprise developer documentation, specifications, and technical instructions; ground claims in current source and finish with a plain-language cleanup.

Assess designs, public interfaces, state ownership, readability, and refactor proposals when the task calls for design review or structural simplification; not for unrelated routine edits.

Clean only the current Enterprise diff before autoreview, preserving behavior, security boundaries, required TODOs, and useful test-intent comments.

Gate new or changed Enterprise tests and audit existing tests for observable behavior, credible regressions, duplicate coverage, and test-only production seams.

Uninstall or hard-clean OpenClaw Companion, Windows node, native Gateway/MXC, WSL Gateway, and managed llama.cpp/Local AI state for a clean retest. Choose the existing dev CLI uninstall or the reviewed hard-clean procedure, inventory exact targets, and obtain…

Build the native (MSIX, isolated-session) OpenClaw Gateway from the latest openclaw/openclaw sources (or any ref, local checkout, or prebuilt openclaw.tgz), register it side by side with the Microsoft Store Gateway, and run Companion against it with…

Invoke and troubleshoot OpenClaw Windows-node commands through the local winnode CLI and MCP endpoint, including command argument schemas and A2UI JSONL calls.

Adversarial dual-model code review that runs two AI models in parallel, cross-references findings, and produces a consensus severity table with fix confidence ratings. Use when asked for a thorough code review, adversarial review, dual-model review,…

Run complete OpenClaw Windows Node issue and PR triage, including landing queues, proof pools, ownership audits, and release planning.

Plan and collect OpenClaw Windows validation/proof: tests, rubber-duck review, UI evidence, MCP output, and gateway runtime proof.

Use the OpenClaw Windows app's local MCP server and winnode CLI for development, debugging, proof, and automation.

Use Crabbox from macOS, Linux, or native Windows controllers to run OpenClaw Windows node builds, tests, and targeted proof on remote native Windows or WSL2 hosts, including Azure or brokered AWS leases and static SSH hosts. Use when remote Windows validation…

Structured code review when explicitly requested, preferring OpenAI/Codex before Claude.

Hand local work to a shared OpenClaw Gateway: start a worktree session there as yourself in one request, seeded with a handoff, and get the session URL back.

Crabbox/Testbox remote proof: portable provider routing, untrusted isolation, Linux/macOS/Windows/WSL2, live E2E, diagnostics, cleanup.

Requested GitHub PR/issue agent transcripts: redact, trim, preview, and insert safely.

Publish a redacted local coding session to an authenticated read-only Beam catalog.

Render Codex, Claude Code, OpenClaw, or Pi session JSONL transcripts as a searchable, shareable single-file HTML viewer.

House README standard: structure, badge row, tone, per-archetype templates, and verification gates for steipete/openclaw repos.

Source-blind user behavior validation against a prewritten contract for apps, CLIs, APIs, and generated artifacts.

Run PR intent distillation across a PR set and persist outputs + sidecar metadata to /memory/pr-intent.

Side-effect-free distillation of a single OpenClaw PR into a short intent memo (stdout-only).

Land an OpenClaw PR end-to-end using the repo landpr checklist. Use when someone requests “/landpr” or asks to merge/land a PR.

Control CLAWDINATOR fleet lifecycle via the control API. Use for /fleet deploy or /fleet status.

Analyze GitHub and Discord signals to prioritize maintainer attention. Use when asked about priorities, what's hot, what needs attention, or project status.

Monitor Discord channel activity and persist notable items to memory. Run from main session during heartbeat.

Google Workspace CLI for Gmail, Calendar, Drive, Contacts, Sheets, and Docs.

ElevenLabs text-to-speech with mac-style say UX.

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

Capture and automate macOS UI with the Peekaboo CLI.

Search markdown knowledge bases, notes, and documentation using QMD. Use when users ask to search notes, find documents, or look up information.

File watcher with auto-rebuild for any language or build system.

Pre-commit/ship code review: Codex default; optional Claude or Pi.

Use when running or explaining the ClawScan CLI, including one-off agent-skill scans, benchmark runs, scanner fixtures, judge harness commands, env var validation, and interpreting clawscan-run-v1 and clawscan-benchmark-v1 artifacts.

Use when a researcher, maintainer, or contributor found or suspects a malicious skill on ClawHub and needs a private reporting workflow: opening a GitHub private vulnerability report, preparing a proposal-only PR, creating `proposals/<GHSA-ID>/clawscan.yml`,…

Use when an OpenClaw maintainer or owner is reviewing a ClawHub malicious-skill profile proposal PR: checking `proposals/<GHSA-ID>/clawscan.yml`, reading the private vulnerability context without leaking it, running the SkillTrustBench Profile Gate or…

First contact with Crabbox: run your repository's tests inside a disposable Docker or Podman container on your own machine, no account and no cloud spend, then stop the box. Use when someone asks what Crabbox is or how to try it, wants a throwaway sandbox for…

Detect and use Crabbox for repository tests and validation on remote runners. Use when crabbox.yaml or .crabbox.yaml exists, the crabbox CLI is available, or work needs remote compute, a clean or reusable environment, target-platform coverage, or auditable…

Structured Codex, Claude, Amp, Pi, or Kimi code review when explicitly requested.

Perform a diff-scoped, behavior-neutral cleanup of AI-generated slop on the current branch before code review. Use for removing trivial comment, defensive-check, type-laundering, redundant-intermediate, compatibility-shim, or local style drift from the branch…

Refactor a whole documentation page in this repository without losing source-verified behavior facts. Use for page rewrites, splits, reorganizations, or substantial shortening of README sections, docs pages, or instruction files. Do not use for ordinary…

Write, review, or audit this repository's technical documentation, including README.md, CONTRIBUTING.md, root and scoped AGENTS.md files, docs pages, and documentation drift. Use for source-backed documentation authoring, behavior verification, and…

Peekaboo release: notarization, npm/GitHub release, appcast, verify, closeout.

Use Peekaboo for macOS screenshots, Accessibility inspection, and background app/window/UI automation, including fallback computer use when the primary tool cannot handle an authorized task.