
Run live OpenClaw integration proof against a named claw gateway profile with showboat-v2.
Manage Git preflight, branches, worktrees, pushes, and completed-work cleanup. Use whenever creating a pr or when explicitly invoked.
Research verified local events and create ranked, source-linked activity reports.
Create, update, or optimize skills and SKILL.md content.
Coordinate explicitly requested subagent work as a manager.
Reproduce and fix OpenClaw issues with Showboat proof, managed implementation, and repo-local integration gateways.
Preview available meeting options and create Google Calendar invites with attendee availability and room booking after confirmation. Use when directly invoked via $cal or when asked to schedule a meeting.
Implement, fix, refactor, or otherwise modify source code.
Convert an existing static HTML site into a private Codex Site, optionally adding a persistent authenticated API and local programmatic writes. Use only when deliberately invoked as $html2site.
Load local dotenvx credential sets for agent workflows.
Proofread publish-ready drafts for meaningful clarity issues and broken links while preserving the author's voice.
Improve skills from agent friction or derive steering principles from user corrections.
Fork or create a Codex thread from a prompt, with optional model and reasoning overrides. Fork by default; create without parent history when the user explicitly asks for a new, fresh, or clean thread.
Turn response annotations and review comments into a question-and-answer FAQ.
Create a self-contained interactive HTML explanation of a code diff, branch, commit, or pull request.
Refactor an existing OpenClaw docs page with source-audited preservation, restructuring, and verification.
Read a Markdown task file, parse frontmatter, split work by level-2 headings outside code fences, and execute each section with subagents while keeping level-3 headings as ordered follow-on instructions for the same subagent.
Use only when explicitly invoked to manage ~/integ/[project] harness repos.
Record, sync, and query local agent activity ledger entries.
Create, inspect, remove, or transactionally clean landed Git worktrees.
Install or document local command-line tools end to end.
List, inspect, validate, or materialize bundled file schemas.
Watch a pull request and CI until green or needing fixes.
Search prior Codex conversations and return up to 3 relevant thread matches with deep links. Use when explicitly invoked as `$convosearch [query] | [filters]`.
Build, publish, and verify OpenClaw Docker/GHCR images. Use when the user asks to build an OpenClaw image, publish or republish GHCR tags, bundle official plugins such as @openclaw/codex, @openclaw/slack, or @openclaw/diagnostics-otel, make or verify multi-arch linux/amd64 and linux/arm64 images, check GHCR visibility, secret-scan an image, enforce Codex image contract gates, or prove a published OpenClaw Docker image works.
Land completed work and update AGD status docs.
Send explicit Slack notifications through `slack-post`.
Create, edit, analyze, or visualize spreadsheet files.
Add an Apache 2.0 license and update package metadata.
Run in fast-mode with only explicitly allowed skills.
Turn an existing concrete spec into a reusable generic spec template. Use when asked to create a generic spec, template spec, reusable implementation template, or generalized version of a spec from a specific implementation such as one plugin, channel, integration, feature, or PR.
Audit documentation rewrites with JSON-first, block-scoped, line-level coverage mappings. Use for moved-section checklists, preservation proofs, migration maps, or line-by-line coverage reviews of Markdown/MDX docs.
Use 1Password CLI safely for agent credential workflows.
Write or review high-quality OpenClaw developer documentation.
Use only when explicitly invoked to manage ~/integ/[project] harness repos.
Fill TODO, placeholder, or missing Markdown links.
Create executable Showboat demos that prove behavior.
Write or review Stripe-style developer documentation.
Create or revise engineering diagrams in ASCII or Mermaid.
Write repository-appropriate git commit messages by first checking local history, then matching that repo's conventions. Use when asked to draft a commit message, explain how a repo formats commits, or adapt commit style across different repositories.
Sweep recent OpenClaw GitHub issues, filter for real unstarted bugs, and write a report to $mem claw/main reports.
Manage Linear issues and projects through `linear-cli`.
Trace how something works with an investigator subagent and a skeptical reviewer subagent.
Manage Codex self-configuration and session analysis; not skill authoring (use $sc).
Audit a repo for code quality issues using focused heuristics.
Create tracked tasks or issues with session context.
Determine whether test failures come from the current branch.
Scan a repo for sensitive data before making it public.
Create, edit, review, or extract Word docx documents.
Simulate implementing a spec against the real source code, then grade the spec as correct, comprehensive, and simple. Use only when explicitly invoked as $spec-simulate or when the user asks to simulate implementation from a spec.
Write sudocode from real code for docs and specs.
Add or update CLI maturity ratings in repo docs.
Generate incremental Slack digests for channels, topics, and categories.
Optimize skill instructions, resources, and usability.
Read a Markdown task file, parse frontmatter, split work by level-2 headings outside code fences, and execute each section with subagents while keeping level-3 headings as ordered follow-on instructions for the same subagent.
Write or review technical documentation.
Automate browser navigation, interaction, screenshots, and extraction.
Judge agent work as approve, reject, or escalate.
Use when creating TypeScript projects or add TypeScript pre-commit checks.
Draft, validate, or explain Conventional Commit messages.
Find, map, or resume Codex CLI sessions.
Run a development task from intake through implementation.
Refresh a repo by syncing local master from origin.
Audit an OpenClaw maturity-scorecard surface into an evidence-backed component score report. Use when given a surface from an OpenClaw maturity-scorecard.md and asked to score coverage, quality, readiness, or generate a detailed surface report plus per-component subreports.
Generate project icons, logos, or inline brand marks.
Create or improve Hacker News submission titles.
Link the current Codex session to a durable Markdown task note.
Create, edit, extract, or analyze PDF documents.
Summarize Codex activity from the agent ledger.