Canonical 7-green PR merge criteria, PR status check pattern, PR freeze discipline, and admin merge protocol
Audit WorldArchitect.AI dice rolls for fairness and anomalies; use when analyzing campaign dice data.
Guide and workflow for Dice Roll Authenticity Standards. Use when you need Dice Roll Authenticity Standards.
Use when completing tasks, implementing major features, or before merging to verify work meets requirements — from jleechanorg/claude-commands
Use when debugging unauthorized/fallback errors. Flags redacted placeholders (e.g. __OPENCLAW_REDACTED__) as invalid tokens; checks env overrides first.
Manual Playwright MCP setup and JSON-RPC usage; use when interacting with Playwright MCP without automatic integration.
Run or maintain the cmux approval worker that scans cmux terminal surfaces for approval dialogs, classifies them with `codex exec`, and sends the matching approval key.
Guide and workflow for Testing Infrastructure. Use when you need Testing Infrastructure.
Steering work on $USER's Ubuntu machine (jeff-ubuntu) via SSH. Use when asked to run commands, install software, check services, or manage files on the Ubuntu box.
Guide and workflow for LLM Prompt Engineering - System Instruction Best Practices. Use when you need LLM Prompt Engineering - System Instruction Best Practices.
Use BEFORE any cost/latency optimization. A/B control MUST be deployed prod config; gate code-start on stated $X/mo savings; reject forced-OFF controls.
Define evidence requirements for end-to-end streaming chunk delivery and timing.
Guide and workflow for Gemini Code Execution + JSON Mode Compatibility. Use when you need Gemini Code Execution + JSON Mode Compatibility.
Use whenever running an AO spawn. Honors exact --agent/--runtime/--project/--claim-pr; verifies session metadata; never silently substitutes a different worker.
Design modal agents that cannot be exited until explicit completion choices are selected.
Use Claude Code to run computer-use style UI automation loops with screenshot → decide → act cycles, safety guardrails, and step-bounded execution.
Generate comprehensive, systematic test suites for any system component using a structured test design methodology.
Control cmux tabs, workspaces, and terminal panes via Unix socket. Use when reading terminal output, sending commands to another agent's pane, switching tabs, or monitoring coder…
Reproduce CI smoke test failures locally, especially MCP smoke and streaming contract failures.
How to run pairv2 directly and via the benchmark script, including what "minimax" means as a CLI option
Use after every `git push` on a PR — enumerates ALL current gate failures, fixes ALL in one local pass, and pushes once. The fix-all-before-push invariant.
Guide and workflow for GCP Deployments Reference. Use when you need GCP Deployments Reference.
Diagnose and fix AO lifecycle-worker backfill failures (stale worktrees, branch conflicts, claim_failed loops)
Use BEFORE creating a new PR. Checks existing open PRs in same scope; stops at ≥3; rebase/cherry-pick from closed PRs instead of duplicating.
Audit Slack channel threads for untracked work items — checks each thread against GH issues/PRs, reports gaps, and optionally redrives dropped threads by posting a status reply to…
Run matched A/B reviewer calibration for /f through the binary-owned review controller, using digest-bound prompts, envelopes, and receipts.
Use when spawning, steering, or auditing Agent Orchestrator workers, especially when the user specifies exact AO parameters such as codex, runtime, project, claim-pr, or PR…
Guide and workflow for Code Centralization - Mandatory Investigation Protocol. Use when you need Code Centralization - Mandatory Investigation Protocol.
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions — from…
Use when fixing broken automation (CI, gates, hooks). A commit is NOT a fix; verify the fix is active post-deploy; restart gateway after config.yaml changes.
Use BEFORE running any automation loop. Requires stating the observable success output (PR, fixed test, push); rejects prediction-only loops.
Classifies GitHub issues/PRs into PR-type categories and recommends autor techniques. Used by packages/core/src/decomposer.ts.
Reproduce a bug, then drive a root-cause-classified fix. Use when asked to /repro a bug, file a REPRO issue, or escalate a regression.
Verify gitignored OpenClaw secret files are present and fresh in Dropbox backup.
Guide and workflow for Chrome Superpowers MCP - Reference Guide. Use when you need Chrome Superpowers MCP - Reference Guide.
Review video evidence by extracting frames with ffmpeg and inspecting key UI states.
Use when designing or reviewing model-owned contracts, output schemas, backend guards, routing, semantic parsing, intent detection, or data fields where application code might…
Diagnose why the automation system is not autonomously driving PRs to green and merge.
Backup all cmux workspaces, surfaces, and their current working directories via the socket API. Produces a timestamped JSON snapshot at ~/.cmux-backups/.
Use when adding/changing a metric (zero-touch, smoothness, etc.). Wires canonical doc, README, AGENTS.md, CLAUDE.md, monitor script in the same pass.
Securely guide teammates through cloud configuration, secrets management, and incident triage
Sparse conversation history triage for current repo/worktree using ~/.claude/projects and ~/.codex/sessions with strict context budgets.
Pre-report gate — verifies all planned evidence artifacts exist before writing comparison/validation reports
Use BEFORE claiming a UI bug fix is complete. Enforces RED-before-GREEN: reproduce the bug, verify the broken element, disclose environment gaps.
Canonical definition of zero-touch-by-operator for PR autonomy measurement. Use when evaluating, reporting, or labeling PR autonomy status.
Token-efficient second opinion slash command /advice. Extracts decision point + artifact (≤150 lines), then fans out in parallel: (1) Opus subagent reviewer with fallback chain…
Use BEFORE infra specs (CI/runner routing/deploy config). Confirm key behavioral decisions explicitly; flag infeasible numeric targets as STOP.
Example/seed/fixture files must use placeholders not real credentials. Pre-commit grep check + enforcement hooks.
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies — from jleechanorg/claude-commands
Guide and workflow for WorldArchitect.AI Local Debugging Reference. Use when you need WorldArchitect.AI Local Debugging Reference.
Safe gateway upgrade/downgrade with pre-flight checks, rollback, and post-verification
Create macOS launchd cleanup agents with dry-run verification. Writes cleanup script + plist installer, verifies with --dry-run, then installs and runs live.
Run one benchmark script that compares pairv2, pair via Claude Teams, and pair via direct Python
Complete reference for GitHub CLI (gh) installation, authentication, and usage in Claude Code environment
Guide and workflow for Integration Verification Protocol. Use when you need Integration Verification Protocol.
Detailed procedures for hook re-fire short-circuit — sentinel files, CR incremental-mode detection, Branch A caps, stale review dismissal commands
API skill for mvp-site-app-dev-i6xf2p72ka-uc.a.run.app. Use when: interacting with this site's APIs, automating workflows, debugging requests.
Use thinclaw MCP server — thin inference-less bridge to OpenClaw Gateway for executing tools
API skill for mvp-site-app-dev-i6xf2p72ka-uc.a.run.app. Use when: interacting with this site's APIs, automating workflows, debugging requests.
Enforcement rules for reviewing evidence artifacts against the evidence-standards skill. Invoked by /er. Produces PASS / PARTIAL / FAIL verdicts.