Codex-native AO evolve loop. Run a deterministic local observe/measure cycle, then optionally delegate targeted fixes via /claw using the canonical evolve-loop skill.
Use when installing/modifying any ~/Library/LaunchAgents plist. Requires template in repo that owns the job; @HOME@ placeholders; install-launchagents.sh cleanup.
Pre-report gate — verifies all planned evidence artifacts exist before writing comparison/validation reports
Use BEFORE infra specs (CI/runner routing/deploy config). Confirm key behavioral decisions explicitly; flag infeasible numeric targets as STOP.
Reproduce CI smoke test failures locally, especially MCP smoke and streaming contract failures.
Canonical 7-green PR merge criteria, PR status check pattern, PR freeze discipline, and admin merge protocol
TDD-driven evidence workflow for generating authoritative failure/fix proof in PRs.
Guide and workflow for LLM Prompt Engineering - System Instruction Best Practices. Use when you need LLM Prompt Engineering - System Instruction Best Practices.
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 running any automation loop. Requires stating the observable success output (PR, fixed test, push); rejects prediction-only loops.
Diagnose and fix AO lifecycle-worker backfill failures (stale worktrees, branch conflicts, claim_failed loops)
Complete reference for GitHub CLI (gh) installation, authentication, and usage in Claude Code environment
Use when dispatching work through the Hermes gateway with /claw, especially when the task may resolve slash commands or hand off into AO worker orchestration.
Analyze conversation and git history to find gaps where cold reviews (codex, Bugbot, CodeRabbit, /reviewdeep) caught issues that dark-factory in-pipeline reviewer nodes missed.
API skill for mvp-site-app-dev-i6xf2p72ka-uc.a.run.app. Use when: interacting with this site's APIs, automating workflows, debugging requests.
Pre-flight checklist for self-hosted runner failures. Use when investigating low disk, missing runner, or stuck Green Gate on the jleechanorg/worldarchitect.ai fleet.
Guide and workflow for WorldArchitect.AI MCP Server Usage. Use when you need WorldArchitect.AI MCP Server Usage.
Define a goal with success criteria and run autonomous convergence loop until criteria are met
Standardize br bead follow-ups for PR reviews and code reviews so each bead includes exact implementation instructions, API/function signatures, and acceptance criteria.
Design modal agents that cannot be exited until explicit completion choices are selected.
Record captioned terminal evidence videos and publish them as GitHub PR attachments with portable, sanitized outputs
API skill for mvp-site-app-dev-i6xf2p72ka-uc.a.run.app. Use when: interacting with this site's APIs, automating workflows, debugging requests.
Guide and workflow for Gemini 3 API (google-genai) - Usage Notes. Use when you need Gemini 3 API (google-genai) - Usage Notes.
Dark Factory spec workflow (/factory-spec, /fs): create a reviewed spec via the spec_gen pipeline, review an existing spec, or display the pipeline node graphs — spec-review…
Run one benchmark script that compares pairv2, pair via Claude Teams, and pair via direct Python
Verify gitignored OpenClaw secret files are present and fresh in Dropbox backup.
Diagnose local OpenClaw gateway model routing, runtime status, and WorldArchitect integration.
Guide and workflow for Chrome Superpowers MCP - Reference Guide. Use when you need Chrome Superpowers MCP - Reference Guide.
Generate comprehensive, systematic test suites for any system component using a structured test design methodology.
Use when adding/troubleshooting MCP servers. Installs to stable paths (npm -g, uvx, uv tool); updates ~/.config/mcp-daemon/start-mcp-daemons.sh for HTTP MCPs.
Use when completing tasks, implementing major features, or before merging to verify work meets requirements — from jleechanorg/claude-commands
Run the Dark Factory DOT pipeline runner against a goal. Slash command: /factory. Implements StrongDM's Attractor pattern as an external Python runner — .dot files are the…
Create macOS launchd cleanup agents with dry-run verification. Writes cleanup script + plist installer, verifies with --dry-run, then installs and runs live.
Example/seed/fixture files must use placeholders not real credentials. Pre-commit grep check + enforcement hooks.
Guide and workflow for Code Centralization - Mandatory Investigation Protocol. Use when you need Code Centralization - Mandatory Investigation Protocol.
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.
Canonical definition of zero-touch-by-operator for PR autonomy measurement. Use when evaluating, reporting, or labeling PR autonomy status.
Checklist for dispatching AO workers — python venv, commit discipline, branch drift, and post-push CodeRabbit verification
Best practices and automation helpers for creating and maintaining high-quality pull requests
Run disk usage diagnostics, growth history logs, and automated cache/temp cleanup on development machines.
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.
Audit WorldArchitect.AI dice rolls for fairness and anomalies; use when analyzing campaign dice data.
Audit automation job runs, logs, PR processing metrics, and AI-authored remote commits.
Guide for WorldArchitect.AI GCP Cloud Run deployment and service management; use for deploys and service lookup.
Use when debugging unauthorized/fallback errors. Flags redacted placeholders (e.g. __OPENCLAW_REDACTED__) as invalid tokens; checks env overrides first.
Use when designing or reviewing backend adjusters, corrections, defaults, suppressions, clamps, guardrails, compatibility aliases, or fallback logic that may override or reshape…
Use whenever running an AO spawn. Honors exact --agent/--runtime/--project/--claim-pr; verifies session metadata; never silently substitutes a different worker.
Use thinclaw MCP server — thin inference-less bridge to OpenClaw Gateway for executing tools
Use for production-code PRs ($PROJECT_ROOT/**, gates, ZFC). Requires full GitHub URL to governing roadmap/design doc and a `br` bead ID in the body.
Canonical /repro workflow for copy+targeted bug repro, twin clones, evidence exports, same-symptom verdicts, and red/green provenance.
Override the model an `ao spawn` worker uses (e.g. force claude-sonnet-4-6 instead of the project default of wafer.ai/GLM-5.1) WITHOUT mutating ~/.hermes/agent-orchestrator.yaml.
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…
Use when writing PR descriptions. Enforces 6 sections in order: Background, Goals, Tenets, High-level description, Testing, Low-level details.
Use BEFORE `mv`/`rm -rf` on any directory. Verifies pwd does not match target; session cwd cannot recover once its directory is gone.
Run a Shadow Execution Gate for high-risk changes using isolated replay, objective evidence, and promotion criteria
skill to programmatically dismiss macOS keychain prompts and debug headless keyring access issues
Use when adding/changing a metric (zero-touch, smoothness, etc.). Wires canonical doc, README, AGENTS.md, CLAUDE.md, monitor script in the same pass.
When asked to verify whether a Claude Code feature works (especially slash commands, dialogs, pickers, status indicators), spawn a real interactive TUI session in cmux — never use…
Set up and use the Symphony launchd daemon in repositories that include orchestration/symphony_overlay/daemon.
Use when asked to analyze a video file and add visual description captions or text overlays burned into the output video