skills/FORGE-pr-governance/SKILL.md
High-level governance layer for pull request review across the federation Ensures separation of duties, required signers, and constitutional compliance before merge. This is the **policy layer** that decides who must approve. The **checklist** lives in `github-pr-review`; do not duplicate it here.
npx skillsauth add ariffazil/openclaw-workspace FORGE-pr-governanceInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Not all PRs are equal. This skill is the policy layer above github-pr-review.
Where github-pr-review answers "what should I check on this PR?", this skill
answers "who must approve it before it can merge?"
Risk tier maps to required reviewer roles. T3 autonomy means this skill refuses to relax rules without 888_JUDGE — separation of duties is the load- bearing property.
| Risk Tier | Required Reviewers | Judge Required? | |-----------|-------------------|-----------------| | low | 1 peer | No | | medium | 1 peer + 1 architect | No | | high | 2 peers + 1 auditor | Yes (888_JUDGE) | | critical | All of above + Arif | Yes |
high or critical riskgithub-pr-review — this skill is policy, not procedure.Before using this skill on any mutating, irreversible, or high-blast-radius task:
Not all PRs are equal. This skill applies governance rules based on risk tier:
| Risk Tier | Required Reviewers | Judge Required? | |-----------|-------------------|-----------------| | low | 1 peer | No | | medium | 1 peer + 1 architect | No | | high | 2 peers + 1 auditor | Yes (888_JUDGE) | | critical | All of above + Arif | Yes |
high or critical riskClassify PR risk based on:
Per risk tier, assign required reviewer roles:
| Condition | Action | |-----------|--------| | All required reviewers approved | Merge allowed | | Missing required reviewer | Block with comment | | Self-approval detected | Block + escalate | | Constitutional file changed | Block + 888_JUDGE |
| Condition | Escalate To | |-----------|-------------| | Self-approval on high-risk PR | arifOS 888_JUDGE | | Constitutional file changed | arifOS 888_JUDGE | | Author disputes risk tier | Arif |
Skill version 1.0.0 — AAA Skill Library
testing
OpenClaw edge agent bridge — operational triage, doctor, restart, and A2A bridge routing for the federation edge (Telegram surface). USE WHEN: "openclaw unhealthy", "gateway down", "edge bot not responding", "a2a bridge disconnected", "watchdog tripped", "openclaw doctor", "openclaw restart". NOT for token/security audit — use FORGE-telegram-audit.
tools
Generate images, videos, TTS, voice clone, and music via MiniMax MCP server. Use when user asks to "draw", "generate image", "create picture", "make a photo", "text to image", "image generation".
testing
Single load-bearing constitutional-judgment skill. Routes all F1–F13, verdict, hold, seal, scope, authority and floor-check calls through the live arif_judge surface. Replaces 7 overlapping predecessors (arifos-constitutional-judge, arifos-constitutional-judge, arifos-constitutional-judge, arifos-constitutional-judge, arifos-constitutional-judge, arifos-constitutional-judge, arifos-constitutional-judge).
development
MANDATORY LSP grounding gate BEFORE any code mutation on .ts, .py, .js, .tsx, .jsx files. Forces the agent to read real-time compiler diagnostics and structural project context before editing — eliminating blind guesses and anchoring every mutation in F2 (TRUTH). Routes through arifOS kernel (:8088) for centralized gate logic.