skills/AGI-skill-unification/SKILL.md
Multi-harness skill catalog unity — AAA catalog, Grok/Claude/Codex views, alias table (V3 short→disk), mesh-sync, BOOT gate, Hermes bridge. Load when auditing skill mesh, resolving dual names, rebinding harness skills, or before claiming skill inventory complete.
npx skillsauth add ariffazil/openclaw-workspace AGI-skill-unificationInstall 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.
AAA is the catalog. Harnesses are views.
Doctrine bodies may live under /root/AAA/skills or /root/.agents/skills (doctrine_core).
Do not invent a second Grok-only catalog.
AAA/skills/BOOTSTRAP_MANIFEST.json — 9 universals (substrate + knowledge) through READY, then domain skills.
| Artifact | Path |
|----------|------|
| Alias table (133 rows: 104 active + 29 tombstone) | ${AAA_HOME:-/root/AAA}/skills/SKILL_ALIAS_TABLE.json |
| Mesh sync | ${AAA_HOME:-/root/AAA}/skills/scripts/skill-mesh-sync.sh |
| V3 registry (64 logical) | ${AAA_HOME:-/root/AAA}/skills/FEDERATED_SKILLS_REGISTRY_V3.yaml |
| Meta atlas | AUDIT-skill-atlas |
| Historical receipt | ${AAA_HOME:-/root/AAA}/skills/docs/SKILL-UNIFICATION-COMPLETE-2026-07-12.md |
| Current receipt | ${FORGE_WORK:-/root/forge_work}/2026-07-15/AAA-SKILL-TOOL-RECONCILIATION.json |
| Hermes bridge | ${AFORGE_HOME:-/root/A-FORGE}/forge_work/2026-07-12/HERMES-V3-DOMAIN-BRIDGE.md |
python3 -c "import json;d=json.load(open('${AAA_HOME:-/root/AAA}/skills/SKILL_ALIAS_TABLE.json'));
print([a for a in d['aliases'] if a['v3_name']=='meta-atlas'][0])"
Prefer primary_path / primary_resolved. Never invent paths from short names alone.
# dry-run
bash ${AAA_HOME:-/root/AAA}/skills/scripts/skill-mesh-sync.sh
# apply missing links (Grok natives preserved)
bash ${AAA_HOME:-/root/AAA}/skills/scripts/skill-mesh-sync.sh --apply
# CI / pre-seal
bash ${AAA_HOME:-/root/AAA}/skills/scripts/skill-mesh-sync.sh --check
Harnesses synced: ~/.grok/skills, ~/.claude/skills, ~/.codex/skills.
arif-governed-autonomous-execution · grok-zen-aaa-substrate · grok-federation-skill-upgrader · orthogonal-skill-update · create-skill · check-work · help · imagine
Pruned: docx pptx xlsx code-review → ~/.grok/skills/.deprecated/
skill-mesh-sync.sh --check exits 0.AUDIT-skill-atlas §0 points to a dated live receipt.Subagents are optional, scope-bounded evidence collectors. They do not inherit authority, cannot validate one another recursively, and never replace a live source-of-truth probe.
# Split only independent questions with explicit evidence contracts:
task(description="Audit registry semantics", subagent_type="auditor", prompt="Return file paths, counts, and contradictions only.")
task(description="Check runtime health", subagent_type="ops", prompt="Return live endpoints, status, and timestamp only.")
ROOT AGENT → live source probes + optional bounded independent audits
→ compare evidence and contradictions
→ arif_judge
→ human/external witness if required
Load AUDIT-skill-atlas for routing and gap detection. This skill is the ops contract for unity.
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.