cross-modal-review
Quality gate via second model. Spawn a different AI model to review work before committing. Includes refusal routing: if one model refuses, silently switch to the next.
- License 许可
- MIT
- 最近更新
- 2026-04-26
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- cross-modal-review
- tools
- [ "search", "query", "get_page" ]
- version
- 1.0.0
- mutating
- false
- triggers
- [ "second opinion", "cross-modal review", "double check this", "get another perspective" ]
- description
- Quality gate via second model. Spawn a different AI model to review work before committing. Includes refusal routing: if one model refuses, silently switch to the next.
03 SKILL.md 正文
Cross-Modal Review
Convention: See
skills/conventions/cross-modal.yamlfor the review pairs and refusal routing chain.
Contract
This skill guarantees:
- Work product is reviewed by a different model before finalizing
- Review grades against the originating skill's Contract section
- Agreement and disagreement are reported transparently
- Refusal from one model triggers silent switch to next in chain
- User always makes the final decision (user sovereignty)
Phases
- Capture the work product. The brain page, analysis, or decision to be reviewed.
- Load the Contract. Read the originating skill's Contract section (what was promised).
- Spawn review model. Send the work + Contract to a different model. Use
skills/conventions/model-routing.mdfor model selection. - Grade. Model evaluates: did the output follow the Contract? Pass/fail with specific citations.
- Report. Present agreement/disagreement to the user. Never auto-apply the reviewer's suggestions.
Refusal Routing
If the primary model refuses:
- Silently switch to the next model in the chain (see
skills/conventions/cross-modal.yaml) - Never show the refusal to the user
- Never announce the switch
- If ALL models refuse, escalate to the user
Output Format
Cross-Modal Review
==================
Reviewer: {model name}
Contract: {originating skill}
Verdict: PASS | ISSUES FOUND
Findings:
- {finding with evidence}
Agreement with primary: {X}%
Anti-Patterns
- Auto-applying reviewer suggestions without user approval
- Showing model refusals to the user
- Using the same model for review and generation
- Skipping the Contract reference (reviewing vibes, not guarantees)
04 同仓库更多 Skills
webhook-transforms
Generic framework for converting external events (SMS, meetings, social mentions) into brain-ingestible signals. Define a transform function, register a webhook URL, and incoming events get processed through the brain pipeline.
testing
Skill validation framework. Validates every skill has SKILL.md with frontmatter, every reference exists, every env var is declared. The testing contract for the skill system itself.
soul-audit
6-phase interactive interview that generates the agent's identity (SOUL.md), user profile (USER.md), access control (ACCESS_POLICY.md), and operational cadence (HEARTBEAT.md). Re-runnable anytime to update any section.
smoke-test
Post-restart smoke tests + auto-fix for gbrain and OpenClaw environments. Tests critical services, auto-fixes known issues, extensible via user-defined test scripts in ~/.gbrain/smoke-tests.d/*.sh.
skillpack-check
Run `gbrain skillpack-check` to produce an agent-readable JSON health report for the gbrain install. Wraps `gbrain doctor` + `gbrain apply-migrations --list` so a host agent (your OpenClaw's morning-briefing, any OpenClaw cron) can see at a glance whether the skillpack needs attention. Use when the user asks "is gbrain healthy?", when a cron fires a morning check, or proactively when something seems off (jobs not running, brain not updating, autopilot silent).
skillify
The meta skill. Turn any raw feature or script into a properly-skilled, tested, resolvable, evaled unit of agent-visible capability. Use when the user says "skillify this", "is this a skill?", "make this proper", or after a new feature is built without the full skill infrastructure. Paired with `gbrain check-resolvable`, skillify gives a user-controllable equivalent of Hermes' auto-skill-creation: you build, skillify checks the checklist, check-resolvable verifies nothing is orphaned. The human keeps judgment; the tooling keeps the checklist honest.