Drop into a skill folder
Personal: ~/.claude/skills/ai-rubric-critique/SKILL.md
Project: .claude/skills/ai-rubric-critique/SKILL.md
Brali Agent Skill · practical · usable
Give AI a Rubric and Ask for Specific Critique
For a draft you own, give AI the purpose and a short rubric, ask it to point to specific places that miss the criteria, then decide which suggestions actually improve the work. Use critique as input, not as an automatic rewrite command.
Portable instruction
What the agent should do
Write three to six criteria that describe a good result. Give the model the draft and rubric, ask for evidence from the draft for each criticism, and request no rewrite on the first pass. Triage the feedback, then make the changes you agree with.
Check-in
Did the critique point to observable gaps in the draft, or mostly produce generic advice I could paste onto any text?
Install
One portable file, host-specific location.
Inspect SKILL.md first. The evidence state and skill mode are part of the contract.
Install for normal use.
Install directly from this URL
hermes skills install https://brali-lifeos.github.io/skill-packs/ai-rubric-critique/SKILL.mdPlace in a discovered skill root
Workspace: <workspace>/skills/ai-rubric-critique/SKILL.md
Global: ~/.openclaw/skills/ai-rubric-critique/SKILL.md
Brali verification
Coverage and trust state are checked together.
Canonical ID: brali:ai-rubric-critique
Evidence state: practical
Skill mode: usable
Recommendation eligible: yes
SHA-256: 4d391fe500948b2858795203d889ba1885506d3faae0165aaf26ef90c29483b3
Brali CI verified. This means identity, state, mode, provenance and file integrity matched the generated corpus. It is not third-party vendor endorsement.
Why every hack gets a skill
Brali keeps a one-to-one machine surface: one hack record, one stable skill identity. Trust state determines what the skill is allowed to do.
License
Original Brali knowledge is available for non-commercial reuse under CC BY-NC-SA 4.0. Keep attribution, canonical record link, evidence state and skill mode.