Drop into a skill folder
Personal: ~/.claude/skills/ai-structured-extraction-check/SKILL.md
Project: .claude/skills/ai-structured-extraction-check/SKILL.md
Brali Agent Skill · practical · usable
Extract a Table with AI, Then Sample-Check the Rows
For repeated unstructured text you are allowed to process, ask AI to extract a fixed schema, include the source span for each row, and flag uncertainty. Then sample-check rows and fully verify fields that drive money, access, compliance, or other high-cost actions.
Portable instruction
What the agent should do
Define the columns and allowed values before extraction. Ask the model to return null rather than guess, preserve a source snippet or locator for each row, and flag ambiguous cases. Check a random sample plus all high-impact rows against the original text before using the result downstream.
Check-in
Do I know the observed extraction error rate well enough for the consequence of the next step?
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-structured-extraction-check/SKILL.mdPlace in a discovered skill root
Workspace: <workspace>/skills/ai-structured-extraction-check/SKILL.md
Global: ~/.openclaw/skills/ai-structured-extraction-check/SKILL.md
Brali verification
Coverage and trust state are checked together.
Canonical ID: brali:ai-structured-extraction-check
Evidence state: practical
Skill mode: usable
Recommendation eligible: yes
SHA-256: 7dc6d60188589ba1df69505236e9f5c42821c444baca7a589a5efc75ad7b8026
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.