agentleFS
Sign inStart free
natalinionatalinio/project-second-brain/.claude/skills/review-note/SKILL.md

review-note

Skill0 starsChanged 25 days agoMITView on GitHub

Check the fidelity of one extracted note (structure, tables, images — not its content), write its abstract and mark it checked. Use on notes in knowledge/extracted/ with status extracted.

The file

Create a free account to mount
Files
SKILL.md

Note: $ARGUMENTS (the text typed after the command).

Sample, don't read the whole note:

  1. Structure — uv run python tools/ingest/query.py "SELECT heading, line_start, line_end FROM kb.sections WHERE path = '<path>' ORDER BY line_start". Headings plausible and in order? A single section spanning > 1,000 lines = lost hierarchy (note it).
  2. Tables — read 2 table-bearing sections (by line range): columns aligned, nothing flattened into prose.
  3. Images — count NOT YET DESCRIBED / NOT EXTRACTED placeholders. List the count; do not describe them now.
  4. Frontmatter — domain (not TODO; one of the domains in project.yaml when listed); evidence right for the type; abstract of 3–5 lines (what it is, what it is authoritative for, main sections with line ranges) when the note is above the abstract threshold (40 KB by default).

Then edit the frontmatter only (the body is immutable, hook-enforced): status: checked, status_note: "checked <today>: <issues or ok>", domain, abstract. If the extraction is defective (lost tables, missing pages), keep status: extracted and propose an OP instead. Reply in ≤ 5 lines.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free