agentleFS
sophonfinance-wqsophonfinance-wq/finance-automation-portfolio/.claude/skills/brain/SKILL.md

brain

Skill16 starsChanged 44 days agoMITView on GitHub

Run the Knowledge Brain (citation-governed retrieval over meeting transcripts: ask/cite/prep/remediate) or its verbatim-or-refuse integrity loop. Use for cited answers, review-to-remediation, or KB drift repair.

25 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use research.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • NVIDIASkill

    research

    Before designing a feature, research how comparable libraries solve the problem, check best practices, known pitfalls, and upstream changes. Use when starting a new feature, investigating an unfamiliar area, or the user asks to research something.

    Also in 4 projects that use this

The file

Files
SKILL.md

Knowledge Brain Engine

Package brain_engine in knowledge-brain-engine/. Stdlib TF-IDF, no network. Exit codes: 0 sourced, 2 usage error, 3 refusal.

Commands (run from knowledge-brain-engine/)

python -m brain_engine ask "how do we handle FX on ACB?"
python -m brain_engine --cite "distributions draw exempt surplus first"
python -m brain_engine remediate "Surplus Review"     # reviewer corrections -> apply-ready prompt
python -m brain_engine.loop --demo                    # INTEGRITY LOOP: re-derive tampered entries verbatim
python -m pytest -q                                   # 7,011 tests

Loop verdicts (brain_engine/loop.py)

CLEAN (0) / REMEDIATED (0) / ESCALATED (3 — the engine's refusal code). The signature rule: tampered text/speakers are re-derived BYTE-FOR-BYTE from Corpus.utterance_text; orphaned citations (no utterance behind them) are quarantined, never repaired — no source, no guess.

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.