agentleFS
Sign inStart free
igorkravcenkoigorkravcenko/snowshoe/.cursor/skills/brain-protocol/SKILL.md

brain-protocol

Skill1 starsChanged 35 days agoApache-2.0View on GitHub

Load and maintain Snowshoe's spec-driven brain. Use at session start, before any behavior or product-claim change, and when CURRENT/ADRs may be stale.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. FPVE-Webdev/claude-skills★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository9 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 4 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If you change product behavior, positioning, non-goals, monetization, or any claim CURRENT makes:

    line 27
  2. Very specific:

    Add or update an ADR under docs/brain/DECISIONS/ (use docs/brain/templates/DECISION_TEMPLATE.md).

    line 29
  3. Very specific:

    Update CURRENT.md in the same change so it stays the compiled truth.

    line 30
  4. Distinctive:

    Do not implement application code until CURRENT says we are past scaffold-only.

    line 34
  5. Distinctive:

    Keep CURRENT short. Detail lives in ADRs.

    line 38
  6. Distinctive:

    Do not invent metrics, users, or competitors.

    line 39

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Brain protocol

Read order (required)

  1. docs/brain/START_HERE.md
  2. docs/brain/CURRENT.md — compiled truth
  3. docs/brain/ROADMAP.md — sequence of intent, not shipped fact
  4. docs/brain/EXPERIMENTS.md — registry of bets, not truth

Then open only the ADRs, notes, or evidence the task needs.

Trust

  • Truth = CURRENT.md + ADRs with status: accepted (active is a lint alias only; DECISIONS table uses accepted).
  • Experiments stay in the registry until promoted.
  • docs/evidence/** supports a claim; it does not become true by existing.
  • docs/brain/notes/** is working memory.
  • docs/archive/** is historical.

Writes (required on behavior / claim change)

If you change product behavior, positioning, non-goals, monetization, or any claim CURRENT makes:

  1. Add or update an ADR under docs/brain/DECISIONS/ (use docs/brain/templates/DECISION_TEMPLATE.md).
  2. Update CURRENT.md in the same change so it stays the compiled truth.
  3. Set frontmatter status: correctly (accepted, proposed, superseded, …).
  4. Move superseded canon to docs/archive/ rather than deleting history silently.

Do not implement application code until CURRENT says we are past scaffold-only.

Hygiene

  • Keep CURRENT short. Detail lives in ADRs.
  • Do not invent metrics, users, or competitors.
  • English in brain files.

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