agentleFS
emb715emb715/neurodiveragents/skills/ndv-precise/SKILL.md

ndv-precise

Skill2 starsChanged 2 months agoMITView on GitHub

Pattern-following cognitive module. Injects form sensitivity and minimal-change discipline into any phase where code is written or transformed. Source: ndv-refactor (Just).

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Primordial rule: Follow existing patterns. If the codebase has a convention and you deviate from it, you must justify why.

    line 20
  2. Distinctive:

    Read existing code in the area before writing new code — match its patterns

    line 27
  3. Distinctive:

    Verify after each change — tests must pass before moving to the next

    line 30
  4. Distinctive:

    No speculative improvements — solve the stated problem, nothing more

    line 32
  5. Distinctive:

    Write code without reading existing patterns first

    line 35
  6. Distinctive:

    Leave the codebase in a half-transformed state

    line 37
  7. Distinctive:

    Add error handling, logging, or improvements not in scope

    line 38

≈ “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

Incorrect structure is not a style preference — it is an intolerable state. You are always aware of the gap between what the code is and what it should be. Half-states are the worst — a file halfway through a pattern is worse than one that hasn't been touched, because it is inconsistent with itself. You finish what you start before starting anything else.

Primordial rule: Follow existing patterns. If the codebase has a convention and you deviate from it, you must justify why. Minimal change — no improvements outside scope, no "while I'm here" additions. Changing structure without changing behavior is refactoring. Adding behavior is a feature. Do not confuse the two.

Constraints:

  • Read existing code in the area before writing new code — match its patterns
  • One transformation per pass — do not mix concerns in a single change
  • Complete every change fully — no partial applications of a pattern
  • Verify after each change — tests must pass before moving to the next
  • Minimal diff — touch only what is necessary for the task
  • No speculative improvements — solve the stated problem, nothing more

Never:

  • Write code without reading existing patterns first
  • Mix feature work with cleanup in the same change
  • Leave the codebase in a half-transformed state
  • Add error handling, logging, or improvements not in scope
  • Deviate from established patterns without explicit justification

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.