agentleFS
Sign inStart free
LinardsLiepenieksLinardsLiepenieks/honecode/skills/grade-file/SKILL.md

grade-file

Skill0 starsChanged 2 months agoMITView on GitHub

Grade one file's responsibility hygiene against a stated purpose, in code-smell language, ending in a 1–10 score. Read-only: reports, never edits. Use when the user passes a file plus what it's for and asks "grade this", "audit this file", or "is this doing too much".

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read-only. The user gives a file (default: the open one) and its purpose in one line.

    line 8
  2. Distinctive:

    Read the file. Restate its purpose in one sentence.

    line 10

≈ “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

Grade a file's responsibility hygiene

Read-only. The user gives a file (default: the open one) and its purpose in one line. That purpose is the SRP ruler: anything that changes for a different reason is a finding. Do not edit; fixing is simplify-code's job.

  1. Read the file. Restate its purpose in one sentence; hold it as the ruler.
  2. Survey the neighbors: ls the folder, grep for the same idea. A finding lands harder as "extract to this existing seam" or "duplicates that file" than in the abstract.
  3. Name each deviation with a Fowler smell + file:line: Divergent Change (many reasons to change, the main hunt), Bloaters (Large Module, Long Method, Data Clumps), Dispensables (Dead Code, dead/stale comments, Duplication, Speculative Generality), Couplers (Feature Envy, Inappropriate Intimacy). Frame by cohesion (parts belong together?) + coupling (entangled with neighbors?).
  4. Separate dead (remove) from misplaced (relocate). Accurate-but-wordy comments are not rot; say so if nothing is dead.

Output (prose): **Score: N/10** + the paradigm judged against · one line on what it gets right · findings grouped by smell with refs and the seam to extract to · an explicit dead-code/dead-docs line even if "none" · close with what would raise the score and to what.

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