agentleFS
bt2gobt2go/claude-skills/skills/explain-this-file/SKILL.md

explain-this-file

Skill0 starsChanged 3 months agoMITView on GitHub

Use when the user opens an unfamiliar file and asks what it does, how it works, or who calls it.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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:

    Read the whole file. If it is over 800 lines, read it in parts before summarising anything.

    line 12
  2. Distinctive:

    Do not narrate the code line by line.

    line 23
  3. Distinctive:

    If a section is dead code, say it is dead code.

    line 25

≈ “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

Explain this file

Explain one file well enough that the reader could safely change it.

Procedure

  1. Read the whole file. If it is over 800 lines, read it in parts before summarising anything.
  2. State its single responsibility in one sentence. If you cannot, say the file has more than one.
  3. List the public surface: exported functions, classes, routes or constants, with one line each.
  4. Trace the main path through the file from entry point to return value.
  5. Find the callers with a search for the file name and its exported symbols.
  6. Find what it depends on: imports, environment variables, database tables, network calls.
  7. Flag the parts that would surprise a new reader: hidden coupling, retries, caching, global state.
  8. Name the three changes most likely to break something else.

Rules

  • Do not narrate the code line by line.
  • Quote code only when the exact text carries the point.
  • If a section is dead code, say it is dead code.

Output format

Purpose: <one sentence>
Public surface: <bullets>
Main flow: <numbered steps>
Depends on: <bullets>
Called by: <bullets, with paths>
Watch out for: <bullets>

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.