agentleFS
h3y6eh3y6e/agent-skills/skills/no-comments/SKILL.md

no-comments

Skill0 starsChanged 29 days agoMITView on GitHub

Removes bad comments in the given files or diff and fixes the root cause behind the workarounds they hide. Use when asked to remove, clean up, or audit code comments, or when a comment or lint suppression justifies a workaround the code should make obvious itself.

68 other projects use a version of this, 1 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use poteto-help, setup-pstack and 10 more.

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.
  • ianclearySkill

    poteto-help

    Guides users through pstack setup, /poteto-mode, and picking the skill, playbook, or principle for a task. Type /poteto-help with a question.

    Also in 13 projects that use this

  • bnemaSkill

    setup-pstack

    Configure which Pi models pstack uses per role. Detects available provider/model specs and writes pstack's user configuration. Use for /setup-pstack, "configure pstack models", or changing pstack model choices.

    Also in 22 projects that use this

  • ianclearySkill

    principle-explain-the-number

    Apply before you trust, report, or act on a number you measured: a speedup, a regression, a throughput, a latency, or an eval result. Find what limits it, and rule out that it measured something other than the work you think.

    Also in 25 projects that use this

  • eryzerzSkill

    make-bot-ui

    Use when building a custom UI (page, dashboard, buttons) that should wake a Grok Bot over a webhook, when the user must provide a webhook sender key, or when exposing that UI on Tailscale.

    Also in 16 projects that use this

  • TheOnlyFusionCubeSkill

    maintain-formal-verification-skill

    Bring a project's formal verification back in line with the code after the code changes: find the commits that touched verified code, update the model, harness, or properties to describe the code as it is now, rerun, and say whether each failure is drift in the verification or a bug in the code. Use for /maintain-formal-verification-skill, \"is the model still true to the code\", or after merges and refactors that touched verified code without rechecking it.

    Also in 19 projects that use this

  • TheOnlyFusionCubeSkill

    create-formal-verification-skill

    Generate a project-local skill that formally verifies the code where a bug costs the most and tests reach the least, in any language, with whichever verification tool fits. Use for /create-formal-verification-skill, \"model-check this race\", \"prove this invariant\", or when concurrency, retries, state machines, parsers, or unsafe code need more than tests.

    Also in 21 projects that use this

  • +1 more from TheOnlyFusionCube

The file

We split this skill into the rules it gives an agent

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

  • 1

    Common

    Most of the 66 edited versions we read keep these.

  • 1

    Distinctive

    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:

    When you cannot prove a comment earns an exception, delete it.

    line 15
  2. Common:

    Use the files or diff you were given.

    line 19

“Common” is measured: kept by at least 6 in 10 of the 66 edited versions of this file we could read. “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

No Comments

Comments that narrate the obvious, banner a section, or sermon over a workaround are debt. Delete them. When a comment is hiding something the code should say for itself, fix the code instead.

When you cannot prove a comment earns an exception, delete it. In doubt, it dies.

Scope

Use the files or diff you were given. Otherwise the current diff against the base branch (default main), including the working tree.

Classify every comment

Decide each in-scope comment: delete, keep, or MUST KILL. Only these exceptions keep one:

  • A legal or license header.
  • Behavior an external dependency, platform, vendor, or protocol forces and you cannot reshape.
  • A // prettier-ignore, or a lint or TS suppression whose rule is faulty, pedantic, or style-only.
  • A doc comment that defines a public API contract.
  • An issue or RFC link explaining a constraint the code cannot express.

eslint-disable, @ts-ignore, @ts-expect-error, and similar suppressions default to dead. Look up the rule. If it catches real bugs or protects correctness or safety, delete the suppression and MUST KILL the exact symbol that trips it.

IMPORTANT, do not remove, too risky, fine for now, and any long justification are claims, not proof. Read the nearby code. If the claim is not obvious there, chase the named symbol or call to settle it. Only a proven external gotcha on a live path survives; a surprise in our own code dies as a MUST KILL. A long justification with no exception is a confession — delete it.

A MUST KILL marks code you will not touch in this pass: name the exact symbol and the reshape — rename, extract, add a type, or restructure — that makes the behavior obvious without prose.

Fix root causes

For each MUST KILL and each workaround a comment was papering over:

  • Trivial: delete the dead path, drop the parameter, use the real API.
  • Needs a new shape: sketch the smallest reshape, then implement it in scope.
  • Out of scope: land the smallest in-scope fix and report the rest open.

Fix the root cause; leave no symptom guard behind, and do not widen the scope to fix instances outside it.

Constraint comments

do not remove, do not change wording, or talk to X before changing about something you cannot change may stay. Offer the cheapest in-scope encoding — a type, a runtime check, a test, or a CI lint — that makes the constraint enforceable. With approval, encode it and delete the comment. Without approval, delete it and report the constraint open with the out-of-scope work it needs.

Report

Files touched, comments deleted, MUST KILL flags (one line each), keeps with their exception, fixes made, encodings offered or made, and open work.

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.