agentleFS
Sign inStart free
luisgui1757luisgui1757/sentinel/skills/no-comments/SKILL.md

no-comments

Skill0 starsChanged 9 days agoMITView on GitHub

Removes code comments that break the comment rule, keeps the few comments that code cannot replace, and makes the code clear where a comment explained a surprise. Use when the user asks to remove or clean up comments, or to check a diff or a repository for comments.

68 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use poteto-help, setup-pstack and 9 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

The file

We split this skill into the rules it gives an agent

8 rules. 0 are common, 8 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 66 edited versions we read keep these.

  • 8

    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:

    Use the files or the diff that the user names.

    line 13
  2. Distinctive:

    When you are not sure that a comment is in this list, remove it.

    line 31
  3. Distinctive:

    Read the code that it points at before you decide.

    line 43
  4. Distinctive:

    If the claim is false today, remove the comment.

    line 45
  5. Distinctive:

    If the claim is about an external limit, keep it with a link.

    line 46
  6. Distinctive:

    If the claim is true and about our code, keep the comment.

    line 47
  7. Distinctive:

    Remove the comments. Change no code in this step.

    line 55
  8. Distinctive:

    Run the tests and the linters of the repository.

    line 59

“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

Code explains itself through names, types, structure and tests. A comment stays only when the code cannot carry its information.

Scope

Use the files or the diff that the user names. If the user names nothing, use the diff against the default branch, with the working tree. Use the full repository only when the user asks for it.

Keep only these

  • License and copyright headers.
  • Lines that a tool reads, such as a shebang, prettier-ignore, an encoding line or a build tag.
  • A lint or type suppression whose rule is wrong for that line, or is only about style.
  • Doc comments that define the contract of a public API, in the doc format of the language. Examples are JSDoc, a Python docstring and a Go comment right above an exported name. In JavaScript, a plain // line above a function is not a doc comment.
  • A limit that an external system forces, such as a vendor, a platform, a protocol or a dependency, with a link to the issue, the spec or the docs.

When you are not sure that a comment is in this list, remove it.

Remove

  • Comments that say what the code does.
  • Banners and step narration, such as // Step 1: load the data.
  • Code in comments.
  • A comment that explains a surprise in our own code. Remove it, and mark the symbol for a reshape in step 4.
  • A suppression whose rule finds real faults. Fix the code in step 4.

A comment such as IMPORTANT, do not remove or ask X first makes a claim. Read the code that it points at before you decide.

  • If the claim is false today, remove the comment.
  • If the claim is about an external limit, keep it with a link.
  • If the claim is true and about our code, keep the comment. Propose a test, a type or a lint rule that enforces it. Remove the comment only when that test, type or lint rule is in the code and enforces the claim.

Steps

  1. List each comment in scope, with its file and line.
  2. Classify each comment: keep, remove, or remove and reshape.
  3. Remove the comments. Change no code in this step.
  4. For each reshape, make the smallest change in scope that makes the code clear: a rename, an extraction or a type. If the change is out of scope, report it.
  5. Run the tests and the linters of the repository. Behavior must not change.

Report

  • The number of comments that you removed, for each file.
  • Each comment that you kept, with its reason from the list above.
  • Each reshape that you did, and each one that you did not do.
  • Each claim that you removed as false, with the code that proves it false.
  • Each claim that needs a test, a type or a lint rule.

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