no-comments
Skill0 starsChanged 53 days agoMITView on GitHub
Delete comments from changed code and fix what needed them.
68 other projects use a version of this, 1 of them edited.
Adopted by
Most recently taken up by
- remotion-dev/remotiontheir own version, first seen Nov 8, 2026
- paramcodes/skillstheir own version, first seen Nov 8, 2026
- endqwerty/endstacktheir own version, first seen Nov 8, 2026
- tristanphvn/keeltheir own version, first seen Nov 8, 2026
- therealmarzouq/skillstheir own version, first seen Nov 8, 2026
- hidenobunagai/astacktheir own version, first seen Nov 8, 2026
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.
ianclearySkillpoteto-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
bnemaSkillsetup-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
ianclearySkillprinciple-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
eryzerzSkillmake-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
TheOnlyFusionCubeSkillmaintain-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
TheOnlyFusionCubeSkillcreate-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
Other versions68 projects use a version of this.
Word for word · 0
None found.
Edited · 1
- h3y6e/agent-skills★ 011% same
Wrote their own version · 67
- remotion-dev/remotion★ 72ksame name
- backnotprop/pstack★ 3.8ksame name
- moeru-ai/xsai★ 667same name
- jtaroreh/agystack★ 128same name
- uzairansaruzi/p3-stack★ 126same name
- Dimon94/dverity★ 107same name
- Dimon94/skills★ 107same name
- dsebban/skills★ 71same name
- overextended/skills★ 22same name
- TheOnlyFusionCube/potetos-for-everyone★ 21same name
57 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository50 other files it gives its agents.
- AGENTS.mdAGENTS.md
- instructions/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- instructions/CLAUDE.mdCLAUDE.md
- author-skillSkill
- architectSkill
- arenaSkill
- astack-helpSkill
- astack-updateSkill
- brag-slimSkill
- bug-fixSkill
- claude-background-jobsSkill
- claude-routerSkill
- codex-background-jobsSkill
- create-verification-skillSkill
- diagnosing-bugsSkill
- domain-modelingSkill
- full-sendSkill
- grillingSkill
- handoffSkill
- harden-prSkill
- hillclimbSkill
- howSkill
- implementSkill
- improve-codebase-architectureSkill
- investigationSkill
- multi-phase-planSkill
- open-prSkill
- orchestrateSkill
- perf-issueSkill
- principlesSkill
- prototypeSkill
- refactoringSkill
- reflectSkill
- review-prSkill
- run-jobSkill
- ship-prSkill
- show-me-your-workSkill
- t3-previewSkill
- tddSkill
- teachSkill
- technical-writingSkill
- to-specSkill
- typescript-best-practicesSkill
- unslopSkill
- wayfinderSkill
- whySkill
- wizardSkill
- worktree-cleanupSkill
- writing-for-agentsSkill
The file
We split this skill into the rules it gives an agent
4 rules. 1 is common, 3 are distinctive, and 0 are very specific to this project.
1
Common
Most of the 66 edited versions we read keep these.
3
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
- Common: line 13
Use the files or diff the caller names.
- Distinctive: line 17
Only these comments survive.
- Distinctive: line 25
When unsure whether a keep-list entry applies, delete the comment.
- Distinctive: line 29
Delete the whole comment rather than shortening it.
“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.
Files
Delete the comments
Delete every comment in scope that is not on the keep list. Flag the code that needed a comment to be understood, then fix what the flags name. A flag is one line in the report naming a symbol that needed a comment. Every flag names code inside the scope and tells the truth.
Scope
Use the files or diff the caller names. With no caller scope, use the current diff against the base branch, main by default, including the working tree.
Keep list
Only these comments survive. Each of the first four survives only with proof that it concerns something outside this repository or a contract this repository publishes. The fifth needs the rule lookup it describes:
- A legal or license header.
- Behaviour forced by an external dependency, platform, vendor, or protocol we cannot change. Behaviour a reader would not expect from the names and types in our own code does not qualify. Delete that comment and flag the symbol.
- A doc comment that defines a public API contract.
- An issue or RFC link that explains a constraint the code cannot express.
// prettier-ignore, and a lint or type suppression whose rule is faulty, pedantic, or style-only. Look up the rule for everyeslint-disable,@ts-ignore,@ts-expect-error, and similar suppression in scope, including the ones you did not write. If the rule catches real bugs or protects correctness or safety, delete the suppression and flag the symbol.
When unsure whether a keep-list entry applies, delete the comment.
Delete these
Delete the whole comment rather than shortening it.
- Narration, banners, commented-out code, and workaround justifications. In a test or verify script the assertion message documents the step.
- A claim comment, such as
IMPORTANT,too risky, orfine for now, and any long justification. A claim is not proof. Read the nearby code, rungit log -L <start>,<end>:<file>on the lines, and read the PR that introduced the comment. The history decides whether the claim is still true on a live path. A claim that is still true and matches a keep-list entry stays. Anything else goes. - A constraint comment, such as
do not remove,do not change wording, ortalk to X before changing. First apply the keep-list test above. When the constraint concerns something we can change, offer the cheapest in-scope type, runtime check, test, or lint, local or CI, that encodes it, and wait for the user's approval. Unattended, treat it as not approved. If approved, encode the constraint, then delete the comment. Otherwise delete the comment, report the constraint open, and sketch the encoding.
Fix what the flags name
Delete the dead path, drop the unused parameter, or call the real API. When two or more flags need the same fix, sketch the new structure once, over the flagged code and its surroundings, before writing code. Make the smallest root-cause fix in scope and remove every named workaround. fix-root-causes.md and redesign-from-first-principles.md guide the intent. Both stay inside the scope. Neither allows fixes in other files. An out-of-scope root cause gets the smallest in-scope fix and a note.
Report
Report these:
- the files touched
- the number of comments deleted
- each comment kept, with its keep-list entry
- each flag, in one line
- each fix made, and each flag left open with its note
- the sketch, if there was one
- the encodings offered and made
- the constraints left open
- other open work
Done when every comment in scope is deleted or matched to a keep-list entry, every flag is fixed or reported open, and the report carries each item above.
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
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.

