no-comments
Skill1 starsChanged 57 days agoMITView on GitHub
Delete the comments in scope, fix the code they were covering for, and offer to encode any constraint they claimed.
68 other projects use a version of this, 50 of them edited.
Adopted by
Most recently taken up by
- remotion-dev/remotiontheir own version, first seen Nov 8, 2026
- paramcodes/skillsedited, first seen Nov 8, 2026
- endqwerty/endstackedited, first seen Nov 8, 2026
- tristanphvn/keeledited, first seen Nov 8, 2026
- therealmarzouq/skillstheir own version, first seen Nov 8, 2026
- hidenobunagai/astackedited, 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 · 50
- backnotprop/pstack★ 3.8k29% same
- moeru-ai/xsai★ 66729% same
- jtaroreh/agystack★ 12838% same
- uzairansaruzi/p3-stack★ 12634% same
- dsebban/skills★ 7136% same
- overextended/skills★ 2227% same
- creedants/pstack-t3★ 1820% same
- painhardcore/pstack★ 1831% same
- Scino/fstack★ 1833% same
- mariusflorescu/pstack-t3★ 1328% same
40 more not listed
Wrote their own version · 18
- remotion-dev/remotion★ 72ksame name
- Dimon94/dverity★ 107same name
- Dimon94/skills★ 107same name
- TheOnlyFusionCube/potetos-for-everyone★ 21same name
- cutfac/cutfac★ 14same name
- educlopez/mallard★ 4same name
- requie/endostack★ 4same name
- stainless-code/lossless★ 4same name
- fullerzz/agent-skills★ 2same name
- niksavis/basicly★ 2same name
8 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 repository27 other files it gives its agents.
- blast-radiusSkill
- codebase-designSkill
- code-reviewSkill
- create-verification-skillSkill
- designingSkill
- domain-modelingSkill
- handoffSkill
- hf-cliSkill
- howSkill
- implementSkill
- improve-codebase-architectureSkill
- interrogateSkill
- laziness-protocolSkill
- maintain-verification-skillSkill
- navigatorSkill
- prototypeSkill
- recallSkill
- redesign-from-first-principlesSkill
- researchSkill
- review-unpushedSkill
- scopeSkill
- show-me-your-workSkill
- technical-writingSkill
- tracerSkill
- unslopSkill
- whiteboardSkill
- writing-for-agentsSkill
The file
We split this skill into the rules it gives an agent
4 rules. 1 is common, 2 are distinctive, and 1 is very specific to this project.
1
Common
Most of the 66 edited versions we read keep these.
2
Distinctive
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
- Common: line 15
Use the caller's files or diff.
- Very specific: line 35
Before accepting a thin IMPORTANT or do not remove kill or keep, investigate the named symbol yourself: git log and git blame on the lines, …
- Distinctive: line 45
Remove every named workaround.
- Distinctive: line 53
If approved, encode the constraint and then delete the comment.
“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
No comments
Spawn Comment Sicko. Act on accepted findings.
Defer to Comment Sicko's fresh perspective.
Scope
Use the caller's files or diff. Otherwise use the current diff against the base branch, default main, including the working tree.
Steps
1. Spawn the sub-agent
Spawn one sub-agent with the brief in COMMENT-SICKO.md, pasted whole. Pass the scope. Do not restate its rules and do not add your own.
2. Audit the report and diff
Reject any of these:
- edits to application code
- deletions outside the scope
- deletions of exception-protected comments
- misstated
MUST KILLreasons - flags that treat kept intentional code as guilty
Reshape flags on our-code surprises stay actionable, and their comments stay deleted. A keep survives only with proof it is about something we cannot change. Audit the scoped linter and type-checker suppressions it missed. Suppressions that protect correctness or safety stay actionable MUST KILLs. Restore a deletion only against an exact exception with scoped proof.
Before accepting a thin IMPORTANT or do not remove kill or keep, investigate the named symbol yourself: git log and git blame on the lines, the ADRs and CONTEXT.md, and any APP_MAP.json decisionsSettled or invariants. An ambiguous kill stands. A keep that is refuted or still ambiguous gets deleted.
Revert and rerun one rejected report, naming the failure. Reject a second and stop. Report it open and fail the run.
3. Sketch a shape where one is needed
Fix trivial accepted flags directly by deleting a dead path, dropping a parameter, or using the real API. If any fix needs a shape, call the Skill tool for codebase-design once for the accepted set and the surrounding code. Stop at the sketch. That skill shapes, step 4 implements.
4. Implement the smallest root-cause fix in scope
Remove every named workaround. Fix causes, never symptoms, and never bolt on a symptom guard. If the root cause is out of scope, land the smallest in-scope fix and report the rest open.
Where a fix has to land in a design written without it, call the Skill tool for redesign-from-first-principles. It guides intent only. It does not authorize widening the fence or fixing instances outside it.
5. Offer to encode the constraints
Constraint comments say do not remove, do not change wording, or talk to X before changing. Leave keeps about things we cannot change. For the rest, offer the cheapest in-scope type, runtime check, test, or CI lint that makes the constraint enforceable, and wait for the user to approve it. A non-interactive run needs that approval from the caller up front.
If approved, encode the constraint and then delete the comment. Otherwise delete the comment, report the constraint open, and sketch the out-of-scope work.
6. Report
Report the deletion count, restored comments, reruns, the design sketch, fixes, encoding offers, encodings made, unenforced constraints, and other open work.
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.

