polish
Skill1 starsChanged 6 days agoMITView on GitHub
Run the quality fixer pipeline with subagents and require verified resolution of actionable findings. Defaults to changed source files; pass `full` for all source files.
70 other projects use a version of this.
Adopted by
Most recently taken up by
- brillout/skillstheir own version, first seen Nov 16, 2026
- Integralist/agent-skillstheir own version, first seen Nov 14, 2026
- galiprandi/job-seekertheir own version, first seen Nov 14, 2026
- theexperiencecompany/gaiatheir own version, first seen Nov 13, 2026
- angusfretwell/skillstheir own version, first seen Nov 10, 2026
- Mrbaeksang/skillstheir own version, first seen Nov 8, 2026
Used with
Projects with it also use layout, shape 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.
owshq-mecSkilllayout
Improve layout, spacing, and visual rhythm. Fixes monotonous grids, inconsistent spacing, and weak visual hierarchy. Use when the user mentions layout feeling off, spacing issues, visual hierarchy, crowded UI, alignment problems, or wanting better composition.
Also in 8 projects that use this
HAR5HA-7663Skillshape
Plan the UX and UI for a feature before writing code. Runs a structured discovery interview, then produces a design brief that guides implementation. Use during the planning phase to establish design direction, constraints, and strategy before any code is written.
Also in 13 projects that use this
PeterCangSkilltokens
Count all historical Claude Code token usage across all local projects, broken down by model, project, date, and week. Includes cost estimation based on official Anthropic pricing.
Also in 3 projects that use this
arjunkshahSkillredesign
Redesign existing interfaces to premium quality while preserving product goals and functional behavior.
Also in 3 projects that use this
leonaaardobSkillmotion
Complete Motion.dev documentation - modern animation library for React, JavaScript, and Vue (formerly Framer Motion)
Also in 3 projects that use this
MicrosoftSkillreview-loop
Iterative review loop using any lens agent against any target (plan, code, design). Use when you want to run a focused review cycle: spawn a fresh reviewer subagent with a specific lens, present findings and remediation to the user, apply fixes with user guidance, and repeat until clean.
Also in 3 projects that use this
Other versions70 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 70
- educlopez/ui-craft★ 441same name
- nexmoe/DayBee★ 424same name
- nexmoe/eve★ 424same name
- Southclaws/storyden★ 351same name
- 10xChengTu/Mux0★ 337same name
- theexperiencecompany/gaia★ 327same name
- AkaraChen/aghub★ 271same name
- zacharyfmarion/openscad-studio★ 252same name
- jagrat7/linux-wallpaper-engine★ 227same name
- MJbae/awesome-novel-studio★ 148same name
60 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 repository8 other files it gives its agents.
- AGENTS.mdAGENTS.md
- create-testSkill
- create-toolSkill
- polishSkill
- review-changesSkill
- create-testSkill
- create-toolSkill
- review-changesSkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 4 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 62 edited versions we read keep these.
4
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
- Very specific: line 14
Default: uncommitted files plus files affected by this task.
- Distinctive: line 24
Use the Agent tool in this order.
- Distinctive: line 44
If executable code changed after the last successful tests, rerun the relevant tests and required final checks.
- Distinctive: line 46
If a rescan finds violations, return them to the responsible fixer and reverify its edits.
- Distinctive: line 50
Use PASS, FAIL, or BLOCKED.
“Common” is measured: kept by at least 6 in 10 of the 62 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
Polish
Read docs/code-quality.md. Success requires its PASS verdict after the last edit.
Scope and Handoffs
Default: uncommitted files plus files affected by this task. full includes all of src/.
Pass the explicit scope to every agent; extend it when a step creates or changes files.
Repository-wide checks still run where the agent requires them.
For documentation-only work, mark source-only steps N/A and run the documentation steps.
Each handoff includes changed files, outstanding findings, and verification already completed. An assigned finding stays open until its owner returns a fix and verification or an evidenced disposition.
Pipeline
Use the Agent tool in this order. Wait for each step, except launch 4a/4b together and wait for both. Restrict 4a to source comments and 4b to documentation files.
| Step | subagent_type | Required result |
| 1 | lint-type-format-fixer | Fix lint, type, and formatting failures. |
| 2 | smart-test-fixer | Fix test failures. Pass step 1's verification so unchanged checks are not repeated. |
| 3 | standards-enforcer | Resolve all actionable size, complexity, smell, prop-drilling, and dead-code findings in scope. |
| 4a | comment-fixer | Resolve documentation findings in the assigned source files. Pass full only for full mode. |
| 4b | docs-reality-sync | Sync affected docs and workflow references, including .agents/skills/ and .codex/agents/. |
| 5 | agents-md-enforcer | Prune redundant instructions while preserving enforcement requirements and working entrypoints. |
| 6 | markdown-quality-fixer | Fix Markdown lint and table formatting for all Markdown changed by the pipeline. |
Announce each step and summarize its result. Route fixable check/test failures back to the responsible fixer. Complete independent work when one finding is blocked, but carry the failure into the final verdict.
Verify the Final State
- Rerun Scopewalker checks affected by edits after step 3. Comment additions can exceed size limits.
- If executable code changed after the last successful tests, rerun the relevant tests and required final checks.
- Reuse successful verification only while relevant inputs and requirements remain unchanged. Changes to dependencies, configuration, imports, or consumers can invalidate earlier results.
- If a rescan finds violations, return them to the responsible fixer and reverify its edits.
- Recheck every outstanding handoff. A promised fix or suggested follow-up cannot count as resolved.
Report step results, applied fixes, retained findings with evidence, and final verification. Use PASS, FAIL, or BLOCKED. Say "Polish complete" only for PASS.
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.

