Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/wpgaurav/claude-code-skills/polishnpx skills add wpgaurav/claude-code-skills --skill polishgit clone --depth 1 https://github.com/wpgaurav/claude-code-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/wpgaurav/claude-code-skills/polish)<a href="https://agentmods.dev/skills/wpgaurav/claude-code-skills/polish"><img src="https://agentmods.dev/badge/skills/wpgaurav/claude-code-skills/polish.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00026 | $0.01916 |
| Opus 5 | $0.00013 | $0.00958 |
| Sonnet 5 | $0.00005 | $0.00383 |
| Haiku 4.5 | $0.00003 | $0.00192 |
Grade A, and why
polish scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
89% identical to polish — 18 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adapted from impeccable by Paul Bakaus, used under the Apache License 2.0. Modified for this collection; see NOTICE.md for what changed.
First: If a design-guidelines skill is installed (Anthropic's frontend-design, impeccable's /impeccable commands, or the project's own design system), load it for principles and anti-patterns. Otherwise continue with the checks below.
Perform a meticulous final pass to catch all the small details that separate good work from great work. The difference between shipped and polished.
Pre-Polish Assessment
Understand the current state and goals:
-
Review completeness:
- Is it functionally complete?
- Are there known issues to preserve (mark with TODOs)?
- What's the quality bar? (MVP vs flagship feature?)
- When does it ship? (How much time for polish?)
-
Identify polish areas:
- Visual inconsistencies
- Spacing and alignment issues
- Interaction state gaps
- Copy inconsistencies
- Edge cases and error states
- Loading and transition smoothness
CRITICAL: Polish is the last step, not the first. Don't polish work that's not functionally complete.
Polish Systematically
Work through these dimensions methodically:
Visual Alignment & Spacing
- Pixel-perfect alignment: Everything lines up to grid
- Consistent spacing: All gaps use spacing scale (no random 13px gaps)
- Optical alignment: Adjust for visual weight (icons may need offset for optical centering)
- Responsive consistency: Spacing and alignment work at all breakpoints
- Grid adherence: Elements snap to baseline grid
Check:
- Enable grid overlay and verify alignment
- Check spacing with browser inspector
- Test at multiple viewport sizes
- Look for elements that "feel" off
Typography Refinement
- Hierarchy consistency: Same elements use same sizes/weights throughout
- Line length: 45-75 characters for body text
- Line height: Appropriate for font size and context
- Widows & orphans: No single words on last line
- Hyphenation: Appropriate for language and column width
- Kerning: Adjust letter spacing where needed (especially headlines)
- Font loading: No FOUT/FOIT flashes
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 204 lines · 26 tokens per session scan A 3d32b7e7361f
polish is a skill published in the GitHub repository wpgaurav/claude-code-skills (3 stars, last pushed 15d ago), licensed MIT. It adds 26 tokens to every session and 1,916 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 89% identical to polish, differing in 18 lines, and is treated as a copy.
Other skills, from other repositories
humanizer
Rewrite AI-sounding text so it reads naturally without changing what it says. Use when editing or reviewing prose for inflated claims, sales language, vague sources, repetitive structure, stock AI words, passive voice, filler, or chatbot artifacts. Based on Wikipedia's "Signs of AI writing.".
shuorenhua
检查和清理中英文文本里的 AI 套路，适用于“去 AI 味”“说人话”“自然一点”“别像模板”“先标问题”这类改写和审稿需求；按场景控制力度，同时保留事实、术语、语域和责任主体。.
speak-human-tw
「說人話」：繁體中文的去 AI 味改寫 skill。審查與改寫文字，去除 AI 味道、校正中國用語與半形標點，讓文字讀起來像真人寫的。 觸發時機：用戶說「去 AI 味」「說人話」「這段好 AI」「改自然一點」「幫我潤稿去掉 AI 感」「校對一下再發」，或要求檢查電子報、社群貼文、銷售頁、課程文案、客服回信、簡報、公告、Email 等對外文字的語感。 不要觸發：逐字翻譯、模仿特定品牌 voice、事實查核（非風格問題）、程式碼／log／設定檔、要求「潤成雷蒙的語氣」（那是 content-writing skill 的事，本 skill 只去 AI 味、不加個人風格）。.
commit
Group changes into one atomic commit, draft a Conventional Commit message in COMMITAGENTMSG, put it through an independent review and the commit-msg gates, confirm it with the operator, then commit and rebase. Use this skill whenever the user asks to commit work in a tbhb repo ("commit this," "commit the staged…
codex-merge-pr
Squash merge a pull request. The commit message comes from this workflow rather than from GitHub, whose own version concatenates every commit on the branch into text no linter ever reads. A briefing script prints the published description, every commit the squash collapses, and the diffstat, then leaves a…
merge-pr
Squash merge a pull request. The commit message comes from this workflow rather than from GitHub, whose own version concatenates every commit on the branch into text no linter ever reads. A briefing script prints the published description, every commit the squash collapses, and the diffstat, then leaves a…