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 skills add hxy91819/mason-skills --skill polishgit clone --depth 1 https://github.com/hxy91819/mason-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/hxy91819/mason-skills/polish)<a href="https://agentmods.dev/skills/hxy91819/mason-skills/polish"><img src="https://agentmods.dev/badge/skills/hxy91819/mason-skills/polish/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/hxy91819/mason-skills/polish"><img src="https://agentmods.dev/badge/skills/hxy91819/mason-skills/polish.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00120 | $0.03953 |
| Opus 5 | $0.00060 | $0.01976 |
| Sonnet 5 | $0.00024 | $0.00791 |
| Haiku 4.5 | $0.00012 | $0.00395 |
Grade A, and why
article-workflow-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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Article Workflow Polish
这是流程类 Skill，默认仅在用户显式调用 $article-workflow-polish 时运行。
This is Phase 5 of the article-workflow-* skill series, corresponding to the "round-by-round polish" step of the article optimization workflow.
Goal: Under the constraint of preserving the author's personal style, iteratively polish the main draft expression across three rounds — remove truly redundant words (not tone carriers), smooth out truly awkward sentences (not flatten deliberate rhythm), and unify residual terminology and formatting inconsistencies. The AI executes; the author makes the final judgment. Each round produces independent output, and the next round only proceeds after the author confirms.
Trigger Scenarios
Use this skill when the user requests:
- Executing article optimization workflow Phase 5
- Round-by-round polish / language polish / polish
- Generating
.article-workflow/05-polish-rounds/output - Doing a final expression polish pass after the main draft is complete
- Starting from the main draft + style bible and iteratively tightening the text
Input and Output
Default inputs:
.article-workflow/04.5-main-draft/main-draft.md(the integrated main draft from Phase 4.5, serving as the polish baseline).article-workflow/style-bible.md(the style bible from Phase 5.0; must be read before each polish round).article-workflow/04.6-visual-plan/visual-plan.md(if present; only used to avoid polish disrupting planned text-image rhythm; does not change the polish scope)
Optional inputs:
.article-workflow/00-cleaned-sources/terminology-notes.md(confirmed proper noun table and uncertain items from Phase 0.5)
Default outputs (all placed in a single directory):
.article-workflow/05-polish-rounds/05.1-trim.md: Round 1 — trim redundant words.article-workflow/05-polish-rounds/05.2-rhythm.md: Round 2 — adjust rhythm.article-workflow/05-polish-rounds/05.3-terms.md: Round 3 — unify terminology.article-workflow/05-polish-rounds/polished-draft.md: Final polished draft output from the three rounds
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago Changed · +3 lines · +120 tokens per session dcf86cff4b90
- 11d ago First seen · 272 lines · 0 tokens per session scan A d6f4117499de
article-workflow-polish is a skill published in the GitHub repository hxy91819/mason-skills (2 stars, last pushed today), licensed MIT. It adds 120 tokens to every session and 3,953 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…