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/mblode/agent-skills/docs-writingnpx skills add mblode/agent-skills --skill docs-writinggit clone --depth 1 https://github.com/mblode/agent-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/mblode/agent-skills/docs-writing)<a href="https://agentmods.dev/skills/mblode/agent-skills/docs-writing"><img src="https://agentmods.dev/badge/skills/mblode/agent-skills/docs-writing.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 | $0.00141 | $0.01402 |
| Opus 5 | $0.00071 | $0.00701 |
| Sonnet 5 | $0.00028 | $0.00280 |
| Haiku 4.5 | $0.00014 | $0.00140 |
Grade A, and why
docs-writing 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.
How it starts
The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation Writing
- IS: writing and auditing technical documentation quality (Diataxis doc types, voice, structure, clarity, runnable code, formatting, navigation, content hygiene) for docs sites, API references, documentation-site tutorials, how-to docs, and existing READMEs.
- IS NOT: editorial blog tutorials or articles (use the external
ghostwriterskill with platformblog), a README from scratch (usereadme-creator), AGENTS.md or CLAUDE.md instructions (useagents-md), or marketing and landing-page copy (usecopywriting).
Mode dispatch
- Reviewing docs? → Audit workflow.
- Writing/rewriting a page? → Writing workflow.
- "Improve"/"fix" docs? → Audit first, then apply fixes yourself.
Audit workflow
Track this checklist:
Docs audit progress:
- [ ] Step 1: Scope to changed files unless a full sweep was requested
- [ ] Step 2: Classify each doc (tutorial, how-to, reference, explanation) and audience
- [ ] Step 3: Run CRITICAL categories (voice-, structure-)
- [ ] Step 4: Run HIGH categories (clarity-, code-)
- [ ] Step 5: Run remaining in-scope categories (format-, nav-, scan-, hygiene-, review-)
- [ ] Step 6: Report per the output contract, by severity
Doc type gates which rules apply, so classify before loading. Load rule files by category prefix (rules/voice-*.md, then rules/structure-*.md, ...) only for in-scope categories. After applying fixes, rerun the rules that produced findings before finalizing.
Writing workflow
Track this checklist:
Docs writing progress:
- [ ] Step 1: Pick one Diataxis type per file (tutorial, how-to, reference, explanation); name the audience
- [ ] Step 2: Read defaults bundles (voice-defaults, clarity-defaults, scan-defaults) plus structure rules for the type
- [ ] Step 3: Draft: bottom line up front, quick start for getting-started docs, runnable example per concept
- [ ] Step 4: Self-audit against CRITICAL and HIGH categories; fix findings
- [ ] Step 5: Verify: run every example, resolve every link, confirm parameter names against the implementation
What ships with it
50 files 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.
- rules/_sections.md 2.3 KB
- rules/_template.md 1.2 KB
- rules/clarity-defaults.md 1.6 KB
- rules/clarity-no-latin.md 796 B
- rules/clarity-no-nominalizations.md 841 B
- rules/clarity-one-idea-per-sentence.md 844 B
- rules/clarity-serial-comma.md 666 B
- rules/code-context-ratio.md 1.1 KB
- rules/code-error-descriptions.md 1.0 KB
- rules/code-isolated-to-full.md 1.2 KB
- rules/code-multiple-languages.md 1.1 KB
- rules/code-named-functions.md 1.2 KB
- rules/code-realistic-example-names.md 1.1 KB
- rules/code-runnable-examples.md 1016 B
- rules/format-bold-ui-code-font.md 956 B
- rules/format-descriptive-links.md 813 B
- rules/format-image-alt-text.md 847 B
- rules/format-lowercase-filenames.md 773 B
- rules/format-periods-inside-quotes.md 822 B
- rules/format-semantic-html.md 991 B
- rules/format-sentence-case.md 766 B
- rules/hygiene-delete-outdated.md 1.0 KB
- rules/hygiene-docs-directory.md 756 B
- rules/hygiene-experimental-label.md 916 B
- rules/hygiene-no-temporal.md 958 B
- rules/hygiene-retcon-label.md 924 B
- rules/hygiene-update-metadata.md 808 B
- rules/nav-breadcrumb-context.md 929 B
- rules/nav-dont-repeat.md 941 B
- rules/nav-every-doc-linked.md 875 B
- rules/nav-layer-depth.md 1.0 KB
- rules/nav-relative-paths.md 729 B
- rules/nav-searchable-headings.md 770 B
- rules/review-defaults.md 1.0 KB
- rules/review-verify-links.md 802 B
- rules/scan-defaults.md 1.0 KB
- rules/scan-three-column-api.md 1.2 KB
- rules/structure-bluf.md 1.2 KB
- rules/structure-conditions-first.md 1.2 KB
- rules/structure-diataxis.md 1.2 KB
- rules/structure-heading-overview.md 1.0 KB
- rules/structure-next-steps.md 1.1 KB
- rules/structure-no-filler-sections.md 1.4 KB
- rules/structure-one-idea-per-section.md 1.4 KB
- rules/structure-procedures.md 1016 B
- rules/structure-quick-start.md 1.2 KB
- rules/voice-defaults.md 1.3 KB
- rules/voice-no-anthropomorphism.md 1.2 KB
- rules/voice-no-jargon.md 1.1 KB
- rules/voice-requirements-language.md 1.1 KB
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 · 98 lines · 141 tokens per session scan A 990c773af0a5
docs-writing is a skill published in the GitHub repository mblode/agent-skills (95 stars, last pushed 5d ago), licensed MIT. It adds 141 tokens to every session and 1,402 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
mcporter
List, auth, and call MCP servers/tools from the terminal.
article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.
sector-rotation
行业轮动分析——申万行业景气度评分、行业动量排名、产业链传导、估值/盈利/资金流多维比较框架.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
complete-partial-pr
Evaluate and complete an issue or PR where the submitted patch fixes only a narrow symptom of the reported pain point. Use when a contribution may miss adjacent integration surfaces, provider/spec semantics, roundtrip behavior, tests, docs, or historical maintainer decisions.
deploy-docker-compose
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…