Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/PracticalSwan/agent-skillsnpx agentmods add skills/practicalswan/agent-skills/documentation-authoringWrote 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/practicalswan/agent-skills/documentation-authoring)<a href="https://agentmods.dev/skills/practicalswan/agent-skills/documentation-authoring"><img src="https://agentmods.dev/badge/skills/practicalswan/agent-skills/documentation-authoring/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/practicalswan/agent-skills/documentation-authoring"><img src="https://agentmods.dev/badge/skills/practicalswan/agent-skills/documentation-authoring.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 71 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
- high Prompt Injection · line 463 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.00040 | $0.03458 |
| Opus 5.5 | $0.00016 | $0.01383 |
| Sonnet 5.5 | $0.00008 | $0.00692 |
| Haiku 4.5 | $0.00004 | $0.00346 |
Grade A, and why
documentation-authoring 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 1mo 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 — 494 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation Authoring Master
Expert guidance for creating structured, high-quality documentation across all types of technical and business documents.
- Leverage native parallel subagent dispatch and 200k+ context windows where available.
Activation Conditions
Use symptom -> action triggers: when one matches, apply this skill and verify with the protocol below.
Trigger Conditions:
- User mentions writing documentation: "write a doc", "draft a proposal", "create a spec", "write up"
- User mentions specific doc types: "PRD", "design doc", "decision doc", "RFC"
- User asks to "create an implementation plan", "document requirements", "plan a feature"
- Creating technical specifications or business requirements
- Starting a new product or feature development cycle
- Translating vague ideas into concrete technical specifications
- Stakeholders need unified "source of truth" for project scope
Part 2: Context Gathering
Initial Questions
Start by asking for meta-context about the document:
-
What type of document is this?
- Technical spec, decision doc, proposal, RFC, PRD, knowledge base
-
Who's the primary audience?
- Developers, executives, stakeholders, end-users? Understanding affects tone and depth
-
What's the desired impact when someone reads this?
- Make a decision, implement a feature, understand a concept?
-
Is there a template or specific format to follow?
- Company templates, industry standards, regulatory requirements
-
Any other constraints or context to know?
- Deadlines, sensitive information, existing related documents
Inform them they can answer in shorthand or dump information however works best for them.
Template Handling
If user provides a template:
- Analyze structure and requirements
- Adapt co-authoring workflow to template format
- Ensure all required sections are covered
If user mentions editing an existing document:
- Fetch the existing document
- Understand current state and gaps
- Plan revisions strategically
What ships with it
6 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.
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.
- 1mo ago Changed ac4486143f22
- 1mo ago Changed 4cba8975d8cc
- 1mo ago Changed 9136c6b4e257
- 1mo ago First seen · 494 lines · 40 tokens per session scan A 7620ff10f1ec
documentation-authoring is a skill published in the GitHub repository PracticalSwan/agent-skills (21 stars, last pushed yesterday), licensed MIT. It adds 40 tokens to every session and 3,458 once invoked, about $0.0002 per session on Opus 5.5. 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
librechat-docs
Use the official LibreChat documentation to install, configure, operate, and troubleshoot LibreChat.
river-review-docs
A documentation review guide for checking whether project instructions and documentation match the code. It also compares Japanese and English documentation and checks that important terms are used consistently.
markdown-search
Search and navigate local markdown via MCP. Use when the user asks to search docs, find a README section, list headings/TOC, extract code examples by language, read frontmatter, or grep internal wikis and ADRs on disk.
doc-quality-review
Assess documentation quality across readability, consistency, audience fit, and prose clarity. Produces a scored review with actionable findings. This skill should be used before releases, during doc reviews, or when documentation feels unclear or inconsistent.
doc-claim-validator
Validate that claims in documentation match codebase reality. Extracts verifiable assertions (file paths, commands, function references, behavioral claims, dependencies) from markdown docs and checks them against the actual project. Use after code changes, before releases, or when docs feel untrustworthy.
prd-authoring
Standard for authoring product PRDs in docs/prd/: state the problem, users, requirements, and success; assign PRD-{AREA}-{NN} IDs; link down to specs.