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/ValorVie/custom-skillsnpx agentmods add skills/valorvie/custom-skills/documentation-guideWrote 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/valorvie/custom-skills/documentation-guide)<a href="https://agentmods.dev/skills/valorvie/custom-skills/documentation-guide"><img src="https://agentmods.dev/badge/skills/valorvie/custom-skills/documentation-guide/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/valorvie/custom-skills/documentation-guide"><img src="https://agentmods.dev/badge/skills/valorvie/custom-skills/documentation-guide.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 | $0.00066 | $0.03710 |
| Opus 5 | $0.00033 | $0.01855 |
| Sonnet 5 | $0.00013 | $0.00742 |
| Haiku 4.5 | $0.00007 | $0.00371 |
Grade A, and why
documentation-guide 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 6d 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 — 479 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation Guide
Language: English | 繁體中文
Version: 2.1.0 Last Updated: 2026-03-17 Applicability: Claude Code Skills
Purpose
This skill provides comprehensive guidance on project documentation, including:
- Documentation structure and file organization
- Content requirements by project type
- Writing standards for technical documents
- Templates for common documentation types
Quick Reference (YAML Compressed)
# === PROJECT TYPE → DOCUMENT REQUIREMENTS ===
document_matrix:
# README ARCH API DB DEPLOY MIGRATE ADR CHANGE CONTRIB
new: [REQ, REQ, if_app, if_app, REQ, NO, REC, REQ, REC]
refactor: [REQ, REQ, REQ, REQ, REQ, REQ, REQ, REQ, REC]
migration: [REQ, REQ, REQ, REQ, REQ, REQ, REQ, REQ, REC]
maintenance:[REQ, REC, REC, REC, REC, NO, if_app, REQ, if_app]
# REQ=Required, REC=Recommended, if_app=If applicable, NO=Not needed
# === DOCUMENTATION PYRAMID ===
pyramid:
level_1: "README.md → Entry point, quick overview"
level_2: "ARCHITECTURE.md → System overview"
level_3: "API.md, DATABASE.md, DEPLOYMENT.md → Technical details"
level_4: "ADR/, MIGRATION.md, CHANGELOG.md → Change history"
# === ESSENTIAL FILES ===
root_files:
README.md: {required: true, purpose: "Project overview, quick start"}
CONTRIBUTING.md: {required: "recommended", purpose: "Contribution guidelines"}
CHANGELOG.md: {required: "recommended", purpose: "Version history"}
LICENSE: {required: "for OSS", purpose: "License information"}
docs_structure:
INDEX.md: "Documentation index"
ARCHITECTURE.md: "System architecture"
API.md: "API documentation"
DATABASE.md: "Database schema"
DEPLOYMENT.md: "Deployment guide"
MIGRATION.md: "Migration plan (if applicable)"
ADR/: "Architecture Decision Records"
# === FILE NAMING ===
naming:
root: "UPPERCASE.md (README.md, CONTRIBUTING.md, CHANGELOG.md)"
docs: "lowercase-kebab-case.md (getting-started.md, api-reference.md)"
# === QUALITY STANDARDS ===
quality:
format:
language: "English (or project-specified)"
encoding: "UTF-8"
line_length: "≤120 characters recommended"
diagrams: "Mermaid preferred, then ASCII Art"
links: "Relative paths for internal links"
maintenance:
sync: "Update docs when code changes"
version: "Mark version and date at top"
review: "Include docs in code review"
periodic: "Review quarterly for staleness"
# === DIÁTAXIS CLASSIFICATION ===
diataxis:
tutorial: "Learning-oriented (getting-started.md)"
how_to: "Task-oriented (deployment.md, migration.md)"
reference: "Information-oriented (api-reference.md, CHANGELOG.md)"
explanation: "Understanding-oriented (architecture.md, ADR/)"
header: "Add **Document Type**: Tutorial | How-to | Reference | Explanation"
# === LLM DISCOVERY ===
llm_discovery:
llms_txt: "Structured index at project root for LLM retrieval"
llms_full_txt: "Optional full concatenated docs"
when: "Public projects, public APIs, projects using AI tools"
# === QUALITY METRICS ===
quality_metrics:
leading: ["Coverage ≥90%", "Freshness ≤90d", "Link Health 100%", "Example Validity 100%"]
lagging: ["Support ticket reduction", "Onboarding time", "Doc-related PR comments"]
tools: [markdown-link-check, lychee, remark-lint, vale, textstat]
# === ADR ENHANCED ===
adr_enhanced:
new_fields: [Date, Deciders, Drivers, "supersedes/superseded-by"]
lifecycle: "proposed → accepted → [deprecated | superseded]"
decision_matrix: "impact × reversibility → ADR required?"
# === TRANSLATION-FRIENDLY ===
translation_friendly:
rules: ["Complete sentences", "No idioms", "Consistent terminology", "Simple SVO", "Explicit references"]
glossary: "Maintain glossary.md for term consistency"
status_tracking: "YAML frontmatter with translation_status, source_version"
What ships with it
2 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.
- 6d ago First seen · 479 lines · 66 tokens per session scan A db97c14e050b
documentation-guide is a skill published in the GitHub repository ValorVie/custom-skills (5 stars, last pushed 2d ago), licensed MIT. It adds 66 tokens to every session and 3,710 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
plan-growth-loop
Generate prioritized growth loops with implementation roadmaps based on codebase analysis. Use when the user says "plan", "growth loops", "prioritize", "what should I build", or "roadmap".
validate-loop
Check if growth loop requirements are actually implemented in the codebase. Use when the user says "validate", "check status", "skene status", "is it done", or "verify implementation".
c-calendar
View and create calendar events via gog (Google Calendar) or icalBuddy (Apple Calendar). Check availability, list upcoming events, create/update/delete events, and manage multiple calendars.
c-jira
Manage Jira issues using jira (jira-cli). List and filter issues, create new tickets, transition issue status, manage sprints, and add comments — all from the terminal without opening a browser.
c-lockin
Lock In Mode — orchestrate distraction blocking, environment setup, and session tracking.
c-notion
Manage Notion pages and databases from the CLI using notion-cli. Create, read, search, and update pages. Query databases, add entries, and manage blocks and properties.