Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Documentation Workflow Bundle · sickn33 | DecimalAI

Documentation

SkillScore64Maintained

documentation

Documentation generation workflow covering API docs, architecture docs, README files, code comments, and technical writing.

Documentationby sickn33

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Doc Ops pack

1 · One-time — install the CLI (docs ↗)

pip install decimalai

2 · Get the skill — writes .claude/skills/documentation/SKILL.md

decimalai skills pull documentation --out .claude/skills/

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/documentation/SKILL.md https://app.decimal.ai/s/documentation/SKILL.md

Raw file: /s/documentation/SKILL.md ↗ · machine-readable summary at /s/documentation.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 55d ago

Yes — +59% lift · at higher cost+35% tokens0% turns64% of whole cases pass with skill (14/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-12	✗→✓	▲ Improved	—	—
case-14	✗→✓	▲ Improved	—	—
case-15	✗→✓	▲ Improved	—	—
case-16	✗→✓	▲ Improved	—	—
case-17	✗→✓	▲ Improved	—	—

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 7/30/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

sickn33 / antigravity-awesome-skills

skills/documentation/SKILL.md

View on GitHub ↗

License MITImported 8/2/2026Version v1

Skill contents

SKILL.md

Documentation Workflow Bundle

Overview

Comprehensive documentation workflow for generating API documentation, architecture documentation, README files, code comments, and technical content from codebases.

When to Use This Workflow

Use this workflow when:

Creating project documentation
Generating API documentation
Writing architecture docs
Documenting code
Creating user guides
Maintaining wikis

Workflow Phases

Phase 1: Documentation Planning

Skills to Invoke

docs-architect - Documentation architecture
documentation-templates - Documentation templates

Actions

Identify documentation needs
Choose documentation tools
Plan documentation structure
Define style guidelines
Set up documentation site

Copy-Paste Prompts

Use @docs-architect to plan documentation structure

Use @documentation-templates to set up documentation

Phase 2: API Documentation

Skills to Invoke

api-documenter - API documentation
api-documentation-generator - Auto-generation
openapi-spec-generation - OpenAPI specs

Actions

Extract API endpoints
Generate OpenAPI specs
Create API reference
Add usage examples
Set up auto-generation

Copy-Paste Prompts

Use @api-documenter to generate API documentation

Use @openapi-spec-generation to create OpenAPI specs

Phase 3: Architecture Documentation

Skills to Invoke

c4-architecture-c4-architecture - C4 architecture
c4-context - Context diagrams
c4-container - Container diagrams
c4-component - Component diagrams
c4-code - Code diagrams
mermaid-expert - Mermaid diagrams

Actions

Create C4 diagrams
Document architecture
Generate sequence diagrams
Document data flows
Create deployment docs

Copy-Paste Prompts

Use @c4-architecture-c4-architecture to create C4 diagrams

Use @mermaid-expert to create architecture diagrams

Phase 4: Code Documentation

Skills to Invoke

code-documentation-code-explain - Code explanation
code-documentation-doc-generate - Doc generation
documentation-generation-doc-generate - Auto-generation

Actions

Extract code comments
Generate JSDoc/TSDoc
Create type documentation
Document functions
Add usage examples

Copy-Paste Prompts

Use @code-documentation-code-explain to explain code

Use @code-documentation-doc-generate to generate docs

Phase 5: README and Getting Started

Skills to Invoke

readme - README generation
environment-setup-guide - Setup guides
tutorial-engineer - Tutorial creation

Actions

Create README
Write getting started guide
Document installation
Add usage examples
Create troubleshooting guide

Copy-Paste Prompts

Use @readme to create project README

Use @tutorial-engineer to create tutorials

Phase 6: Wiki and Knowledge Base

Skills to Invoke

wiki-architect - Wiki architecture
wiki-page-writer - Wiki pages
wiki-onboarding - Onboarding docs
wiki-qa - Wiki Q&A
wiki-researcher - Wiki research
wiki-vitepress - VitePress wiki

Actions

Design wiki structure
Create wiki pages
Write onboarding guides
Document processes
Set up wiki site

Copy-Paste Prompts

Use @wiki-architect to design wiki structure

Use @wiki-page-writer to create wiki pages

Use @wiki-onboarding to create onboarding docs

Phase 7: Changelog and Release Notes

Skills to Invoke

changelog-automation - Changelog generation
wiki-changelog - Changelog from git

Actions

Extract commit history
Categorize changes
Generate changelog
Create release notes
Publish updates

Copy-Paste Prompts

Use @changelog-automation to generate changelog

Use @wiki-changelog to create release notes

Phase 8: Documentation Maintenance

Skills to Invoke

doc-coauthoring - Collaborative writing
reference-builder - Reference docs

Actions

Review documentation
Update outdated content
Fix broken links
Add new features
Gather feedback

Copy-Paste Prompts

Use @doc-coauthoring to collaborate on docs

Documentation Types

Code-Level

JSDoc/TSDoc comments
Function documentation
Type definitions
Example code

API Documentation

Endpoint reference
Request/response schemas
Authentication guides
SDK documentation

Architecture Documentation

System overview
Component diagrams
Data flow diagrams
Deployment architecture

User Documentation

Getting started guides
User manuals
Tutorials
FAQs

Process Documentation

Runbooks
Onboarding guides
SOPs
Decision records

Quality Gates

] All APIs documented
] Architecture diagrams current
] README up to date
] Code comments helpful
] Examples working
] Links valid

Related Workflow Bundles

development - Development workflow
testing-qa - Documentation testing
ai-ml - AI documentation

Limitations

Use this skill only when the task clearly matches the scope described above.
Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

Illustrative Want to see what documentation would put in front of your model? Preview the rendered body and check its trigger phrases — no LLM call, no signup.

Latest benchmark · publisher runVerified

7/28/2026, 19:22 UTC · 22 cases

Lift

+59%

64% vs 5%

Agent turns

0%

1.0 vs 1.0

Tokens

+35%

3,468.95 vs 2,577.27

fail → pass · 13pass → pass · 1fail → fail · 8

Per-case results (22)

Case	Status	Duration (ms)			Turns			Tokens			Tool calls
Case	Status	Without	With	Δ	Without	With	Δ	Without	With	Δ	Without	With	Δ
case-12 Before our upcoming v2.0 release of 'order-management-service', we need to create comprehensive release notes from git commits. Is there an automated workflow subskill for generating changelogs from git history?	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-14 After releasing 'notifications-service', we need a strategy to update outdated docs, fix broken links, and collaborate on ongoing revisions. What subskills support collaborative writing and maintenance?	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-18 We need to organize our documentation artifacts for 'shipping-service' into distinct operational categories. How should JSDoc comments and runbooks be classified across documentation types?	pass→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-15 When building architecture diagrams for 'checkout-service', we want to cover all four C4 levels. Which individual subskills correspond to Context and Container diagrams?	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-16 At the start of a major project 'data-mesh-core', we need to establish style guidelines, choose tools, and plan documentation structure. Which planning phase subskills should be invoked first?	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-13 We are about to finalize documentation for 'billing-service'. Before publishing, we want to ensure all quality gates are met. What specific verification checklist items define documentation quality completion?	fail→fail	—	—	—	—	—	—	—	—	—	—	—	—
case-17 For our onboarding wiki in 'engineering-handbook', we want dedicated subskills to write onboarding guides and handle developer QA. Which specific wiki subskills fulfill these roles?	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-11 Our engineering organization needs an internal developer portal and wiki site for 'platform-docs'. Instead of plain text files in folders, we want a structured VitePress wiki layout with onboarding pages. Which subskills should handle wiki architecture and page writing?	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-09 In our TypeScript repository 'user-profile-api', function signatures and exports lack structured doc comments. We are tempted to write generic inline comments manually. What code documentation subskills should be leveraged to automate and explain function level comments?	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-19 We want copy-paste prompt examples to invoke documentation subskills in our team chat for 'search-indexer'. Show the exact prompt format used to invoke the C4 architecture skill.	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-10 We are releasing an open-source CLI tool 'deploy-cli'. We need to generate a project README along with interactive onboarding tutorials and setup guides. Outline the phase and subskills for getting started documentation.	fail→fail	—	—	—	—	—	—	—	—	—	—	—	—
case-21 We need to research legacy source code and write wiki pages for 'legacy-ledger-service'. Which specific wiki subskills assist with research and page creation?	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-20 When documenting the external REST API for 'payment-gateway', what specific documentation assets belong in the API Documentation category versus User Documentation?	fail→fail	—	—	—	—	—	—	—	—	—	—	—	—
case-07 We have REST API endpoints in our Express.js backend repository 'auth-service'. We want to draft an API documentation workflow. Should we manually write static markdown for each endpoint, or is there a structured subskill invocation pattern for API docs and OpenAPI specs? Provide the recommended plan.	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-06 We need to build a machine learning model using PyTorch to detect fraudulent transactions in 'fraud-detector-v2'. Please write the Python training loop, data loader preprocessing scripts, and loss evaluation code.	fail→fail	—	—	—	—	—	—	—	—	—	—	—	—
case-02 I need help organizing and writing documentation for our recently refactored payment processing service. Could you produce a structured workflow guide detailing how to generate our API endpoint references, build context and container architectural diagrams, insert function explanations across the codebase, and setup release notes based on commit history?	fail→fail	—	—	—	—	—	—	—	—	—	—	—	—
case-01 We are preparing to launch a new web backend service written in TypeScript. I need a complete technical documentation framework established for this repository. Please outline a multi-phase documentation plan that covers everything from initial architecture planning, OpenAPI spec generation, and C4 system diagrams down to code-level TSDoc comments, the primary README, and an internal wiki onboarding structure.	fail→fail	—	—	—	—	—	—	—	—	—	—	—	—
case-04 We are refactoring our Node.js payment gateway module in 'payment-service'. We need you to write a Jest unit test suite covering success and failure paths for the 'chargeCustomer' function rather than writing documentation. Please provide the test code.	fail→fail	—	—	—	—	—	—	—	—	—	—	—	—
case-03 Our team is taking over an existing legacy platform with almost no written context. Please design a comprehensive documentation roadmap for us that specifies how to structure the getting-started guides, capture automated changelogs, build interactive developer wiki pages, and establish quality gates for ongoing doc maintenance.	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-05 Our PostgreSQL database queries in 'analytics-pipeline' are taking over 5 seconds to run on large tables. Please analyze our SQL queries, write optimized SQL indexes, and refactor the database schema to improve execution speed.	fail→fail	—	—	—	—	—	—	—	—	—	—	—	—
case-08 Our team needs to document the system architecture for our distributed 'inventory-service'. We want to map out system levels from high-level context down to containers and code components. What specific C4 modeling skills and diagram tools should be invoked for this phase?	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-22 During the final review gate for 'identity-provider', what checks must be completed regarding API endpoints and the primary project README?	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—

These cases were also screened by the skill’s intent / safety pass.See the Trust review ↗Reproduce this benchmark in Colab ↗

How this skill was measured

DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +59 percentage points is the difference between those two pass rates over the 22 comparable cases.

Model measured: gemini-3.6-flash
Graded by: gemini-3.6-flash
Grading method: judged
Verification: verified
Pass rate without the skill: 4.6%
Pass rate with the skill: 63.6%
Cases attempted: 22
Cases counted toward lift: 22
Cases that regressed: 0
Skill version measured: v1
Run completed: 7/28/2026, 19:22 UTC

The per-case answers from this run were removed by the retention sweep, so the case table below shows the verdicts without the text either arm produced. The counts above were recorded at the time and are unaffected. Answers are now kept for 180 days.

SkillScore blends 4 signals1 of 4 complete

BenchmarkPass rate WITH skill on a verified run64

Live evalNeeds ≥10 evaluated traces in 30 days

AI ratingNeeds ≥10 rated traces

AdoptionNeeds ≥10 serves across ≥2 orgs in 30 days

Efficiency · separate axis (at equal correctness)+0% turns+66% tokens

Shown for transparency; not credited unless a verified run shows no correctness regression.

Backed by 1 of 4 signals — each added signal makes the score more robust.

Verified on gemini-3.6-flash · re-tested 55 days ago

Other measured skills in the registry, with their headline benchmark lift.