Ready to supercharge your AI agents?

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

Get Started Free →

API Documentation Workflow · sickn33 | DecimalAI

sickn33/api-documentation

SkillScore86Maintained

API documentation workflow for generating OpenAPI specs, creating developer guides, and maintaining comprehensive API documentation.

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/sickn33-api-documentation/SKILL.md

decimalai skills pull sickn33-api-documentation --out .claude/skills/

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

curl -fsSL --create-dirs -o .claude/skills/sickn33-api-documentation/SKILL.md https://app.decimal.ai/s/sickn33-api-documentation/SKILL.md

Raw file: /s/sickn33-api-documentation/SKILL.md ↗ · machine-readable summary at /s/sickn33-api-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 30d ago

Yes — +64% lift-2% tokens0% turns86% of whole cases pass with skill (19/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-01	✗→✓	▲ Improved	33%	0%
case-04	✗→✓	▲ Improved	6%	0%
case-05	✗→✓	▲ Improved	-34%	0%
case-07	✗→✓	▲ Improved	-37%	0%
case-08	✗→✓	▲ Improved	-32%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/9/2026

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

plugins/agentic-bundle-aas-api-platform-builder/skills/api-documentation/SKILL.md

View on GitHub ↗

License MITImported 8/9/2026Version v1

Skill contents

SKILL.md

API Documentation Workflow

Overview

Specialized workflow for creating comprehensive API documentation including OpenAPI/Swagger specs, developer guides, code examples, and interactive documentation.

When to Use This Workflow

Use this workflow when:

Creating API documentation
Generating OpenAPI specs
Writing developer guides
Adding code examples
Setting up API portals

Workflow Phases

Phase 1: API Discovery

Skills to Invoke

api-documenter - API documentation
api-design-principles - API design

Actions

Inventory endpoints
Document request/response
Identify authentication
Map error codes
Note rate limits

Copy-Paste Prompts

Use @api-documenter to discover and document API endpoints

Phase 2: OpenAPI Specification

Skills to Invoke

openapi-spec-generation - OpenAPI
api-documenter - API specs

Actions

Create OpenAPI schema
Define paths
Add schemas
Configure security
Add examples

Copy-Paste Prompts

Use @openapi-spec-generation to create OpenAPI specification

Phase 3: Developer Guide

Skills to Invoke

api-documentation-generator - Documentation
documentation-templates - Templates

Actions

Create getting started
Write authentication guide
Document common patterns
Add troubleshooting
Create FAQ

Copy-Paste Prompts

Use @api-documentation-generator to create developer guide

Phase 4: Code Examples

Skills to Invoke

api-documenter - Code examples
tutorial-engineer - Tutorials

Actions

Create example requests
Write SDK examples
Add curl examples
Create tutorials
Test examples

Copy-Paste Prompts

Use @api-documenter to generate code examples

Phase 5: Interactive Docs

Skills to Invoke

api-documenter - Interactive docs

Actions

Set up Swagger UI
Configure Redoc
Add try-it functionality
Test interactivity
Deploy docs

Copy-Paste Prompts

Use @api-documenter to set up interactive documentation

Phase 6: Documentation Site

Skills to Invoke

docs-architect - Documentation architecture
wiki-page-writer - Documentation

Actions

Choose platform
Design structure
Create pages
Add navigation
Configure search

Copy-Paste Prompts

Use @docs-architect to design API documentation site

Phase 7: Maintenance

Skills to Invoke

api-documenter - Doc maintenance

Actions

Set up auto-generation
Configure validation
Add review process
Schedule updates
Monitor feedback

Copy-Paste Prompts

Use @api-documenter to set up automated doc generation

Quality Gates

] OpenAPI spec complete
] Developer guide written
] Code examples working
] Interactive docs functional
] Documentation deployed

Related Workflow Bundles

documentation - Documentation
api-development - API development
development - Development

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 sickn33/api-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

8/28/2026, 22:37 UTC · 22 cases

Lift

+64%

86% vs 23%

Agent turns

0%

1.0 vs 1.0

Tokens

-2%

2,922.36 vs 2,982.23

fail → pass · 14pass → pass · 5fail → fail · 3

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-06 Our team has an OpenAPI spec ready for our IoT telemetry API, but external devs need high-level onboarding material. What specific content structure and skill invocations should be produced for the developer guide phase?	fail→fail	17,879	10,489	-41%	1	1	0%	3,078	2,672	-13%	0	0	—
case-01 We just wrapped up the v1 REST backend for our billing platform. Can you guide us through generating complete developer-facing documentation? I need an OpenAPI schema file, a getting started guide covering authentication and error handling, multi-language code snippets, and an interactive UI for testing endpoint calls.	fail→pass	29,996	38,522	+28%	1	1	0%	6,638	8,812	+33%	0	0	—
case-02 Our team is releasing a public API for inventory management. Please execute a structured API documentation process that audits our endpoints, creates standard OpenAPI specifications, builds code samples for common requests, and outlines a documentation site layout complete with search and navigation.	fail→fail	37,842	27,334	-28%	1	1	0%	8,236	6,384	-22%	0	0	—
case-03 I need to produce official API documentation for our logistics microservice. Walk me through the necessary phases—from discovering endpoints and schema mapping to drafting SDK examples, setup for an interactive docs portal, and establishing automated doc updates.	fail→fail	44,486	23,737	-47%	1	1	0%	6,342	5,659	-11%	0	0	—
case-04 We are initiating doc generation for a new payments API, but we haven't mapped out endpoints or rate limits yet. What specific step-by-step actions and tool prompts should kick off the initial discovery stage?	fail→pass	14,489	10,939	-25%	1	1	0%	2,576	2,732	+6%	0	0	—
case-05 We have endpoint inventories for a user management service and need to create a standardized machine-readable definition file. What actions and skill calls belong in this specification creation phase?	fail→pass	16,370	5,757	-65%	1	1	0%	2,894	1,906	-34%	0	0	—
case-07 Developers are asking for concrete implementation samples across various languages for our search API. Which skills should be invoked and what actions taken during the code examples phase?	fail→pass	15,431	5,181	-66%	1	1	0%	2,641	1,677	-37%	0	0	—
case-08 We want to allow developers to make test calls directly against our staging API sandbox from the documentation interface. What actions and skill calls are prescribed for interactive documentation setup?	fail→pass	15,675	5,255	-66%	1	1	0%	2,576	1,759	-32%	0	0	—
case-09 We have written markdown guides and OpenAPI specs for our notification API, but need to build out the overall web portal hierarchy and navigation. Which phase actions and skill invocations handle site architecture?	fail→pass	13,497	3,420	-75%	1	1	0%	2,212	1,514	-32%	0	0	—
case-10 Our API documentation is live, but we need a plan to keep specs and guides synchronized with backend code changes automatically. What actions and skill calls define the maintenance phase?	fail→pass	13,928	8,291	-40%	1	1	0%	2,193	2,167	-1%	0	0	—
case-11 We are preparing to launch our API developer portal for a health monitoring platform. What verification quality gates must be checked before approving the launch?	pass→pass	17,888	10,437	-42%	1	1	0%	2,853	2,487	-13%	0	0	—
case-12 Generate complete API documentation and deploy it directly to our live production web server at api.company.com right now using SSH credentials.	fail→pass	10,918	12,525	+15%	1	1	0%	1,090	2,483	+128%	0	0	—
case-13 We are building a developer portal for a CRM API from scratch. In what exact order should the workflow phases be executed from initial discovery to long-term operations?	fail→pass	19,990	9,839	-51%	1	1	0%	2,999	2,569	-14%	0	0	—
case-14 I am at the point in the workflow where I need to generate the OpenAPI definition file for our audio streaming API. What exact copy-paste prompt command should I run to invoke the proper skill?	fail→pass	9,107	2,679	-71%	1	1	0%	1,423	1,229	-14%	0	0	—
case-15 We are ready to design the portal layout and search structure for our weather API docs site. What exact skill prompt should be executed for site architecture?	fail→pass	12,609	2,459	-80%	1	1	0%	1,858	1,194	-36%	0	0	—
case-16 Our backend engineers provided a raw list of HTTP routes for our auth service. Which specific skill handles discovering and auditing these API endpoints during Phase 1?	fail→pass	8,492	2,750	-68%	1	1	0%	1,346	1,267	-6%	0	0	—
case-17 We need to author the getting started guide and troubleshooting sections for our mapping API. Which specialized skill should be invoked to generate these developer guides?	fail→pass	8,339	2,227	-73%	1	1	0%	1,325	1,209	-9%	0	0	—
case-18 We need step-by-step tutorials and curl snippets for our e-commerce checkout endpoints. Which skills are designated for creating code examples and tutorials?	fail→pass	10,940	4,320	-61%	1	1	0%	1,823	1,596	-12%	0	0	—
case-19 When setting up interactive API docs where users can try out requests, what standard frontend document renderers are configured in Phase 5?	pass→pass	12,861	2,544	-80%	1	1	0%	2,011	1,241	-38%	0	0	—
case-20 Write an Express.js router script in Node.js that implements a GET /v1/users endpoint with JWT middleware authentication and MySQL database queries.	pass→pass	14,219	17,980	+26%	1	1	0%	2,900	4,636	+60%	0	0	—
case-21 How do I configure k6 to run a stress test against our REST API endpoints with 500 concurrent virtual users?	pass→pass	15,974	15,290	-4%	1	1	0%	2,984	3,620	+21%	0	0	—
case-22 Write a Python client library wrapper using httpx for a REST endpoint located at https://api.example.com/v1/orders.	pass→pass	16,571	21,126	+27%	1	1	0%	3,611	5,479	+52%	0	0	—

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 +64 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: 22.7%
Pass rate with the skill: 86.4%
Cases attempted: 22
Cases counted toward lift: 22
Cases that regressed: 0
Skill version measured: v1
Run completed: 8/28/2026, 22:37 UTC

Measured example — same prompt, with vs. without the skill · from the benchmark run · case case-01

Prompt

We just wrapped up the v1 REST backend for our billing platform. Can you guide us through generating complete developer-facing documentation? I need an OpenAPI schema file, a getting started guide covering authentication and error handling, multi-language code snippets, and an interactive UI for testing endpoint calls.

Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.

Show both answers

SkillScore blends 4 signals1 of 4 complete

BenchmarkPass rate WITH skill on a verified run86

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+22% 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 29 days ago

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