mgiovani/ai-arsenal / skills/docs-init
docs-init
VerifiedBootstraps a documentation structure (architecture, onboarding, data-model, deployment, security, contributing, and a first ADR) for a project that has little or no docs/ directory, exploring the codebase and populating templates only with content evidenced in the code. Use when the user wants to set up docs, bootstrap documentation, initialize project docs, scaffold a docs/ folder, or create docs from scratch for a new or undocumented project. Not for refreshing or syncing docs that already exist (use docs-update). Not for generating a standalone architecture or ER diagram without the surrounding document (use docs-diagram).
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 7.9 KB |
| assets/templates/architecture.md | markdown | 1.5 KB |
| assets/templates/contributing.md | markdown | 6.5 KB |
| assets/templates/data-model.md | markdown | 860 B |
| assets/templates/deployment.md | markdown | 1.2 KB |
| assets/templates/onboarding.md | markdown | 1.8 KB |
| assets/templates/security.md | markdown | 1.5 KB |
| evals/evals.json | config | 3.4 KB |
| evals/trigger-eval.json | config | 1.9 KB |
evals/evals.json
View on GitHub{
"skill": "docs-init",
"evals": [
{
"id": "fresh-repo-full-detection",
"prompt": "/docs-init for this FastAPI + PostgreSQL service. There's no docs/ directory yet — a Dockerfile, a GitHub Actions workflow, and SQLAlchemy models under app/models/ all exist in the repo.",
"assertions": [
"Explores the codebase (via Task/Explore or inline grep+find+read) before writing any documentation file",
"Creates docs/architecture.md, docs/onboarding.md, and docs/adr/0001-record-architecture-decisions.md",
"Creates docs/data-model.md because a database/ORM was detected, and docs/deployment.md plus docs/security.md because deployment configs were detected",
"Every generated file contains zero unresolved {{TOKEN}}-style placeholders",
"Technology stack, entity names, and other specifics named in the docs are traceable to files actually read in this run, not invented",
"The security.md Compliance section is either filled with real evidence found in the code or removed entirely — never left as a generic GDPR/HIPAA/SOX boilerplate paragraph with no basis in the code"
]
},
{
"id": "minimal-library-no-db-no-infra",
"prompt": "/docs-init for this small Python library — it's just a pip-installable package with no database, no Dockerfile, no CI config, and a single maintainer.",
"assertions": [
"Creates docs/architecture.md, docs/onboarding.md, and docs/adr/0001-record-architecture-decisions.md",
"Does NOT create docs/data-model.md, since no database or ORM was found",
"Does NOT create docs/deployment.md or docs/security.md, since no deployment/infra config was found",
"The final report explicitly states these files were skipped and why (no evidence), not silently omitted",
"No file contains a fabricated database schema, deployment pipeline, or compliance claim for infrastructure that doesn't exist"
]
},
{
"id": "partial-existing-docs-skip-behavior",
"prompt": "/docs-init — this repo already has docs/architecture.md (written by a teammate) but is missing onboarding, data-model, and contributing docs.",
"assertions": [
"Does not overwrite or modify the existing docs/architecture.md content",
"Creates the missing docs (onboarding, data-model if a database is present, contributing) without being asked twice",
"The final report lists docs/architecture.md under 'skipped (already exists)' and lists the newly created files separately",
"No confirmation prompt is raised for files that did not previously exist — only pre-existing files trigger the overwrite question"
]
},
{
"id": "all-docs-already-exist-refusal",
"prompt": "/docs-init on a repo where docs/architecture.md, docs/onboarding.md, docs/data-model.md, docs/deployment.md, docs/security.md, and docs/contributing.md all already exist.",
"assertions": [
"Does not write, overwrite, or delete any file under docs/ in this run",
"No mutating command (Write/Edit to any docs/ file) is executed before user confirmation is obtained",
"The final response clearly states that all target docs already exist and asks the user whether to overwrite any of them, rather than proceeding silently or guessing an answer",
"The final response does not fabricate a 'Created:' list — it accurately reports zero files created"
]
}
]
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |