document-specialist-skill

A Claude Code “skill” that generates, audits, and converts software documentation. It supports greenfield template-based documents (e.g., SRS/PRD/SDD/OpenAPI/user guides), brownfield reverse-engineering for certain frameworks (notably Spring Boot and Pulumi), documentation audits with gap analysis/checklists, and diagram generation (via other skills). It also uses a “Progressive Disclosure Architecture (PDA)” approach described as loading only the core routing content by default and pulling workflow/templates on demand.

Evaluated Mar 30, 2026 (26d ago)
Repo ↗ DevTools documentation claude-code-skill docx pdf openapi srs prds arc42 diagrams mermaid plantuml agentic-skill pda
⚙ Agent Friendliness
36
/ 100
Can an agent use this?
🔒 Security
10
/ 100
Is it safe for agents?
⚡ Reliability
24
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
0
Documentation
35
Error Messages
0
Auth Simplicity
100
Rate Limits
0

🔒 Security

TLS Enforcement
0
Auth Strength
0
Scope Granularity
0
Dep. Hygiene
30
Secret Handling
30

No transport/security model, auth, or secret-handling guarantees are stated in the provided content. Because it generates documentation from code and may integrate other skills, the main risk is data exposure to the LLM provider/environment (not specified here) and potential leakage of sensitive code/docs into generated outputs. Dependency hygiene can’t be verified from README alone; a modest score is used due to lack of evidence.

⚡ Reliability

Uptime/SLA
0
Version Stability
45
Breaking Changes
20
Error Recovery
30
AF Security Reliability

Best When

You want documentation that’s consistent with established templates/styles (SRS/PRD/SDD/OpenAPI) and you’re working within the skill’s supported ecosystems (especially Spring Boot and Pulumi), with optional diagram/format conversion via companion skills.

Avoid When

You need a strict, deterministic documentation extractor for arbitrary languages/frameworks not covered by existing mappings (e.g., the README marks many as planned). Also avoid using it when you cannot tolerate potential hallucinations/generic sections from an LLM-style generation workflow.

Use Cases

  • Generate IEEE-style SRS, PRD, and arc42/SDD-style design docs from a project description
  • Extract documentation artifacts from a Spring Boot codebase (OpenAPI, diagrams, ER diagrams)
  • Create API documentation packages and audit them for quality gaps/best-practices
  • Audit existing documentation for completeness and provide improvement recommendations
  • Convert generated Markdown docs into DOCX and/or PDF
  • Generate architecture diagrams (C4, Mermaid/PlantUML) for system documentation
  • Produce documentation sets for compliance-oriented teams (e.g., audit-ready documentation workflows)

Not For

  • Implementing or running production software services/APIs
  • Providing verified legal/compliance attestations (it’s documentation generation/auditing, not compliance certification)
  • Acting as a secure credential vault or key-management solution
  • Fully supporting every framework/technology listed as “planned” without additional work

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
No
SDK
No
Webhooks
No

Authentication

OAuth: No Scopes: No

No authentication mechanism is described. This appears to be a local/skills-based Claude Code extension that runs within the Claude Code environment.

Pricing

Free tier: No
Requires CC: No

README only mentions installation via a marketplace; no pricing, tiers, or usage limits are provided in the available content.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • Skill is framed as LLM-driven generation/extraction; results may be generic if inputs lack sufficient context.
  • Some framework mappings are labeled “Planned” rather than implemented; detection/extraction may fail or fall back to generic templates.
  • Diagram/format conversion depends on other skills being installed (mermaid-architect, plantuml, docx, pdf).
  • No concrete contract/interface (e.g., JSON schemas, tool signatures) is described in the README; integration is likely prompt/command driven rather than API-contract driven.

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for document-specialist-skill.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-30.

8642
Packages Evaluated
17761
Need Evaluation
586
Need Re-evaluation
Community Powered