← Back to Skills Marketplace
anderskev

Ensure Docs

by Kevin Anderson · GitHub ↗ · v1.0.1 · MIT-0
cross-platform ⚠ suspicious
139
Downloads
0
Stars
1
Active Installs
2
Versions
Install in OpenClaw
/install ensure-docs
Description
Verify documentation coverage and generate missing docs interactively
README (SKILL.md)

Ensure Documentation Coverage

Verify documentation coverage across a codebase, report gaps, and generate missing docs with parallel language-specific agents.

Workflow

Complete steps in order. Do not advance until each step’s Pass is satisfied.

  1. Language detection — Follow Phase 1 (language detection) in references/workflow.md.

    • Pass: For each language you will verify, you have evidence of at least one matching source file (counts or command output); if none qualify, stop with a short “no applicable languages” message and do not spawn verifiers.
  2. Load standards — Read the sections for your detected languages (language standards, verifier prompts, consolidation format) in the same reference file.

    • Pass: You can state which standard applies per language (e.g. Google docstrings, JSDoc, GoDoc) before spawning agents.
  3. Parallel verification — Spawn one verifier per qualifying language using the agent prompts and JSON output shape in the reference (Phase 2).

    • Pass: Each completed agent returns parseable JSON including language, files_scanned, and findings (array, possibly empty).
  4. Consolidated report — Merge results per Phase 3 (summary table, severity grouping, detailed findings if requested).

    • Pass: The user sees the merged report (inline or written to an agreed path) before you claim the audit is done or propose fixes.
  5. Generation — Only if --report-only is not set: offer choices per Phase 4; apply doc edits only after an explicit user choice to generate.

    • Pass: No documentation edits for gaps until the user selects an option that includes generation; if they decline or choose report-only behavior, end after the report.
  6. Post-edit verification — After any generation, run or offer the linter commands in Phase 5 of the reference for languages you changed, when those tools exist in the repo.

    • Pass: Linter run completed with output captured, or N/A with a one-line reason (e.g. tool not configured); remaining issues are listed or cleared.

Notes

  • Use --report-only to skip generation.
  • Avoid test files unless they are test helpers.
  • Keep report output aligned with the language-specific standards in the reference file.
Usage Guidance
The skill's behavior mostly matches its description, but it contains a critical contradiction: disable-model-invocation is set true while the workflow requires spawning Task-based subagents and asking interactive questions (which need model invocation). Before installing: 1) Ask the publisher to clarify/fix the disable-model-invocation setting — as-is the skill will likely be non-functional. 2) Confirm your platform provides the Task tool (subagent capability) and that you trust it to inspect the repository. 3) Run the skill in --report-only mode first (no automatic edits) and test on a non-sensitive repository. 4) Only allow generation (edits) after reviewing the proposed changes; the skill's docs state edits should only proceed after explicit user choice, but verify this behavior in practice.
Capability Analysis
Type: OpenClaw Skill Name: ensure-docs Version: 1.0.1 The ensure-docs skill is a documentation auditing and generation tool that automates the verification of docstring compliance for Python, TypeScript, and Go. It uses standard shell commands (find, grep) for language detection and spawns sub-agents to analyze code and generate missing documentation interactively. The workflow is well-documented in SKILL.md and references/workflow.md, utilizing standard development tools like ruff, eslint, and staticcheck for post-generation verification without any signs of malicious intent or data exfiltration.
Capability Assessment
Purpose & Capability
The name/description ('Verify documentation coverage and generate missing docs') align with the instructions: detect languages, run codebase scans, consolidate findings, and optionally generate docs. The file-scanning, standards, and generation steps are coherent for this purpose.
Instruction Scope
The SKILL.md header and registry metadata set disable-model-invocation: true, but the workflow repeatedly instructs spawning verification and generation subagents via the Task tool (and using AskUserQuestion) which require model invocation. This is a direct contradiction: either the skill will be unable to perform its described agent-spawning behavior, or the metadata is wrong. The instructions also call standard shell tools (find, grep) to read the repository — that is expected for this purpose but assumes typical shell availability.
Install Mechanism
Instruction-only skill with no install spec and no code to write to disk. This is the lowest-risk install profile.
Credentials
The skill declares no required environment variables, no credentials, and no config paths. The actions described (scanning repo files, optionally running linters present in the repo) are proportionate to the stated purpose.
Persistence & Privilege
Skill is not always-on, does not request elevated persistence, and does not modify other skills' configs. It does instruct spawning subagents for parallel verification, which is expected for the task.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install ensure-docs
  3. After installation, invoke the skill by name or use /ensure-docs
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
- Expanded and clarified the workflow steps for verifying and generating documentation. - Added explicit "Pass" criteria for each workflow step, detailing required evidence and conditions before advancing. - Included requirements for language standards identification and agent output validation. - Mandated user confirmation before generating any documentation, and clarified behavior for `--report-only`. - Specified post-edit linter verification, including guidance on handling missing or unavailable tools.
v1.0.0
Initial release of ensure-docs: - Verifies documentation coverage across a codebase for multiple languages. - Detects languages, analyzes docs, and reports gaps. - Offers interactive generation of missing documentation where needed. - Consolidates findings into a single, standards-aligned report. - Excludes regular test files from coverage. - Includes option to report only, without generating docs.
Metadata
Slug ensure-docs
Version 1.0.1
License MIT-0
All-time Installs 1
Active Installs 1
Total Versions 2
Frequently Asked Questions

What is Ensure Docs?

Verify documentation coverage and generate missing docs interactively. It is an AI Agent Skill for Claude Code / OpenClaw, with 139 downloads so far.

How do I install Ensure Docs?

Run "/install ensure-docs" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Ensure Docs free?

Yes, Ensure Docs is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Ensure Docs support?

Ensure Docs is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Ensure Docs?

It is built and maintained by Kevin Anderson (@anderskev); the current version is v1.0.1.

💬 Comments