Install
$ agentstack add skill-democra-ai-skill-to-workflow-input-skill ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
About
Doc Audit
Overview
This skill audits a documentation folder and produces a single prioritized report of quality problems. It checks four independent dimensions, confirms each finding is real, and groups the results by severity.
When to use
Use when the user asks to audit documentation, check docs quality, or do a pre-release docs pass on a folder of Markdown/MDX files.
Procedure
Step 1 — Inventory
List every documentation file under the target folder (default: ./docs). Record the relative path and size of each .md / .mdx file. If there are no docs, stop and report that.
Step 2 — Audit the four dimensions
For the inventory, check these four dimensions. They are independent — none of them depends on the result of another:
- Broken links — find internal links that point to missing files/anchors
and external links that look dead or malformed.
- Stale code examples — find fenced code blocks that reference APIs,
flags, or file paths that no longer exist in the project.
- Missing sections — compare each page against the expected shape for its
type (a how-to needs prerequisites + steps; a reference needs a parameter table) and list missing sections.
- Readability — flag pages with overlong paragraphs, undefined jargon, or
a reading level inappropriate for the audience.
For each dimension, produce a list of findings. Each finding has: file, a short title, a severity (blocker / major / minor), and a suggested fix.
Step 3 — Verify each finding
Documentation audits produce false positives (a "broken" link that is actually valid, a "stale" example that still works). Before reporting, confirm each finding is real by re-checking it against the actual files. Drop findings that do not hold up.
Step 4 — Prioritize and report
Merge the confirmed findings from all four dimensions, de-duplicate any that overlap, sort by severity (blockers first), and write a single DOC-AUDIT.md report grouped by dimension with a summary count at the top.
Notes
- Treat
README.mdas a how-to for the "missing sections" check. - Never edit the docs themselves — this skill only reports.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: democra-ai
- Source: democra-ai/skill-to-workflow
- License: MIT
- Homepage: https://github.com/democra-ai/skill-to-workflow
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.