verify-docs
Skill8 starsChanged 9 months agoMITView on GitHub
Verify documentation line numbers match current code state
5 other projects use a version of this.
Adopted by
Most recently taken up by
- ProjectAJ14/eklavyatheir own version, first seen Oct 20, 2026
- agentydragon/ducktapetheir own version, first seen Oct 9, 2026
- RemiMyrset/rootstheir own version, first seen Oct 2, 2026
- Dangooy/tianji-skillstheir own version, first seen Sep 26, 2026
- paulo-yamagishi/claude-code-setuptheir own version, first seen Feb 9, 2026
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 5
- ProjectAJ14/eklavya★ 29same name
- agentydragon/ducktape★ 11same name
- Dangooy/tianji-skills★ 11same name
- paulo-yamagishi/claude-code-setup★ 2same name
- RemiMyrset/roots★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository7 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- context-optimizeSkill
- implementSkill
- planSkill
- researchSkill
- validateSkill
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 6 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 4 edited versions we read keep these.
6
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 7
Check if documentation line numbers still match the actual code.
- Distinctive: line 11
After code changes, line numbers in documentation may drift.
- Distinctive: line 23
Check if file exists
- Distinctive: line 24
Check if line number is within file bounds
- Distinctive: line 75
After adding/removing significant code
- Distinctive: line 76
Before creating a PR
“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Context Engineering: Verify Documentation
Check if documentation line numbers still match the actual code.
Purpose
After code changes, line numbers in documentation may drift. This skill:
- Finds all
file:linereferences in.claude/documentation - Verifies the referenced lines exist and match described content
- Reports accuracy and suggests fixes
Process
- Scan Documentation
- Find all patterns like
file.py:123or[file.py:123] - Extract file path and line number
- Find all patterns like
- Verify References
- Check if file exists
- Check if line number is within file bounds
- Sample content to verify it matches description
- Calculate Accuracy
- Total references found
- Valid references
- Accuracy percentage
- Generate Report
Documentation Accuracy Report ============================= Total References: 156 Valid: 142 Invalid: 14 Accuracy: 91% Invalid References: - context/workflows/auth.md:45 → src/auth.py:230 (line moved to 245) - context/workflows/api.md:12 → src/api.py:100 (file renamed)
Usage
Check specific file:
/context-eng:verify-docs path/to/changed/file.pyCheck all documentation:
/context-eng:verify-docsAuto-fix (update line numbers):
/context-eng:verify-docs --fixTarget Accuracy
| Level | Accuracy | Action |
| Excellent | ≥80% | No action needed |
| Good | 60-80% | Update when convenient |
| Warning | 40-60% | Update soon |
| Critical | <40% | Update immediately |
When to Run
- After refactoring
- After adding/removing significant code
- Before creating a PR
- Weekly maintenance
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.