technical-audit
Skill0 starsChanged 8 months agoMITView on GitHub
Procedure for auditing documentation for factual accuracy and redundancy.
4 other projects use a version of this.
Adopted by
Most recently taken up by
- younesbenallal/seo-skillstheir own version, first seen Nov 1, 2026
- huifer/AdSense-Readiness-Benchmarktheir own version, first seen Oct 25, 2026
- DarynaRodriguez/seo-skillstheir own version, first seen Aug 27, 2026
- donatassimkus/claude-ai-skillstheir own version, first seen Jul 23, 2026
Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 4
- huifer/AdSense-Readiness-Benchmark★ 14same name
- DarynaRodriguez/seo-skills★ 1same name
- donatassimkus/claude-ai-skills★ 1same name
- younesbenallal/seo-skills★ 1same 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 repository11 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- code-reviewSkill
- cpp-opencl-devSkill
- design-creationSkill
- gradingSkill
- readme-creationSkill
- sync-designSkill
- sync-readmeSkill
- task-creationSkill
- ux-reviewSkill
- validate-dodSkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 0 are distinctive, and 5 are very specific to this project.
0
Common
Most of the 4 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 9
Big picture: Read workflow/design/00-executive-summary.md to understand vision, philosophy and structure
- Very specific: line 10
Analyze the Content: Read the module's *.md then its corresponding workflow/design/design_[module].md and code .h/.cpp/.cl/ CMakeLists.txt
- Very specific: line 13
Use the web_search tool to query the internet and validate these claims against current data.
- Very specific: line 17
Use FileEdit to strip redundant comments from the files if necessary.
- Very specific: line 20
Use the web_search tool to provide references
“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
Technical Audit Skill
Instructions
- Big picture: Read
workflow/design/00-executive-summary.mdto understand vision, philosophy and structure - Analyze the Content: Read the module's
*.mdthen its correspondingworkflow/design/design_[module].mdand code.h/.cpp/.cl/CMakeLists.txt - Fact Check:
- Identify technical claims (e.g., "Nvidia has poor OpenCL 2.0 support", "stb_image doesn't support 16-bit PNGs").
- Use the
web_searchtool to query the internet and validate these claims against current data.
- De-duplicate: Identify areas where README or code comments redundantly explain the exact same concept.
- Report & Fix:
- Output an "Audit Report" listing false claims (with citations from your web search) and redundancies.
- Use
FileEditto strip redundant comments from the files if necessary.
- Suggest Additional Materials:
- Suggest external knowlegde sources to explor specific topics in depth
- Use the
web_searchtool to provide references
- Suggest Updates:
- Improving consistency between design to code
- Clearly mark HW requirements and limitation if missing in README
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.