MicrosoftKnown publishermicrosoft/frontier-ai-starter-kit-rvas/.github/skills/content-accuracy-audit/SKILL.mdcontent-accuracy-audit
Skill7 starsChanged 20 days agoMITView on GitHub
Audit plugin guidance, setup commands, documentation, and bundled resources for current facts, broken references, and contradictions. Report verified findings and apply confirmed fixes.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- microsoft/frontier-agentic-cobuild-rvasword for word, first seen Oct 24, 2026
Other versions1 project uses a version of this.
Word for word · 1
- microsoft/frontier-agentic-cobuild-rvas★ 7100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
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 repository28 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .github/copilot-instructions.mdCopilot instructions
- azure-aigatewaySkill
- azure-aiSkill
- diagram-designSkill
- excalidraw-diagramSkill
- humanize-contentSkill
- impeccableSkill
- finetuningSkill
- capacitySkill
- customizeSkill
- presetSkill
- deploy-modelSkill
- microsoft-foundrySkill
- rvap-brandSkill
- writing-for-agentsSkill
- agentic-workflowsSkill
- foundry-hosted-agentsSkill
- foundry-iq-knowledge-basesSkill
- foundry-modelsSkill
- foundry-observabilitySkill
- foundry-projects-resourcesSkill
- foundry-toolboxesSkill
- foundry-workflowsSkill
- impeccableSkill
- ai-agent-creatorSkill
- cloud-architecture-diagramSkill
- idea-forgeSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 31
Verify Microsoft claims through current Microsoft Learn evidence.
- Very specific: line 38
After confirmation, fix sources and run npm run build, npm test, and affected diagram tests.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Content Accuracy Audit
Inspect the requested sources for correctness and currency. Apply fixes only after the user confirms findings. Read the audit checklist for the checks.
Scope
| Source | Check |
plugins/agentic-cobuild/skills/ | References, approval gates, resource paths, and current product guidance |
scripts/agentic-skills.json, docs/build.js | Upstream selectors, skill descriptions, runtime requirements, and generated command flags |
docs/start.md, docs/index.html | Installation and handoff instructions |
docs/start.html, docs/supporting-skills.md | Generated consistency; fix sources and rebuild |
README.md, CONTRIBUTING.md, PRODUCT.md | Cross-links and claims |
.github/skills/ | Maintainer guidance and references |
Procedure
- Inventory the requested source files.
- Extract checkable claims: commands, SDK signatures, resource paths, host capabilities, approval boundaries, and product maturity.
- Verify Microsoft claims through current Microsoft Learn evidence. Verify Copilot/VS Code behavior through official host documentation. Verify upstream skill selectors against the source repository and installed resources.
- Compare commands with the local implementation. Check requirements against tests rather than assuming setup success proves delivery readiness.
- Report ranked findings with file/line references, evidence, and the smallest proposed fix using the report template.
- After confirmation, fix sources and run
npm run build,npm test, and affected diagram tests. Report any unavailable verification explicitly.
Complete when every reported claim has evidence or an explicit verification gap, fixes preserve the intended workflow, and generated files match their sources.
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.