Favicon of Docs Grounding Verifier

Docs Grounding Verifier Skill

AI Agent SkillPythonOpen source

CLAIM-LEVEL grounding verification. Adapts the RAGAS faithfulness-eval pattern (proven in RAG literature) to docs/code instead of generated- answers/retrieved-context. Source code is the ground truth; docs paragraphs are the candidate text under audit. Published by microsoft in apm.

What is Docs Grounding Verifier Skill?

CLAIM-LEVEL grounding verification. Adapts the RAGAS faithfulness-eval pattern (proven in RAG literature) to docs/code instead of generated- answers/retrieved-context. Source code is the ground truth; docs paragraphs are the candidate text under audit. Published by microsoft in apm. This profile combines repository metadata with install, compatibility, and usage signals so developers can quickly decide whether it fits their agent workflow before opening the source repository.

Trust signal
95/100
Maintenance signal
90/100
Adoption signal
87/100

Automated repository signals based on public metadata such as recency, license, installation evidence, and adoption. These are not a security audit or endorsement.

Key capabilities

  • Includes SKILL.md support
  • Reusable instructions support
  • Security review
  • Documentation
  • Security review use cases
  • Documentation use cases

Technical details

Copy skill directory
  • Install or run with Copy skill directory

When to use Docs Grounding Verifier Skill

  • Use it for security review.
  • Use it for documentation.

Built with

PythonCopy skill directory

Editorial notes

Source

  • Creator: microsoft
  • Repository: microsoft/apm
  • Skill file: .apm/skills/docs-grounding-verifier/SKILL.md

What it does

CLAIM-LEVEL grounding verification. Adapts the RAGAS faithfulness-eval pattern (proven in RAG literature) to docs/code instead of generated- answers/retrieved-context. Source code is the ground truth; docs paragraphs are the candidate text under audit.

Skill instructions

docs-grounding-verifier CLAIM-LEVEL grounding verification. Adapts the RAGAS faithfulness-eval pattern (proven in RAG literature) to docs/code instead of generated- answers/retrieved-context. Source code is the ground truth; docs paragraphs are the candidate text under audit. python-architect persona doc-writer persona Sibling contract This skill is a SIBLING of docs-corpus-audit and docs-sync. The boundary is load-bearing: | Skill | Trigger | Scope | Granularity | | ---------------------- | -------------------------------------- | ---------------- | --------------- | | docs-sync | PR opened/synchronized | PR diff only | Page-level | | docs-corpus-audit | Maintainer asks for whole-corpus pass | Entire corpus | Page-level | | docs-grounding-verifier | Verify specific pages factually | 1..N pages | CLAIM-level | docs-corpus-audit invokes this skill in its VERIFY phase on the highest-risk pages of each wave. docs-sync can invoke it on the specific pages in a PR diff. The skill is also run

Explore related resources

Frequently asked questions

What is Docs Grounding Verifier?

Docs Grounding Verifier is a open-source AI agent skill with Copy skill directory. CLAIM-LEVEL grounding verification. Adapts the RAGAS faithfulness-eval pattern (proven in RAG literature) to docs/code instead of generated- answers/retrieved-context.

Who is Docs Grounding Verifier best for?

Docs Grounding Verifier is best for reusing agent instructions, scripts, and references, security review workflows, documentation workflows.

How do I install Docs Grounding Verifier?

Install or run Docs Grounding Verifier using Copy skill directory. Check Docs Grounding Verifier for the latest setup command.

Is Docs Grounding Verifier actively maintained?

Docs Grounding Verifier may need a closer maintenance check before production use.

Share:

Stars
3,219
Forks
283
Last commit
10 days ago
Repository age
10 months
License
MIT

Auto-fetched from GitHub.

Ad
Favicon

 

  
 

Similar to Docs Grounding Verifier