agentleFS
arraydudearraydude/agent-skills/skills/validate-pr/SKILL.md

validate-pr

Skill2 starsChanged 3 days agoMITView on GitHub

Validate AI-generated PR review comments — check whether they are accurate or hallucinated by cross-referencing each comment against the actual code changes. Use when the user wants bot or AI review comments on a PR checked for accuracy, or wants to triage which review feedback is worth addressing.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are 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.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read individual rule files for detailed explanations and examples:

    line 83

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Validate PR Comments

Validate AI-generated PR review comments on a pull request — determine which are accurate, which are low-priority noise, and which are hallucinations — by cross-referencing every comment against the actual diff.

When to Apply

Reference these guidelines when:

  • The user wants AI/bot review comments on a PR checked for accuracy
  • Triaging which review feedback is worth addressing before merge
  • Separating genuine findings from hallucinations or misread intent
  • Producing a prioritized action list from a noisy automated review

Prerequisite: the gh CLI must be installed and authenticated.

Rule Categories by Priority

PriorityCategoryImpactPrefix
1Setup & InputCRITICALsetup-
2Data GatheringCRITICALfetch-
3ValidationCRITICALvalidate-
4OutputHIGHoutput-

Quick Reference

1. Setup & Input (CRITICAL)

  • setup-gh-cli - Verify the gh CLI is installed and authenticated before anything else
  • setup-resolve-pr - Resolve the PR from the user's message (number/URL) or fall back to the current branch

2. Data Gathering (CRITICAL)

  • fetch-pr-data - Fetch comments, reviews, body, title, and files in one gh pr view --json call
  • fetch-complete-coverage - Also pull inline review-thread comments; review ALL of them, never a sample

3. Validation (CRITICAL)

  • validate-against-diff - Cross-reference each comment against the real diff and referenced files
  • validate-hallucination - Classify each comment: Valid / Low Priority / Hallucination / Addressed
  • validate-worth-addressing - Judge whether a technically-true comment is actually worth the change

4. Output (HIGH)

  • output-summary-table - Present a priority-sorted table with fixed assessment labels
  • output-followup-details - Expand a single item (comment ID, assessment, verdict) on request

Core Workflow

  1. Setup — Confirm gh is available and authenticated; resolve which PR to validate.
  2. Fetch — Pull all PR data plus inline review comments; count them so nothing is dropped.
  3. Validate — For each comment, cross-reference the diff, decide hallucination vs. valid, and weigh whether it is worth addressing.
  4. Report — Emit the priority-sorted summary table, then expand any item the user asks about.

Output Format

Report findings as a single table sorted by priority (Critical first):

#Brief CommentAssessmentPriority
1Description of the concern...✅ ValidCritical
2Description of the concern...✅ ValidHigh
3Description of the concern...⚠️ Low PriorityMedium
4Description of the concern...⚠️ Low PriorityLow
5Description of the concern...❌ Hallucination-

Assessment labels: ✅ Valid · ⚠️ Low Priority · ❌ Hallucination · ✔️ Addressed

Priority levels (sort Critical first): Critical (must fix before merge) · High (should address) · Medium (nice to have) · Low (minor) · - for hallucinations/addressed.

Close with: Ask for details on any item by number (e.g., "more on #2").

How to Use

Read individual rule files for detailed explanations and examples:

rules/setup-gh-cli.md
rules/setup-resolve-pr.md
rules/fetch-pr-data.md
rules/fetch-complete-coverage.md
rules/validate-against-diff.md
rules/validate-hallucination.md
rules/validate-worth-addressing.md
rules/output-summary-table.md
rules/output-followup-details.md

Each rule file contains a brief explanation plus incorrect/correct examples.

Full Compiled Document

For the complete guide with all rules expanded: AGENTS.md

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.