review-hog-validation-criteria — Claude Code skill: setup and features
review-hog-validation-criteria serves as a final PR review gate, filtering candidate findings to keep real defects while discarding speculative noise.
no license 187 installs ★ 101 updated 2026-10-24
npx skills add PostHog/ai-plugin --skill review-hog-validation-criteria -a claude-codeWhat review-hog-validation-criteria does
The skill functions as a decision gate for pull request reviews. Instead of inspecting code from scratch or inventing fresh problems, it assesses candidate issues raised by previous checkers. It inspects callers, validation logic, and surrounding context in the live tree before deciding whether each candidate warrants surfacing to the author.
Evaluation relies on a strict precision-over-recall threshold. Findings remain valid only when they describe concrete defects: logic bugs, authentication or injection vulnerabilities, data loss, API contract breaks, and high-load performance drops like N+1 queries. Pure cosmetic critiques, naming debates, defensive guards against impossible states, and hypothetical edge cases get thrown out.
When a candidate lacks both an observable execution path and an explicit consequence, the skill drops it immediately.
What it helps with
- filter speculative suggestions and cosmetic remarks out of code reviews
- confirm whether a reported defect is truly reachable through existing callers
- suppress redundant defensive checks already handled by types or frameworks
- surface only actionable flaws involving correctness, security, or API contracts
Example prompts for the agent
- Filter these candidate PR review findings using review-hog-validation-criteria
- Verify if this flagged performance defect is reachable in the codebase before reporting it
How to install review-hog-validation-criteria
1Skills CLI (Vercel)
npx skills add PostHog/ai-plugin --skill review-hog-validation-criteria -a claude-code2Manually: put the files in place
~/.claude/skills/review-hog-validation-criteria/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/review-hog-validation-criteria/
1Skills CLI (Vercel)
npx skills add PostHog/ai-plugin --skill review-hog-validation-criteria -a codex2Manually: put the files in place
.agents/skills/review-hog-validation-criteria/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add PostHog/ai-plugin --skill review-hog-validation-criteria -a cursor2Manually: put the files in place
.cursor/skills/review-hog-validation-criteria/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install PostHog/ai-plugin skills/review-hog-validation-criteria2Manually: put the files in place
.github/skills/review-hog-validation-criteria/SKILL.md1Skills CLI (Vercel)
npx skills add PostHog/ai-plugin --skill review-hog-validation-criteria -a gemini-cli2Platform CLI
gemini skills install https://github.com/PostHog/ai-plugin --path skills/review-hog-validation-criteriaManually: put the files in place
.devin/skills/review-hog-validation-criteria/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add PostHog/ai-plugin --skill review-hog-validation-criteria -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about review-hog-validation-criteria
How to install review-hog-validation-criteria in Claude Code?
Run npx skills add PostHog/ai-plugin --skill review-hog-validation-criteria -a claude-code. The file will be placed in ~/.claude/skills/review-hog-validation-criteria/SKILL.md.
What does review-hog-validation-criteria do?
It evaluates pre-flagged review candidates against the live codebase, setting is_valid to true only for verifiable bugs, security flaws, or breaking changes.
How does the skill handle uncertain findings?
It applies a precision-over-recall rule: whenever evidence fails to confirm real impact, the issue is dropped rather than surfaced.