Blind-spot check
SkillDev toolsThis skill is the general blind-spot check for PostHog Review, a final sweep that runs after every enabled review perspective has reviewed a chunk. It reads what the earlier specialist reviews found, then hunts only where they did not look: edge cases, error paths, unhandled inputs, and cross-file interactions. It reports only genuinely new, concrete problems and returns an empty list when nothing was missed.
Then ask your AI: use the Blind-spot check skill
Details
Instructions available. Your AI can read the instructions. Execution depends on the setup they require.
Account requirements not reviewed. Check the skill instructions before use; Ahel provides instructions and does not run this skill.
No other account needed.
Have a PR chunk that has already been reviewed by every enabled review perspective.
What your AI can do with it
- Runs as the last step of a multi-perspective code review of a PR chunk
- Reads prior specialist findings to avoid re-walking their ground
- Hunts untested edge cases, error paths, and unhandled inputs
- Checks cross-file interactions and assumptions under load or hostile input
- Reports only new, concrete problems with a nameable trigger and consequence
- Returns an empty issues list instead of padding when nothing was missed
Getting started
- Have a PR chunk that has already been reviewed by every enabled review perspective.
- Ensure the review prompt lists which perspectives ran and what they found, or notes that they found nothing.
- Add this skill as the final step after all perspective reviews complete.
- Run the review and collect the issues list, which may be empty.
What this skill tells your AI
The instructions your AI receives, as published by posthog/posthog in products/review_hog/skills/review-hog-blind-spots-general/SKILL.md and read by Ahel’s review.
You are the blind-spot check — the final sweep of a PR-chunk review. Several specialist perspectives have each already reviewed this exact chunk in parallel: which ones ran is listed in your review prompt, along with what they found (or a note that they found nothing on this chunk). Your job is to catch the real, high-value issues that ALL of them missed. You are conditioned on their actual output, so hunt where they did not look instead of re-walking their ground.
How to hunt
- Study the covered findings first (when there are any): they show where the perspectives spent their attention. Your value is everywhere else.
- Dig into what the prior findings did NOT touch — untested edge cases, error and failure paths, unhandled inputs, cross-file interactions, and assumptions that break under load or hostile input.
- You are not scoped to one specialty: a real issue is in scope no matter which lens it belongs to, as long as no perspective already raised it.
What to report
- Only genuinely NEW problems. Do not re-report, restate, or minorly reword anything already covered in the findings above or in the PR's inline comments.
- The bar is the same as any perspective's: a real, concrete problem with a nameable trigger and a nameable consequence, anchored to this chunk's changes.
- If the perspectives were thorough and nothing was missed, return an empty issues list. An empty sweep is a valid, good outcome — padding is not.
Signals
- GitHub stars
- 40k
- Forks
- 3k
- Last commit
- Oct 2026
Questions
- What does this skill do?
- It is the final sweep of a PR-chunk review. It reads what the specialist perspectives found, then hunts for real, high-value issues they all missed, and returns only genuinely new problems.
- When does it run?
- It runs after every enabled review perspective has reviewed a chunk, as the last step of the multi-perspective review.
- What does it report?
- Only genuinely new, concrete problems with a nameable trigger and consequence, anchored to the chunk's changes. It does not re-report or reword anything already covered.
Advanced
- Item type
- skill
- Key
review-hog-blind-spots-general-posthog- Source
- github.com/posthog/posthog