scrutinize SKILL.md skillA

scrutinize from pitimon/8-habit-ai-dev is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add pitimon/8-habit-ai-dev/scrutinize@git:20260914.5d5e0e3

Pins git:20260914.5d5e0e3 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
pitimon/8-habit-ai-dev
Path
skills/scrutinize/SKILL.md
Versions recorded
6
Latest version
git:20260914.5d5e0e3, committed Sep 14, 2026
First version recorded
May 24, 2026
Size
13,537 bytes
Repository stars
3
License
MIT

Outsider-perspective end-to-end review of a plan, PR, or proposed change — questions intent first (is there a simpler way?), then traces the actual code path (not just the diff) to verify the change does what it claims. Use BEFORE committing to an implementation, or BEFORE merging a PR — pairs with `/review-ai` (scope-question vs diff-local). Output is concise, actionable, with rationale per finding. Maps to H5 (Understand First — outsider lens) + H8…

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Scrutinize (มองจากภายนอก แล้วไล่ทางจริง)

**Habit**: H5 — Seek First to Understand + H8 — Find Your Voice | **Anti-pattern**: Rubber-stamp "LGTM" reviews that only check what's already in the diff

Stand outside the change and ask whether it should exist at all, then verify it actually does what it claims end-to-end. Different from `/review-ai`: that skill checks security/quality/perf on the diff. This skill questions scope, traces the call graph, and surfaces whether a simpler alternative was missed.

## Operating Stance

- **Outsider.** Forget who wrote it and why they think it's right. Read the artifact cold.
- **End-to-end, not diff-local.** The diff is the entry point, not the scope. Follow the call graph through real code paths.
- **Actionable, concise, with rationale.** Every finding states _what to change_, _why_, and _what evidence_ led you there. No filler, no restating the diff back.

## When to Use

- Before committing to an implementation approach (after `/design` or `/build-brief`, before code is written).
- Before merging a PR — as a second pass alongside `/review-ai`.
- When a plan or design doc feels "fine" but you want an independent check.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add pitimon/8-habit-ai-dev/scrutinize@sha256:99c31450ecc12d60

The line at the top of this page pins the label git:20260914.5d5e0e3, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_dzzjy2nb4xcwjd62.svg)](https://markdownregistry.com/a/art_dzzjy2nb4xcwjd62)

4 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 6 versions of this file, between May 24, 2026 and Sep 14, 2026, about one every 23 days.

versioncommittedcommitsizeaudit
git:20260914.5d5e0e3 latest2026-09-14 5d5e0e3 13,537 BA view · diff
git:20260912.910e5212026-09-12 910e521 13,455 BA view · diff
git:20260619.3260c742026-06-19 3260c74 13,291 BA view · diff
git:20260615.37b25042026-06-15 37b2504 13,246 BA view · diff
git:20260607.0f240c42026-06-07 0f240c4 13,015 BA view · diff
git:20260524.8540f9e2026-05-24 8540f9e 12,592 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (13537 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

pitimon/8-habit-ai-dev · 3 stars · license MIT · pushed 2026-10-13 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_dzzjy2nb4xcwjd62
GET https://markdownregistry.com/api/v1/resolve?ref=pitimon/8-habit-ai-dev/scrutinize
GET https://markdownregistry.com/api/v1/blob/99c31450ecc12d6098b4344819599ebbe9351f6472d86b144fd7d73040868f01

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from pitimon/8-habit-ai-dev

AGENTS.md AGENTS.md file
pitimon/8-habit-ai-dev · AGENTS.md
git:20261009.b232d26 · audit A · 3 stars
CLAUDE.md CLAUDE.md file
pitimon/8-habit-ai-dev · CLAUDE.md
git:20261013.98d63d7 · audit A · 3 stars
llms.txt llms.txt file
pitimon/8-habit-ai-dev · llms.txt
git:20261010.654723b · audit A · 3 stars
AGENTS.md@plugin AGENTS.md file
pitimon/8-habit-ai-dev · plugin/AGENTS.md
git:20261009.b232d26 · audit A · 3 stars
CLAUDE.md@plugin CLAUDE.md file
pitimon/8-habit-ai-dev · plugin/CLAUDE.md
git:20261013.98d63d7 · audit A · 3 stars
llms.txt@plugin llms.txt file
pitimon/8-habit-ai-dev · plugin/llms.txt
git:20261010.654723b · audit A · 3 stars
ai-dev-log SKILL.md skill
pitimon/8-habit-ai-dev · plugin/skills/ai-dev-log/SKILL.md · Generate AI-assisted development log from git history + Co-Authored-By trailers. Use for EU AI Act Article 11…
git:20260914.5d5e0e3 · audit A · 3 stars
breakdown SKILL.md skill
pitimon/8-habit-ai-dev · plugin/skills/breakdown/SKILL.md · Decompose feature into atomic tasks — 1 task per agent. Use AFTER /design and BEFORE /build-brief. Step 3 of 7-step…
git:20261004.ce92b6f · audit A · 3 stars
build-brief SKILL.md skill
pitimon/8-habit-ai-dev · plugin/skills/build-brief/SKILL.md · Generate context-rich implementation brief before coding. Use AFTER /breakdown for each task. Step 4 of 7-step…
git:20261004.ce92b6f · audit A · 3 stars
calibrate SKILL.md skill
pitimon/8-habit-ai-dev · plugin/skills/calibrate/SKILL.md · Assess your 8-habit maturity level via 5-7 questions and persist a profile to ~/.claude/habit-profile.md. Other skills…
git:20260914.5d5e0e3 · audit A · 3 stars
consistency-check SKILL.md skill
pitimon/8-habit-ai-dev · plugin/skills/consistency-check/SKILL.md · Cross-artifact and incident/config consistency analyzer — runs 5 detection passes across persisted spec artifacts (PRD…
git:20260914.5d5e0e3 · audit A · 3 stars
cross-verify SKILL.md skill
pitimon/8-habit-ai-dev · plugin/skills/cross-verify/SKILL.md · Run 17-question 8-Habit cross-verification checklist on a plan or implementation. Use AFTER planning and BEFORE…
git:20261004.ce92b6f · audit A · 3 stars

Every file in pitimon/8-habit-ai-dev

Other files named scrutinize

scrutinize SKILL.md skill
baphuongna/pi-crew · skills/scrutinize/SKILL.md · Outsider-perspective review questioning intent before tracing code. When NOT to use: implementation work (use…
git:20260911.3de89a2 · audit A · 57 stars
scrutinize SKILL.md skill
pitimon/8-habit-ai-dev · plugin/skills/scrutinize/SKILL.md · Outsider-perspective end-to-end review of a plan, PR, or proposed change — questions intent first (is there a simpler…
git:20260914.5d5e0e3 · audit A · 3 stars

Browse by kind, by grade A, or by owner.