deep-review SKILL.md skillA

deep-review from drafthq/draft is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add drafthq/draft/deep-review@git:20260819.fda278e

Pins git:20260819.fda278e in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
drafthq/draft
Path
skills/deep-review/SKILL.md
Versions recorded
5
Latest version
git:20260819.fda278e, committed Aug 19, 2026
First version recorded
Jun 11, 2026
Size
21,747 bytes
Repository stars
40
License
MIT

Single-module production readiness audit (ACID, resilience, observability). Use to audit one service/module end-to-end — NOT for diff/PR review (use review / quick-review) or bug-finding sweeps (use bughunt).

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

# Deep Review — Production-Grade Module Audit

Perform an exhaustive end-to-end lifecycle review of a service, component, or module. Ensure ACID compliance and production-grade enterprise quality. Unlike standard review commands, this operates strictly at the module level.

## MANDATORY GRAPH LOOKUP (read before Phase 1)

When `draft/graph/schema.yaml` exists, this skill **must** follow the graph-first lookup contract in [core/shared/graph-query.md](../../core/shared/graph-query.md) §Mandatory Lookup Contract. Deep-review uses the graph to **narrow review scope** — a key 30–50% scope reduction:

First resolve the bundled helpers:

```bash
# Locate Draft's bundled helpers (cwd is the user's project; ${CLAUDE_PLUGIN_ROOT}
# is not exported into skill Bash). See core/shared/tool-resolver.md.
DRAFT_TOOLS="${DRAFT_PLUGIN_ROOT:-$(cat ~/.cache/draft/plugin-root 2>/dev/null)}/scripts/tools"
[ -d "$DRAFT_TOOLS" ] || DRAFT_TOOLS="$(ls -d ~/.claude/plugins/cache/*/draft/*/scripts/tools 2>/dev/null | sort -V | tail -1)"
[ -d "$DRAFT_TOOLS" ] || DRAFT_TOOLS="$(ls -d ~/.claude/plugins/marketplaces/*draft*/scripts/tools 2>/dev/null | tail -1)"
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add drafthq/draft/deep-review@sha256:fa18a07c33b52ab1

The line at the top of this page pins the label git:20260819.fda278e, 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_7lcsefcwelhvv5xg.svg)](https://markdownregistry.com/a/art_7lcsefcwelhvv5xg)

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

Versions

The registry has recorded 5 versions of this file, between Jun 11, 2026 and Aug 19, 2026, about one every 17 days.

versioncommittedcommitsizeaudit
git:20260819.fda278e latest2026-08-19 fda278e 21,747 BA view · diff
git:20260716.8fa8aa02026-07-16 8fa8aa0 21,725 BA view · diff
git:20260616.41b20702026-06-16 41b2070 21,681 BA view · diff
git:20260615.4c8d2a32026-06-15 4c8d2a3 20,779 BA view · diff
git:20260611.33c921c2026-06-11 33c921c 20,756 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 (21747 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

drafthq/draft · 40 stars · license MIT · pushed 2026-10-21 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_7lcsefcwelhvv5xg
GET https://markdownregistry.com/api/v1/resolve?ref=drafthq/draft/deep-review
GET https://markdownregistry.com/api/v1/blob/fa18a07c33b52ab1cec1398f8ad68994a306aee9d64b111f55bf44f3dd6e3daf

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 drafthq/draft

CLAUDE.md CLAUDE.md file
drafthq/draft · CLAUDE.md
git:20261021.53d9aec · audit A · 40 stars
AGENTS.md@integrations/agents AGENTS.md file
drafthq/draft · integrations/agents/AGENTS.md
git:20261021.53d9aec · audit C · 40 stars
adr SKILL.md skill
drafthq/draft · skills/adr/SKILL.md · Create and manage Architecture Decision Records. Documents significant technical decisions with context, alternatives…
git:20260819.fda278e · audit A · 40 stars
assist-review SKILL.md skill
drafthq/draft · skills/assist-review/SKILL.md · Reviewing someone else's PR for handoff/sign-off. Isolates structural changes from trivial edits, flags HLD/LLD drift…
git:20260819.fda278e · audit A · 40 stars
bughunt SKILL.md skill
drafthq/draft · skills/bughunt/SKILL.md · Performs an exhaustive 14-dimension bug hunt across the codebase using Draft context (architecture, tech-stack…
git:20260819.fda278e · audit B · 40 stars
change SKILL.md skill
drafthq/draft · skills/change/SKILL.md · Handle mid-track requirement changes. Analyzes impact on completed and pending tasks, proposes amendments to spec.md…
git:20260819.fda278e · audit A · 40 stars
coverage SKILL.md skill
drafthq/draft · skills/coverage/SKILL.md · Compute code coverage for active track or module. Targets 95%+ coverage with report and justification for uncovered…
git:20260819.fda278e · audit A · 40 stars
debug SKILL.md skill
drafthq/draft · skills/debug/SKILL.md · Structured debugging session. Reproduce, isolate, diagnose, and fix bugs using systematic investigation. Invoked by…
git:20260819.fda278e · audit A · 40 stars
decompose SKILL.md skill
drafthq/draft · skills/decompose/SKILL.md · Decompose project or track into modules with dependency mapping. Project scope updates architecture.md and derives…
git:20260819.fda278e · audit A · 40 stars
deploy-checklist SKILL.md skill
drafthq/draft · skills/deploy-checklist/SKILL.md · Pre-deployment verification checklist. Generates customized checklists based on tech-stack with rollback triggers…
git:20260819.fda278e · audit A · 40 stars
discover SKILL.md skill
drafthq/draft · skills/discover/SKILL.md · Primary router for discovery, debugging, investigation, quality, and exploration workflows. Analyzes user intent and…
git:20260614.c276954 · audit A · 40 stars
docs SKILL.md skill
drafthq/draft · skills/docs/SKILL.md · Primary router for authoring and documentation workflows. Analyzes intent and dispatches primarily to documentation…
git:20260609.d617e1b · audit A · 40 stars

Every file in drafthq/draft

Other files named deep-review

deep-review SKILL.md skill
lobehub/lobehub · .agents/skills/deep-review/SKILL.md · Use for independent PR, diff or branch review; not explanations. Full multi-agent review requires an explicit…
git:20261009.71f05f9 · audit A · 84,260 stars
deep-review SKILL.md skill
michelkerkmeester/skilled-agent-harness_spec-driven-loops · .hermes/skills/deep-review/SKILL.md · Autonomous iterative code-review loop with externalized state, convergence detection, P0/P1/P2 findings, fresh context…
v1.11.7.0 · audit A · 40 stars
deep-review SKILL.md skill
ulises-jeremias/agent-toolkit · plugins/agent-toolkit-complete/.opencode/skills/deep-review/SKILL.md · Evidence-based deep code review rubric — severity + confidence findings across maintainability, correctness, security…
git:20260831.856ee57 · audit A · 19 stars
deep-review SKILL.md skill
ulises-jeremias/agent-toolkit · plugins/agent-toolkit-complete/.github/skills/deep-review/SKILL.md · Evidence-based deep code review rubric — severity + confidence findings across maintainability, correctness, security…
git:20260831.856ee57 · audit A · 19 stars
deep-review SKILL.md skill
smart-ai-memory/attune-ai · .claude/skills/deep-review/SKILL.md · Multi-pass deep code review — security, quality, and test gaps
v1.0.0 · audit A · 11 stars
deep-review SKILL.md skill
smart-ai-memory/attune-ai · .agents/skills/deep-review/SKILL.md · Multi-pass deep code review — security, quality, and test gaps
git:20260718.206f45d · audit A · 11 stars
deep-review SKILL.md skill
fabioc-aloha/alex_skill_mall · plugins/code-quality/deep-review/skills/deep-review/SKILL.md · Adversarial code review with three parallel perspectives — Advocate, Skeptic, Architect — that create productive…
git:20260728.80a7ab6 · audit A · 5 stars
deep-review SKILL.md skill
alexwaha/agentry · plugin/skills/deep-review/SKILL.md · Multi-lens parallel review of code, architecture, documents, or configuration with severity-ranked findings…
git:20261014.88e2c2f · audit A · 3 stars

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