Home / iuliandita / skills · skills/plan-review/SKILL.md · GitHub

plan-review skillA

plan-review is agent-read markdown (skill) from iuliandita/skills: Review product, business, and engineering decisions and plans: clarify requirements, challenge assumptions, and assess risks..

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

What the file says

# Plan Review

Review product, business, and engineering decisions before implementation. Clarify unresolved requirements or critique a settled proposal through constructive and adversarial lenses.

1. **Clarification** turns an unresolved plan into a decision record, then stress-tests it.
2. **Settled-decision critique** challenges an existing decision or artifact without reopening choices that evidence does not invalidate.

Use both lenses by default: identify who benefits, who pays, what becomes hard to undo, and the constraint that preserves the useful upside. Honor an explicit Jekyll-only or Hyde-only request while still naming cost bearers, reversibility, and a concrete next step.

## When to use

- Clarify a feature, infrastructure, architecture, product, business, or fiction plan before building.
- Challenge a settled strategy, roadmap, pricing, platform, governance, or design decision.
- Pressure-test assumptions, failure paths, incentives, reversibility, and second-order effects.

## When NOT to use

- Review existing code for bugs, security flaws, or repository health: use the appropriate code or **repo-audit** skill.
…

Read the whole file at its exact version.

How to install

Latest version
mdr add iuliandita/skills/plan-review@git:20260920.ebf9a3d
Exact content
mdr add iuliandita/skills/plan-review@sha256:0aff83de9effb594

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_3fvurlgvuprdoade.svg)](https://markdownregistry.com/a/art_3fvurlgvuprdoade)

1 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260920.ebf9a3d latest2026-09-20 ebf9a3d 5,864 BA view · diff
git:20260920.ac018532026-09-20 ac01853 5,650 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, 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 (5864 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

iuliandita/skills · 7 stars · license MIT · pushed 2026-09-24 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_3fvurlgvuprdoade
GET https://markdownregistry.com/api/v1/resolve?ref=iuliandita/skills/plan-review
GET https://markdownregistry.com/api/v1/blob/0aff83de9effb594d9e7ba1e6001cf14a92d8105d2b92f2206f2b6a791adba65

Your agent 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.

More from iuliandita/skills

ai-ml skill
iuliandita/skills · skills/ai-ml/SKILL.md · Deprecated name. Use llm-app-development; load this notice only when ai-ml is explicitly requested.
git:20260920.ac01853 · audit A · 7 stars
ansible skill
iuliandita/skills · skills/ansible/SKILL.md · Write, review, and debug Ansible playbooks, roles, inventories, Ansible Vault, Molecule tests, and AWX/AAP.
git:20260920.ac01853 · audit A · 7 stars
anti-ai-prose skill
iuliandita/skills · skills/anti-ai-prose/SKILL.md · Edit prose that sounds AI-written: remove filler and canned phrasing in docs, emails, and replies.
git:20260920.ac01853 · audit A · 7 stars
anti-slop skill
iuliandita/skills · skills/anti-slop/SKILL.md · Deprecated name. Use code-simplification; load this notice only when anti-slop is explicitly requested.
git:20260920.ac01853 · audit A · 7 stars
arch-btw skill
iuliandita/skills · skills/arch-btw/SKILL.md · Deprecated name. Use arch-linux; load this notice only when arch-btw is explicitly requested.
git:20260920.ac01853 · audit A · 7 stars
arch-linux skill
iuliandita/skills · skills/arch-linux/SKILL.md · Administer Arch Linux, CachyOS, EndeavourOS, and Manjaro: pacman, AUR, upgrades, boot, GPU, and desktop issues.
git:20260920.ebf9a3d · audit A · 7 stars
backend-api skill
iuliandita/skills · skills/backend-api/SKILL.md · Design and review REST/HTTP APIs, with bounded GraphQL and gRPC contract guidance: OpenAPI, auth, pagination…
git:20260920.ac01853 · audit A · 7 stars
browse skill
iuliandita/skills · skills/browse/SKILL.md · Deprecated and removed. Load this notice only when browse is explicitly requested; no replacement skill.
git:20260920.ac01853 · audit A · 7 stars
ci-cd skill
iuliandita/skills · skills/ci-cd/SKILL.md · Build, review, and debug CI/CD pipelines and runners: GitHub Actions, GitLab CI, Forgejo/Gitea, and Woodpecker.
git:20260920.ebf9a3d · audit A · 7 stars
cluster-health skill
iuliandita/skills · skills/cluster-health/SKILL.md · Deprecated name. Use kubernetes-health; load this notice only when cluster-health is explicitly requested.
git:20260920.ac01853 · audit A · 7 stars
code-review skill
iuliandita/skills · skills/code-review/SKILL.md · Review code and diffs for correctness: bugs, regressions, edge cases, races, and resource leaks.
git:20260920.ac01853 · audit A · 7 stars
code-simplification skill
iuliandita/skills · skills/code-simplification/SKILL.md · Review code for dead code, duplication, overengineering, invented APIs, and weak tests. Report safe reductions; no…
git:20260920.ebf9a3d · audit A · 7 stars

Every file in iuliandita/skills

Other files named plan-review

plan-review skill
sd0xdev/sd0x-harness · skills/plan-review/SKILL.md · Pre-ExitPlanMode adversarial plan review loop via Codex exec. Use when: in plan mode, before presenting a plan to the…
git:20260905.3012b9f · audit A · 189 stars
plan-review skill
jikig-ai/soleur · plugins/soleur/skills/plan-review/SKILL.md · This skill should be used when having multiple specialized agents review a plan in parallel. It spawns DHH, Kieran, and…
git:20260916.6c1dbcb · audit A · 15 stars
plan-review skill
mickeyyaya/evolve-loop · skills/plan-review/SKILL.md · Use when scout-report.md exists and TDD/Build hasn't started yet. Runs four lenses (CEO, Eng, Design, Security) in…
git:20260913.4657393 · audit A · 5 stars

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