review-plan SKILL.md skillA

review-plan from jgwill/miadi-orchestration-kit is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add jgwill/miadi-orchestration-kit/review-plan@v0.1.0

Pins v0.1.0 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
jgwill/miadi-orchestration-kit
Path
claude/miadi-session-orchestrator/skills/review-plan/SKILL.md
Versions recorded
1
Latest version
v0.1.0, committed May 23, 2026
Size
1,756 bytes
Repository stars
5
License
none declared

Full plan-review cycle: read a proposed/ file, run 5-point gap analysis, create or update the jgwill/src tracking issue, output revision prompt. Use when the user says "review the plan", "check the proposal", or when a new proposed/ file has landed and needs analysis before the implementing agent gets the next prompt.

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

# Review Plan Skill

This skill runs the full complementary-review cycle for a Miadi proposed plan file.

## Steps

1. **Locate the plan** — find the target `proposed/*.md` file (passed as argument or most recent)
2. **Read platform context** — check `/src/Miadi/app/api/` for existing routes that overlap
3. **Run gap analysis** — apply the 5-point checklist (payload, idempotency, failure path, write-back, naming)
4. **Check tracking issue** — search `jgwill/src` for an existing issue; create one if absent
5. **Output revision prompt** — paste-ready instructions for the implementing agent

## 5-Point Checklist

| # | Check | Pass condition |
|---|-------|---------------|
| 1 | `plan_content` inline | POST payload contains content, not just file path |
| 2 | Idempotency key | API deduplicates on `session_id + plan_filename` |
| 3 | Failure observability | Langfuse error trace on async failure, not just success |
| 4 | Write-back resolved | One of: return-content pattern OR explicit mount documented |
| 5 | Naming consistent | `plan_file` / `plan_filename` unified across schema + tables |

## Output contract

Always produce both:
- **Gap Report** (numbered, severity-tagged)
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add jgwill/miadi-orchestration-kit/review-plan@sha256:dcd8e1a766b6cdd4

The line at the top of this page pins the label v0.1.0, 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_fr2i4bkus5gp4ouf.svg)](https://markdownregistry.com/a/art_fr2i4bkus5gp4ouf)

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

Versions

The registry has recorded 1 version of this file, committed on May 23, 2026.

versioncommittedcommitsizeaudit
v0.1.0 latest2026-05-23 5cfcc8a 1,756 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 (1756 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

jgwill/miadi-orchestration-kit · 5 stars · license none declared · pushed 2026-10-21 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_fr2i4bkus5gp4ouf
GET https://markdownregistry.com/api/v1/resolve?ref=jgwill/miadi-orchestration-kit/review-plan
GET https://markdownregistry.com/api/v1/blob/dcd8e1a766b6cdd4265a4c79aab7aeb37c8602730140a07bef5fe42141ec2e12

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 jgwill/miadi-orchestration-kit

AGENTS.md AGENTS.md file
jgwill/miadi-orchestration-kit · AGENTS.md
git:20260905.7457baf · audit A · 5 stars
AGENTS.md@antigravity AGENTS.md file
jgwill/miadi-orchestration-kit · antigravity/AGENTS.md
git:20260607.e22b11e · audit A · 5 stars
AGENTS.md@claude AGENTS.md file
jgwill/miadi-orchestration-kit · claude/AGENTS.md
git:20261018.428e9dc · audit A · 5 stars
ava-companion SKILL.md skill
jgwill/miadi-orchestration-kit · claude/ava-companion/skills/ava-companion/SKILL.md · Be Ava, Guillaume's companion, in a Claude Code session, in an episode or not. Use when /ava is run, when Guillaume…
git:20261006.d525fcb · audit B · 5 stars
mia-episode-companion SKILL.md skill
jgwill/miadi-orchestration-kit · claude/mia-episode-companion/skills/mia-episode-companion/SKILL.md · Be Mia, William's development companion, in a Claude Code seat bound to one Chronicle episode. Use when a mia-listen…
git:20261020.10db0ba · audit B · 5 stars
screenwalk-notebook SKILL.md skill
jgwill/miadi-orchestration-kit · claude/miadi-deepdiver/skills/screenwalk-notebook/SKILL.md · Turn Miadi reviews and their screenwalk videos into a Gemini Notebook, ask it the episode's questions, generate and…
git:20261020.caa57ce · audit A · 5 stars
operator-desk SKILL.md skill
jgwill/miadi-orchestration-kit · claude/miadi-operator-desk/skills/operator-desk/SKILL.md · Answer William's questions about how the Miadi Factory works (a tool's commands, tmux and other multiplexers, which…
git:20261007.d6f124d · audit A · 5 stars
miadi-pi-network SKILL.md skill
jgwill/miadi-orchestration-kit · claude/miadi-pi-network/skills/miadi-pi-network/SKILL.md · Work with the Miadi Pi Network hub from a Claude Code session — join as a peer, list peers, send a prompt to another…
git:20260906.a175fb2 · audit B · 5 stars
AGENTS.md@claude/miadi-session-issue AGENTS.md file
jgwill/miadi-orchestration-kit · claude/miadi-session-issue/AGENTS.md
git:20261019.b144a52 · audit A · 5 stars
AGENTS.md@claude/miadi-session-observability AGENTS.md file
jgwill/miadi-orchestration-kit · claude/miadi-session-observability/AGENTS.md
git:20261021.ca1ff8d · audit A · 5 stars
session-continuity SKILL.md skill
jgwill/miadi-orchestration-kit · claude/miadi-session-observability/skills/session-continuity/SKILL.md · T1's practice: after a reboot or an exit, every terminal still knows which agent session it held, and the agents come…
v1.1.0 · audit A · 5 stars
session-fork SKILL.md skill
jgwill/miadi-orchestration-kit · claude/miadi-session-observability/skills/session-fork/SKILL.md · Branch a Claude Code session without touching it. Ask a branch of another session a question with every tool disabled…
git:20261008.7c09d63 · audit A · 5 stars

Every file in jgwill/miadi-orchestration-kit

Other files named review-plan

review-plan SKILL.md skill
tobihagemann/turbo · claude/skills/review-plan/SKILL.md · Review a plan by running internal reviews and a peer review in parallel and returning combined findings. Use when the…
git:20261008.aff1027 · audit A · 414 stars
review-plan SKILL.md skill
tobihagemann/turbo · codex/skills/review-plan/SKILL.md · Review a plan by running internal reviews and a peer review in parallel and returning combined findings. Use when the…
git:20261008.aff1027 · audit A · 414 stars
review-plan SKILL.md skill
lploc94/cross-review · skill-packs/cross-review/skills/review-plan/SKILL.md · Review/debate plans before implementation with an external reviewer model (Codex CLI by default; Claude Code or…
git:20261016.8439179 · audit A · 153 stars
review-plan SKILL.md skill
jkaloger/lazyspec · examples/spec/skills/review-plan/SKILL.md · Use when a Plan is complete and ready for review. Two-stage review -- spec contract compliance first, code quality…
git:20260309.b2e83d0 · audit A · 10 stars
review-plan SKILL.md skill
rube-de/cc-skills · plugins/council/skills/review-plan/SKILL.md · Use after writing implementation plans (superpowers:writing-plans output) or when the user says "review plan", "check…
git:20261006.6783c23 · audit A · 10 stars
review-plan SKILL.md skill
mgiovani/cc-arsenal · skills/review-plan/SKILL.md · Adversarially review an implementation plan before any code is written,
v1.0.0 · audit A · 8 stars

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