Review Plan logo

Review Plan

Organization
DasDigitaleMomentum
review-plan

Independent review of a plan against its requirements, scope, and completeness. Produces a structured review with severity-rated findings. Use after create-plan to validate quality before execution.

Overview

PublisherDasDigitaleMomentum
Repositoryopencode-processing-skills
Skill namereview-plan
Stars
61
Forks
3
Bundled files
2
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by DasDigitaleMomentum on GitHub. Read the source before you install it.

Installation

Install the Review Plan AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/DasDigitaleMomentum/opencode-processing-skills/tree/main/skills/review-plan
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/DasDigitaleMomentum/opencode-processing-skills.git /tmp/opencode-processing-skills
mkdir -p .claude/skills
cp -r /tmp/opencode-processing-skills/skills/review-plan .claude/skills/review-plan
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Review Plan in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Review Plan on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Review Plan is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Skill: Review Plan

This skill provides an independent quality gate for plans created via create-plan.

A fresh reviewer (with no authoring context) evaluates the plan against structured criteria. The review is persisted as a plan artifact for traceability.


When to Use

Use this skill when:

  • A plan has been created via create-plan and you want to validate it before proceeding.
  • You want a second opinion on plan quality (scope clarity, DoD, testing strategy, etc.).
  • The user explicitly requests a plan review.

Do not use this skill to:

  • Review implementation plans (use review-implementation-plan).
  • Review completed implementations (use review-implementation).
  • Fix or rewrite the plan (the reviewer only reports findings; the primary decides how to act).

Review Focus

The default priority is the smallest complete scope: confirm that requested outcomes are covered and that no phase or material deliverable is unauthorized, unnecessary, or needlessly separate. Inspect the relevant plan elements, but record only evidence-backed exceptions. The primary may add a focus via {{focus}}.

Review posture

Detect existing gold-plating without becoming an adversarial reviewer. A scope-reduction finding must identify a concrete planned item and show missing authorization, missing present necessity, or a smaller path that remains complete: the requested behavior must still work, affected real paths must still integrate, and applicable existing invariants must be preserved. Scope discipline is not permission to omit necessary work. Do not invent requirements, ideal architectures, hardening, infrastructure, or findings. Zero findings remains valid.

DoD wording, testing, references, documentation, and other formal criteria are not checklist obligations. Report them only when a concrete defect would block or misdirect execution.


Execution Model

Roles

  • Primary (maintainer)

    • Invokes the review skill.
    • Delegates the review to delegate-strong (default) or general (for same-model perspective).
    • Receives the review summary and decides on follow-up actions.
    • Updates the plan via update-plan if findings require changes.
  • Subagent (delegate-strong / general)

    • Reads plan + phase documents with no prior context (fresh eyes).
    • Applies this skill's exception-based review focus.
    • Writes the review artifact to plans/<name>/reviews/plan-review.md.

Why delegate-strong (not doc-explorer)

The reviewer must approach the plan without authoring context — fresh eyes catch what familiarity misses. delegate-strong provides the judgment depth needed to evaluate scope, consistency, and completeness. Writing docs or selected plan artifacts belongs to the relevant authoring workflow, not the review workflow.

Routing Matrix (Who does what)

  • Writes: plans/<name>/reviews/plan-review.md
  • Does NOT write: plans/<name>/plan.md, plans/<name>/phases/**, or any other plan artifact.
  • Primary: owns the decision of whether to act on findings.
  • delegate-strong/general: performs the review and writes the review artifact.

Workflow

1) Prepare references

Primary gathers:

  • Review focus from the delegation prompt
  • plans/<name>/plan.md
  • plans/<name>/phases/ (all phase docs)

2) Delegate

Primary delegates to delegate-strong (or general) using tpl-review-plan-prompt.md.

Provide:

  • Plan path
  • Phases directory path
  • Review output path: plans/<name>/reviews/plan-review.md
  • Review focus (freetext — what to prioritize)

3) Receive summary

Subagent returns:

  • Overall verdict (Ready / Needs Revision / Major Gaps)
  • Reduction required (Yes / No)
  • Finding count by severity and the top 3 actionable findings
  • Required next action

4) Act on findings

Primary decides:

  • Ready: Proceed to author-and-verify-implementation-plan only when reduction is not required and no Critical/Major findings remain.
  • Needs Revision: Do not proceed. Accept or explicitly reject each blocking finding. Apply accepted plan reductions once through the review-remediation mode of update-plan.
  • Major Gaps: Stop and discuss the missing intent or authorization with the user before restructuring the plan.

Plans remain conversation-owned by the Primary. Resume the same reviewer task_id only for clarification; apply accepted changes through update-plan, not reviewer edits through review-fix. The remediation digest closes that pass. Do not automatically re-review or continue until zero findings. Escalate materially changed scope or new risk/uncertainty to the Primary; a fresh review requires an explicit Primary or user decision.


Output Contract

The review artifact plans/<name>/reviews/plan-review.md MUST:

  • Follow the canonical template headings and frontmatter keys.
  • Include a clear assessment with verdict, reduction flag, and brief reasoning.
  • Report only exceptions; do not reproduce coverage matrices or certify clean phases/deliverables individually.
  • Give every finding a stable ID, severity, evidence, and concrete action.
  • State No findings when the review finds no material problem.

Verdict rules:

  • Ready requires Reduction Required: No and zero Critical/Major findings.
  • Any executable phase or deliverable without clear authorization or present necessity is at least Major and requires Needs Revision.
  • Use Major Gaps when missing intent or authorization prevents a defensible reduction decision and needs user input.

Rules

  • The reviewer must approach the plan without prior context. Do not include plan content in the delegation prompt — the reviewer reads it themselves.
  • Findings are advisory decisions, not automatic edits. The primary must accept or explicitly reject blocking findings before progression.
  • Do not rewrite or modify the plan during review — only produce the review artifact.
  • Retain the reviewer task_id until finding clarification is complete.
  • Ensure the reviews/ directory exists before delegating (create if needed).
  • Zero findings is valid. Flag only concrete gaps or unnecessary planned work; do not invent requirements, policy, infrastructure, or replacement scope.
  • Pay particular attention to foundations, shared abstractions, cleanup, generic infrastructure, and future-phase preparation, but report only concrete unnecessary work.
  • Once a review is invoked, Reduction Required: Yes or unresolved Critical/Major findings block progression until the primary remediates or explicitly rejects them with rationale.
  • One review plus one accepted remediation pass is the default bound. Never start an automatic review/fix/re-review loop.

Templates

  • tpl-plan-review.md — Canonical compact review output
  • tpl-review-plan-prompt.md — Primary → reviewer delegation prompt

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Review Plan AI skill do?

Independent review of a plan against its requirements, scope, and completeness. Produces a structured review with severity-rated findings. Use after create-plan to validate quality before execution.

Why use Review Plan on TypingMind?

Because you install it once and use it with any model. Review Plan is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Review Plan in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/DasDigitaleMomentum/opencode-processing-skills/tree/main/skills/review-plan. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Review Plan?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Review Plan?

As many as you like. As long as a model supports skills, you can use Review Plan with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Review Plan AI skill free?

Yes. It is published on GitHub by DasDigitaleMomentum under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇