Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Review Plan

ASecurity

Review an implementation plan for completeness, feasibility, dependency coverage, and risk assessment.

10 stars
0 votes
0 copies
0 views
Added 10/6/2026
testinggotestingapi

Works with

cliapi

Security Analysis

A100/100

Scanned 10/6/2026

$npx -y skills add tomzx/agents --skill review-plan --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Review Plan?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Review Plan
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/tomzx-review-plan/badge)](https://www.skillsdirectory.com/skills/tomzx-review-plan)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: review-plan
description: Review an implementation plan for completeness, feasibility, dependency coverage, and risk assessment.
---

# Review Plan

Reviews an implementation plan and reports findings across six categories: completeness, feasibility, dependencies, risk coverage, timeline realism, and reversibility.

## Prerequisites

- Apply the shared SDLC conventions in `skills/sdlc/references/shared.md`.
- If no argument is provided, locate the feature directory under `.sdlc/features/` whose frontmatter `issue` field references `$ISSUE_NUMBER`.
- `.sdlc/features/N-<slug>/plan.md` (unified) **or** `.sdlc/features/N-<slug>/plan/index.md` plus its sibling `plan/<concern>.md` files (split), or an implementation plan provided in context or as a file path
- `.sdlc/features/N-<slug>/specification.md` (optional, improves coverage analysis)

## Steps

1. **Resolve the plan.** Look for `.sdlc/features/N-<slug>/plan.md` first; if absent, look for `.sdlc/features/N-<slug>/plan/index.md` and read it together with every `plan/<concern>.md` it lists. Otherwise read from context or as a file path. Treat the whole plan set (index + concern files) as the unit under review.
2. Cross-reference against the specification or requirements if available.
3. Run the deterministic checker when possible: render each `mermaid` block with `mmdc` (or `npx -y @mermaid-js/mermaid-cli`) when available. A tool that is not installed is skipped (never blocks); a render failure is a blocking finding under Dependencies or Timeline Realism.
4. Identify issues in each category below. For a split plan, also check that `plan/index.md` aggregates milestones, cross-concern dependencies, risks, and timeline consistently with the concern files.
5. Report findings. Omit any category that has no findings.
6. Write the findings to `.sdlc/features/N-<slug>/review-plan.md` with frontmatter `artifact: plan`, `verdict` (`approved` if there are no blocking findings, `changes-requested` if the author must address findings, `rejected` for a fundamental flaw), and `reviewed_at: <ISO date>`, and the findings as the body, per `skills/sdlc/references/shared.md`. Record any unresolved open questions in the findings body. For any question that carries meaningful risk to the implementation, also invoke `/create-assumption` to record it formally.

## Review Checklist

### Completeness
- Does the plan cover all requirements and spec deliverables?
- Are all phases clearly defined with success criteria?
- Are setup, deployment, and rollout steps included?

### Feasibility
- Are effort estimates realistic for the described work?
- Does the plan account for ramp-up, reviews, and integration work?
- Are milestones achievable within the stated constraints?

### Dependencies
- Are all internal and external dependencies identified?
- Does the phase-dependency flowchart match the per-phase `Depends on:` fields (no edge missing, no edge invented)?
- Are critical-path dependencies clearly marked?
- Is there a contingency for delayed or unavailable dependencies?

### Risk Coverage
- Are the most significant risks captured in the risk register?
- Does each risk have a concrete mitigation strategy?
- Are there single points of failure not mentioned as risks?

### Timeline Realism
- Is the timeline consistent with the effort estimates (gantt durations vs. phase effort)?
- When a gantt is present, do its task dependencies match the phase-dependency flowchart?
- Are there parallel tracks that could shorten total duration?
- Are buffer periods included for testing and review?

### Reversibility
- Can we undo this cleanly once implemented, or does the plan create one-way-door commitments?
- Does the plan include a rollback path for each phase (migrations, deployments, config)?
- Are irreversible steps (destructive migrations, deletions, public API removals) flagged and ordered safely?

## Output Format

```markdown
## Completeness

<Findings or "No issues found.">

## Feasibility

<Findings or "No issues found.">

## Dependencies

<Findings or "No issues found.">

## Risk Coverage

<Findings or "No issues found.">

## Timeline Realism

<Findings or "No issues found.">

## Reversibility

<Findings or "No issues found.">
```

## Outcome

If `$OUTCOME_YAML` is set, emit your verdict there per `skills/sdlc/references/shared.md`:

| Verdict | When |
|---|---|
| `approved` | No blocking findings; the subject passes review |
| `changes-requested` | Findings the author must address before it passes |
| `rejected` | Fundamental flaw requiring rework or stopping |

In the same emission, list the findings file under `artifacts:` (`.sdlc/features/N-<slug>/review-plan.md`).

## Example Usage

**Scenario 1: Missing rollout step**
Plan ends at "integration testing complete" with no deployment or rollout phase.
Report under Completeness.

**Scenario 2: Underestimated effort**
Phase 2 (API + auth) is estimated at 1 day for a spec that describes 8 endpoints with complex permission logic.
Report under Feasibility.

**Scenario 3: Unmitigated critical dependency**
Plan depends on a third-party API but lists no spike or contingency if that API is unavailable.
Report under Risk Coverage.

## Next Step

Once the findings verdict is `approved`, run `/publish-plan` to commit the plan and open a draft PR for author sign-off, then continue with `/create-tasks-decomposition`.

## Useful Commands Reference

| Command | Description |
|---|---|
| `mmdc -i <diagram.mmd>` or `npx -y @mermaid-js/mermaid-cli` | Best-effort Mermaid render check; failure is a blocking finding |

Attribution

tomzxtomzx
View sourceSee grades on GitHubMore from tomzx →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Screen Reader Testing

Practical guide to testing web applications with screen readers for comprehensive accessibility validation.

401991 votes

Tdd Workflow

在编写新功能、修复错误或重构代码时使用此技能。强制执行测试驱动开发,包含单元测试、集成测试和端到端测试,覆盖率超过80%。

2456590 votes

Eval Harness

克劳德代码会话的正式评估框架,实施评估驱动开发(EDD)原则

2456590 votes

Python Testing

使用pytest、TDD方法、夹具、模拟、参数化和覆盖率要求的Python测试策略。

2456590 votes

Django Tdd

Django测试策略,包括pytest-django、TDD方法论、factory_boy、模拟、覆盖率以及测试Django REST Framework API。

2456590 votes
View all in testing →