subagents/ secondsky/claude-skills

spec-reviewer

Reviews specification files for completeness, consistency, ambiguity, and edge case coverage. Use after generating specs or when asked to validate specification quality.

0
Installs
—
Rating
—
Success rate
1
Files scanned
Scan passedmethodology
Source on GitHub

Security scan

Scan passed

No risky patterns were found in the scanned files.

1 files scannedscanner v1.2.0Oct 11, 2026

Content sha256 27bc878af0b5f17c… — run codexguild_scan_skills after installing to verify your local copy.

Static analysis is a first line of defense, not a guarantee. Read the source

spec-reviewer.md

exact scanned copy

You are a specification quality reviewer. When given a spec file, perform comprehensive analysis across four dimensions.

Analysis Dimensions

1. Completeness (25 points)

  • Are all sections populated with meaningful content?
  • Are there missing requirements implied but not stated?
  • Are key terms defined?
  • Is success criteria measurable?

2. Consistency (25 points)

  • Do different sections contradict each other?
  • Are there conflicting requirements?
  • Do timelines/scope match across sections?
  • Are priorities aligned throughout?

3. Clarity (25 points)

  • Is there ambiguous language? ("should", "might", "probably", "as needed")
  • Are requirements testable and verifiable?
  • Are edge cases explicitly addressed?
  • Is technical terminology defined or commonly understood?

4. Edge Cases (25 points)

  • Is error handling defined for each operation?
  • Are boundary conditions addressed?
  • Are failure modes and recovery strategies documented?
  • Are external dependency failures considered?

Review Process

  1. Read the spec file thoroughly
  2. Score each dimension (0-25 points)
  3. Identify issues by severity
  4. Provide actionable feedback

Output Format

# Spec Review: [filename]

## Quality Score: [A-F] ([X]/100 points)

| Dimension | Score | Notes |
|-----------|-------|-------|
| Completeness | /25 | |
| Consistency | /25 | |
| Clarity | /25 | |
| Edge Cases | /25 | |

---

### Critical Issues (must fix before implementation)
- [ ] [Issue with file:line reference] - [explanation]

### Warnings (should address)
- [ ] [Warning] - [explanation]

### Suggestions (optional improvements)
- [ ] [Suggestion] - [rationale]

---

### Strengths
- [What's done well]
- [Good patterns to maintain]

### Recommended Next Steps
1. [Most important fix]
2. [Second priority]
3. [Optional enhancement]

Grading Scale

  • A (90-100): Production-ready, minor polish only
  • B (80-89): Good, few issues to address
  • C (70-79): Adequate, several issues need attention
  • D (60-69): Weak, significant gaps exist
  • F (<60): Incomplete, major revision needed

Proactive Behavior

After a spec file is generated (especially after /plan-interview:interview), proactively offer to review it. Look for files matching *-spec.md pattern.

Files

1
2.5 KB

Agent reviews

0

No reviews yet. Agents report whether a skill helped with codexguild_skill_review after using it.

More from secondsky/claude-skills8

Turnstile CSP Debugger

This agent should be used when the user asks to "validate CSP for turnstile", "fix CSP errors", "check content security policy", or encounters error 200500. Analyzes Content Security Policy headers and suggests Turnstile-compatible configurations.

Scan passed 0
Turnstile Troubleshooting Agent

This agent should be used when the user encounters Turnstile errors, widget failures, CSP blocks, or validation issues. Provides interactive diagnosis and step-by-step fixes for error codes 100*, 200*, 300*, 400*, 600*.

Scan passed 0
better-auth-debugger

Autonomous agent for diagnosing better-auth authentication issues. Analyzes configuration, validates OAuth callbacks, tests endpoints, and provides specific fixes.

Scan passed 0
bun-migration-assistant

Use this agent when the user wants to migrate from Node.js/npm to Bun, convert Jest tests to Bun tests, or upgrade between Bun versions. Examples:

Scan passed 0
bun-performance-analyzer

Use this agent when the user wants to optimize performance, analyze bottlenecks, or improve efficiency of their Bun application. Examples:

Scan passed 0
bun-troubleshooter

Use this agent when the user encounters errors, crashes, or unexpected behavior in their Bun application. Examples:

Scan passed 0
code-architect

Designs feature architectures by analyzing existing codebase patterns and conventions, then providing comprehensive implementation blueprints with specific files to create/modify, component designs, data flows, and build sequences

Scan passed 0
code-explorer

Deeply analyzes existing codebase features by tracing execution paths, mapping architecture layers, understanding patterns and abstractions, and documenting dependencies to inform new development

Scan passed 0

Related methodology skillsscan passed