ai-spec-review
Architectural and engineering design review tool for specifications.
Install
mkdir -p .claude/skills/ai-spec-review && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/10081" && unzip -o skill.zip -d .claude/skills/ai-spec-review && rm skill.zipInstalls to .claude/skills/ai-spec-review
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Review a markdown specification across business logic, architecture, performance, security, testing, DevOps/CI/CD, dependencies, standards, UX, documentation, code quality, and maintainability. Generates a structured review, risk register, test plan, implementation tasks, and dimension scores (0–10).Key capabilities
- →Review markdown specifications
- →Generate risk registers
- →Create test plans
- →Score engineering dimensions
- →Identify implementation tasks
How it works
The skill parses a markdown specification and evaluates it against multiple engineering dimensions, producing a structured YAML report with risks, issues, and a test plan.
Inputs & outputs
When to use ai-spec-review
- →Reviewing architectural designs
- →Identifying security risks in specs
- →Preparing implementation plans
About ai-spec-review
Critically assesses technical specs by scoring dimensions like security, maintainability, and DevOps. Generates a risk register and actionable implementation tasks.
Review a markdown specification across business logic, architecture, performance, security, testing, DevOps/CI/CD, dependencies, standards, UX, documentation, code quality, and maintainability. Generates a structured review, risk register, test plan, implementation tasks, and dimension scores (0–10)
When not to use it
- →Summarizing specs without critical review
Limitations
- →Cannot assess dimensions not present in the specification
How it compares
This skill performs a critical design readiness review rather than a simple summary, identifying risks and gaps before implementation.
Compared to similar skills
ai-spec-review side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| ai-spec-review (this skill) | 0 | 2mo | Review | Advanced |
| ck:predict | 0 | 3mo | No flags | Intermediate |
| agent-v3-security-architect | 3 | 6mo | Review | Advanced |
| pair-capability-verify-adoption | 0 | 5mo | No flags | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
ck:predict
lengo0951
5 expert personas debate proposed changes before implementation. Catches architectural, security, performance, and UX issues early. Use before major features or risky changes.
agent-v3-security-architect
ruvnet
Agent skill for v3-security-architect - invoke with $agent-v3-security-architect
pair-capability-verify-adoption
foomakers
Checks code and configuration against project adoption files for a given scope. Detection-only: returns conformity/non-conformity list per area without resolving issues. Caller decides resolution. Invocable independently or composed by /pair-process-review and /pair-process-implement.
golden-principles
rjmurillo
Scan repository for golden principle violations with agent-readable remediation. Enforces GP-001 through GP-008 from .agents/governance/golden-principles.md. Use when auditing compliance, preparing PRs, or running garbage collection scans.
audit-workflow
FlorianDrevet
Use when: code audit, technical audit, security audit, performance audit, scalability audit, database audit, audit markdown, GitHub audit issues, findings reconciliation, labels sync.
harness-boundary
zkp442910864
Harness 工程边界约束与变更评估。Use when: 评估代码变更影响范围、确认安全边界、检查工程规范合规性、审查变更风险等级。