ai-review
Run an independent adversarial correctness review against a specification
- License 许可
- MIT
- 最近更新
- 2026-07-29
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- ai-review
- description
- Run an independent adversarial correctness review against a specification
- argument-hint
- [spec-path]
- disable-model-invocation
- true
03 SKILL.md 正文
Delegate to the correctness-reviewer agent: review the current implementation against $ARGUMENTS. Determine the base reference from the current run manifest or AI_BASE_REF.
For risk R2 and above, also delegate to security-reviewer in a separate context and preserve both sets of findings verbatim.
04 同仓库更多 Skills
workflow-retrospective
Improve the durable workflow when the same agent, review, test, scope, or validation failure pattern recurs; use after incidents or repeated verifier returns.
verification
Perform final independent read-only verification of acceptance criteria, review remediation, test integrity, scope, and quality-gate evidence.
ticket-authoring
Turn a reported or observed defect into one reviewable ticket under tickets/ with reproduction, evidence, impact, and closure criteria, bound to a fix version — without fixing it or rewriting it into a specification.
technical-planning
Create a read-only implementation plan from an approved specification before code changes; use for non-trivial features, bugs, migrations, and cross-module work.
skill-governance
Audit newly installed or updated agent skills as untrusted content and propose required, optional, or denied assignments to existing agent roles. Use after staging a skills.sh installation and before promoting the skill or changing agent permissions.
security-review
Adversarially review authentication, authorization, tenant isolation, sensitive data, abuse resistance, and production reliability for a completed implementation.