菜单
Use when generated code, plans, tests, prompts or architecture need critique, repair and verification before completion; especially for coding tasks requiring self-review, test-driven repair or quality gates.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Use when reviewing code before merge to assess correctness, tests, maintainability, security and user impact.
Use when reviewing plans, recommendations, prioritisation, risk registers, retrospectives or agent outputs for judgement distortion from cognitive bias — not for checking whether an argument's premises validly support its conclusion.
Use when evaluating whether premises in plans, ADRs, reviews, security justifications or agent recommendations validly support their conclusions — for logical fallacies, not judgement distortion from cognitive bias.
Use when a coding agent needs robust problem solving, explicit decomposition, alternative-path exploration, program-aided reasoning, ReAct loops, or self-correction.
Identifies risks, scores likelihood and impact, selects treatment, assigns owners and review cadence. Use when building or updating a risk register, treating agent autonomy risks, or deciding mitigate, transfer, accept or avoid.
Identifies assets, trust boundaries, threats and mitigations for systems and agents. Use when designing security-sensitive features, reviewing attack surface, or planning abuse-case tests.
| name | reflection-and-verification |
| description | Use when generated code, plans, tests, prompts or architecture need critique, repair and verification before completion; especially for coding tasks requiring self-review, test-driven repair or quality gates. |
Use this skill after an initial implementation, plan or generated artefact exists and quality matters. Apply it to code generation, debugging, planning, documentation, prompts, tests and architecture proposals.
Reflection must not replace deterministic verification. Run tests, linters, type checks and static analysis wherever available.
Critique and repair artefacts using deterministic checks first, then bounded review loops.
tdd-practice — executable verification firstcode-review-and-quality — human or agent review loopcognitive-bias-review — judgement distortion after checks passlogical-fallacy-review — invalid premises-to-conclusion chainsapply-laws-of-ai — safety gates before claiming completion