菜单
Run general-review and deep-code-review together as one consolidated review. Use when the user asks for a full code review, a combined general and deep review, or a comprehensive review of code, a diff, branch, or pull request.
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
Clone/checkout an ai-dynamo/dynamo PR, build it (maturin + editable Python), bring up etcd/NATS, run the end-to-end aggregated server via the repo's examples/backends/sglang/launch/agg.sh, drive load with uvx aiperf, verify the change empirically, then post a scoped evidence-backed GitHub review. Use when asked to test/try/review a Dynamo PR (e.g. "test ai-dynamo/dynamo#10254", "review this dynamo PR").
First-pass workflow for GitHub PR comments and review threads: pull feedback into a simple actionable markdown table before deciding what to fix. Use before github:gh-address-comments when the user asks to review, triage, address, fix, summarize, classify, ledger, or selectively handle PR comments/review feedback.
Check out an SGLang PR in a throwaway worktree, build it in a fresh venv, run it with sglang.launch_server, drive load with uvx aiperf, verify the change empirically, then post a scoped evidence-backed GitHub review. Use when asked to test/try/review an sglang PR (e.g. "test sgl-project/sglang#12345", "review this sglang PR").
Generate a bi-weekly/monthly engineering status update ("T5T") for a date range by mining the ~/memory work-vault and cross-referencing GitHub PR activity via gh. First emit a full evidence-backed mega dump of active work, then a separately labeled recommended T5T for approval. Use when asked to "write my T5T", "status update", "what did I do from X to Y", "biweekly update", "T5T mega dump", or "T5T for approval".
Create or update GitHub pull request descriptions without deleting existing content or adding long narrative slop. Use when the user asks to write, refresh, clean up, standardize, or update a PR body/description for a current branch or GitHub PR.
MANUAL-ONLY. Use only when the user explicitly invokes `mh-draw-the-owl` or asks to use the draw-the-owl workflow. Never auto-invoke it based on feature or diff size. Explore a feature end to end, then decompose oversized work into atomic, incremental, reviewable tasks.
| name | full-code-review |
| description | Run general-review and deep-code-review together as one consolidated review. Use when the user asks for a full code review, a combined general and deep review, or a comprehensive review of code, a diff, branch, or pull request. |
Establish this bar before invoking either child skill: include a finding only when it gives a concrete, in-scope failure case — precondition/input, affected code path, and outcome (wrong behavior, crash, data loss, security-boundary violation, or measurable regression). Prefer a reproduction; otherwise trace the path and show why its precondition is supported.
For example, “A zero-length batch reaches this division and returns 500” is a finding. “A future caller might pass an undocumented shape” is not one without an in-scope caller or contract. Skip speculative edge cases, style preferences, unsupported inputs, and alternative designs; do not recommend defensive code solely for them. Retain findings about trust-boundary validation, data safety, or security.
Run both existing review skills against the same target:
../general-review/SKILL.md completely, applying the finding threshold above.../deep-code-review/SKILL.md completely, applying the finding threshold above.This sets the admission bar for the consolidated report; do not copy, weaken, or replace either child skill's rubric.