/SKILL.md
# SKILL.md 本文件定義 **SENTRY Messenger / messages-flow 重構專案** 中,AI Agent(尤其是 Codex 類型)**被允許使用、被禁止使用、以及必須具備的技能邊界**。 這不是能力清單,而是 **「可動用技能白名單」**。 --- ## 1. 技能分級模型(Agent 能做什麼) ### Level 0:讀取與取證(永遠允許) Agent 必須能熟練執行: - `rg`, `grep`, `sed`, `awk`, `nl` - `git status`, `git diff`, `git show` - 靜態閱讀程式碼 - 比對行為與文件是否一致 - 列出「有 / 沒有」的證據 > **任何改動前,先取證。沒有取證直接改碼 = 違規。** --- ### Level 1:結構性重構(允許,需明確指令) 可做的事情: - 模組切分(file split / move) - Facade / Adapter / Coordinator 抽離 - 重命名(只要語意更精準) - 將舊邏輯「包起來」但不改行為 - 新
npx skillsauth add sentry-security/sentry-messenger sentry-messengerInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
本文件定義 SENTRY Messenger / messages-flow 重構專案 中,AI Agent(尤其是 Codex 類型)被允許使用、被禁止使用、以及必須具備的技能邊界。
這不是能力清單,而是 「可動用技能白名單」。
Agent 必須能熟練執行:
rg, grep, sed, awk, nlgit status, git diff, git show任何改動前,先取證。沒有取證直接改碼 = 違規。
可做的事情:
限制:
僅在明確指示下允許,例如:
Agent 絕對禁止使用以下能力:
Agent 必須隨時知道:
一旦跨層,必須停下。
Agent 必須能維持以下長期共識:
如果遺忘,等同技能失效。
每一次輸出,Agent 都必須能:
rg 證明沒有違規在輸出前,Agent 應自問:
只要有一題是「是」,就該停下。
這個專案需要的不是聰明,而是紀律。
Agent 的價值不是「寫很多程式碼」,
而是 在極嚴格邊界內,穩定地完成指定工作。
請以此為最高指導原則。
development
Maintainer-only workflow for handling GitHub Secret Scanning alerts on OpenClaw. Use when Codex needs to triage, redact, clean up, and resolve secret leakage found in issue comments, issue bodies, PR comments, or other GitHub content.
development
Maintainer workflow for OpenClaw releases, prereleases, changelog release notes, and publish validation. Use when Codex needs to prepare or verify stable or beta release steps, align version naming, assemble release notes, check release auth requirements, or validate publish-time commands and artifacts.
development
Run, watch, debug, and extend OpenClaw QA testing with qa-lab and qa-channel. Use when Codex needs to execute the repo-backed QA suite, inspect live QA artifacts, debug failing scenarios, add new QA scenarios, or explain the OpenClaw QA workflow. Prefer the live OpenAI lane with regular openai/gpt-5.4 in fast mode; do not use gpt-5.4-pro or gpt-5.4-mini unless the user explicitly overrides that policy.
development
End-to-end Parallels smoke, upgrade, and rerun workflow for OpenClaw across macOS, Windows, and Linux guests. Use when Codex needs to run, rerun, debug, or interpret VM-based install, onboarding, gateway smoke tests, latest-release-to-main upgrade checks, fresh snapshot retests, or optional Discord roundtrip verification under Parallels.