Index of every page on this site: llms.txt
All skills
cat-xierluo avatar

/self-evolve

@5fb69a0
Run it yourself

扫描本机 Claude Code、Codex、WorkBuddy、CodeBuddy、ZCode 等 Agent 会话,保留初始化和增量处理记录,低成本初筛后由当前 Agent 提炼经验、迭代与 Skill 沉淀建议,生成可独立打开的 HTML 报告。也用于复盘当前对话、接续每周沉淀或检查扫描覆盖。无需单独配置模型 API Key;不自动应用建议或安装 Skill。

Use this Skill: https://skilld.dev/gh/cat-xierluo/legal-skills/self-evolve

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

references06-review-workflow.md

≈682 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Review Inbox 工作流

目标

把“机器发现值得关注”与“用户决定采用”明确分开。任何自动化阶段都不得代替人工决定。

数据流

session summary / cluster
  → privacy gate
  ├─ fail → review/quarantine(仅规则、计数、哈希)
  └─ pass → review/inbox + artifact hash
               ↓
          machine proposal
               ↓
       localhost human decision
               ↓
       applied → verified outcome

审阅顺序

  1. 检查隐私状态必须为 passed,并核对产物哈希。
  2. 检查目标 Skill 当前版本与 proposal 目标版本。
  3. 检查是否已被现有功能覆盖,是否只是同修订重复证据。
  4. 逐条审查 change points,必要时选择部分接受。
  5. 记录原因;拒绝和部分接受必须给出可理解理由。
  6. 人工修改目标资产并提交后,登记 commit hash。
  7. 用真实或 synthetic 场景复验,登记 verified、failed 或 inconclusive。

人工决定

状态 含义
pending 尚未作出人工判断
accepted 接受当前修订的全部 change points
partially_accepted 只接受明确列出的部分 change points
rejected 当前修订不采用
observe 证据不足,继续积累但不实施

人工决定通过 localhost 面板或显式 CLI 追加写入,并同时绑定 proposal revision_hash、当前唯一 review/inbox/ 逻辑路径与产物哈希。Deep proposal 产物先按内容寻址并 no-clobber 发布。接受或部分接受时,服务端必须通过目录文件描述符无符号链接地读取常规文件、现场核验 SHA-256,并把已核验字节固化到 review/archive/proposal-artifacts/ 的 revision-bound no-clobber 快照;人工事件追加保存原路径和快照路径。缺失、篡改、多路径、路径逃逸或符号链接一律拒绝。只允许对 inventory 中唯一解析且版本/内容状态明确的目标执行接受或部分接受;路径、内容或其他修订输入变化后必须重新审阅。机器后续 upsert 可以补充证据或改变机器处置,但不能覆盖人工事件;applied 验证决定快照,不依赖随后可能变化的 Inbox 文件。

安全边界

  • 面板只绑定 loopback,并要求 nonce;
  • 面板不修改外部 Cron 的启停或时间表;
  • Review Inbox 不展示原始 transcript;
  • quarantine 不保留命中原文;
  • 不从 Markdown 勾选框推断规范状态;
  • 不允许机器身份写入 human decision。
  • JSONL 事件截断、坏行、重复事件 ID、冲突终态或非法生命周期顺序一律失败关闭,不用“跳过坏行”伪造健康状态。

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

1 warning18d3 checks · Risk SAFE
  • Gen Agent Trust Hub18d

    The skill is a tool for analyzing local AI agent session history to suggest improvements. It naturally requires access to local logs and performs local script execution, but it includes robust privacy gating and instructions to mitigate risks from untrusted data.

  • Socket18d

    No alerts

  • Snyk18d

    Risk: MEDIUM · 1 issue

Signed by skilld at 5fb69a0. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated 4 weeks ago
Other metadata
metadata
{
  "version": "1.28.1",
  "homepage": "https://github.com/cat-xierluo/legal-skills",
  "author": "杨卫薪律师(微信ywxlaw)"
}

README badge

README badge for cat-xierluo/legal-skills/self-evolve