do-something SKILL.md skillA
do-something from hanzhangzzz/agent-skills-zh is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add hanzhangzzz/agent-skills-zh/do-something@git:20261028.bd6709dPins git:20261028.bd6709d in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- hanzhangzzz/agent-skills-zh
- Path
do-something/SKILL.md- Versions recorded
- 8
- Latest version
- git:20261028.bd6709d, committed Oct 28, 2026
- First version recorded
- Sep 2, 2026
- Size
- 13,580 bytes
- Repository stars
- 1
- License
- MIT
Autonomously push the current project forward: answer feedback first, select the highest-value task supported by real evidence, finish and verify a durable outcome, or explicitly return NO-OP when nothing valuable can truly be completed. Every run continues on one do/main branch with bounded DO.md state; optional MR mode pairs with ci-review's separate value and execution verdicts before auto-merge. Built for unattended cron/loop runs and manual triggers. Use when the user says /do-something…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# do-something 你醒来了。没有人给你任务。眼前只有这个项目。做点什么。 ## 唯一原则 每次运行最多交付**一件事**：此刻对项目价值最高、有事实支撑、且本次能真正完成并验证的事。 没有任何候选同时满足价值与完成条件，就返回 **NO-OP**；不制造提交来证明循环还活着。 有证据的尝试允许失败，但无价值的产出不是进展。隔离分支降低试错成本，不降低进入 main 的标准。 一件事不必是代码：一份尖锐的方案评审、一次竞品调研、一个重构提案、一篇文章的初稿， 都算——只要它有完整产出、可被人类 review。 ## 续做优先于新开 推进是累积的：每次运行先站上上一次的肩膀，再决定往哪走。 1. `do/main` 分支已存在 → 切过去工作（工作区脏则 `git worktree add`，不碰用户现场）， 先读 DO.md 的目的、约束、当前状态和开放风险：上一件事没做完或有明显的下一步，就续着做深； 否则在同一分支上判断新的一件事。 唯一例外：若只有 DO.md 的当前状态是上轮 NO-OP 留下的本 skill 自有改动，直接沿用，不另建 worktree。 2. `do/main` 不存在（首次运行，或人类已收割/否决上一轮）→ 从默认分支最新处新建。 3. 非 git 目录 → 固定用 `do/` 子目录承担同样角色，DO.md 放在其中，不改动目录内既有文件。 续做前比较 DO.md 的证据指纹。HEAD、失败 checks、未解决 issue/MR、`feedback_seen` 之后的新评论、用户约束或开放风险有变化， 就重新红队追问："目的还成立吗？新证据改变了最高价值任务吗？" 证据没变化且上轮已经判定无合格候选，快速 NO-OP。 绝不合并、绝不改写历史；默认也绝不 push（MR 模式见下节，只推 `do/main`）。 人类合并 `do/main` 即收割，删除即否决——这是收尾的唯一方式。 仅当用户以 `/do-something direct` 触发、或 DO.md 约束写明"允许直改"时，才在当前分支直接修改（仍独立 commit）。 ## 三层判断 从上往下落，落在哪层就做哪层： **第一层：有明确待办。** 项目里有 TODO、issue、里程碑、"下一步"、未完成的清单。 不挑最容易的，挑最能推进项目目的的那一件，做完闭环。 **第二层：有目的，无待办（或待办与目的冲突）。** README、CLAUDE.md、代码本身透露了这个项目为什么存在。从那个最本真的目的出发问： "如果今天只能做一件事，让项目更接近它存在的理由，是哪件？" 旁征博引——你见过无数同类项目的生与死，用你的全部世界知识判断，不要只在项目内的文档里打转。 …
Read the whole file at its exact version.
How to install
mdr add hanzhangzzz/agent-skills-zh/do-something@sha256:a1f8789e646d5d9eThe line at the top of this page pins the label git:20261028.bd6709d, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_bxw7gsdmdzuxp6an)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 8 versions of this file, between Sep 2, 2026 and Oct 28, 2026, about one every 8 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261028.bd6709d latest | 2026-10-28 | bd6709d | 13,580 B | A | view · diff |
| git:20261028.7206195 | 2026-10-28 | 7206195 | 12,623 B | A | view · diff |
| git:20260922.c0f20e5 | 2026-09-22 | c0f20e5 | 12,283 B | A | view · diff |
| git:20260904.a90a8bf | 2026-09-04 | a90a8bf | 11,371 B | A | view · diff |
| git:20260904.31a353b | 2026-09-04 | 31a353b | 9,546 B | A | view · diff |
| git:20260903.cb78194 | 2026-09-03 | cb78194 | 9,072 B | A | view · diff |
| git:20260903.ba8990e | 2026-09-03 | ba8990e | 8,616 B | A | view · diff |
| git:20260902.5ded76a | 2026-09-02 | 5ded76a | 8,032 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (13580 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
hanzhangzzz/agent-skills-zh · 1 stars · license MIT · pushed 2026-10-29 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_bxw7gsdmdzuxp6an GET https://markdownregistry.com/api/v1/resolve?ref=hanzhangzzz/agent-skills-zh/do-something GET https://markdownregistry.com/api/v1/blob/a1f8789e646d5d9e03083c0cd6b5e28e930066511c0ad8b81b413c0df41f0d30
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.