experiment-handoff SKILL.md skillA
experiment-handoff from ninjasln-labs/agent-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add ninjasln-labs/agent-skills/experiment-handoff@v1.1.0Pins v1.1.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- ninjasln-labs/agent-skills
- Path
experiment-handoff/SKILL.md- Versions recorded
- 3
- Latest version
- v1.1.0, committed Sep 29, 2026
- First version recorded
- Sep 18, 2026
- Size
- 9,780 bytes
- Repository stars
- 3
- License
- none declared
Experiment handoff for mid-project experiments and spikes. Isolates a trial in a git worktree (default), an in-place branch, or a project copy; records a small experiment doc (.experiments/<slug>.md plus a generated index); supports handing off to another agent/session; and on close merges the validated change back into the project (full or partial) or discards it, then cleans up the sandbox. Auto-detects VCS and the isolation strategy, and records the base revision. This skill is mounted but…
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
# 实验性交接（Experiment Handoff） ## 角色 你是**实验性交接**的执行者。项目进行到中途要试功能/跑测试时：**隔离出一个沙箱**（worktree/branch/copy），写一份小实验文档交接给下一个 agent/session，实验有结论后**把验证过的改动合并回主项目或丢弃**，并清理沙箱。 与 `project-handoff`（项目状态交接）并列：本技能只管**单个实验**的隔离与回收，**自足**——不依赖其它技能的脚本或文件。 ## 何时使用（**已挂载 · 仅用户手动 `/experiment-handoff`**） 本技能**已挂载**（`~/.agents/skills/experiment-handoff`，用户可用 `/experiment-handoff` 调用），但 **agent 不得自主触发**——只有用户显式调用时才执行： - **触发方式**：用户键入 `/experiment-handoff`（或明确点名该技能）；**仅手动**。 - 三段手动：① 用户 `/invoke` 本技能 ② 用户手动把会话交给另一个 agent ③ 用户手动宣告实验结束。 - **其余全自动**：探测 VCS、选隔离策略、建隔离、写文档/索引、记基线、合并回主、清理。 ## 硬约束 1. **隔离优先**——实验改动**不得污染主工作树**；一律先进沙箱。 2. **结论驱动合并**——先写 `结论/反馈`，再决定合并范围（全量/部分/丢弃）；不得先合并后补结论。 3. **可回滚**——合并前记基线（commit/快照 hash）；合并后跑验证，不通过即回滚。 4. **必清理**——收束必删沙箱（worktree/branch/copy）与临时分支；不留残留。 5. **防膨胀**——实验文档小（≤~600 tokens）；收束即迁 `archive/`；活跃实验 ≤10 条（超出先归档）。 6. **脱敏**——文档不含 API Key/密码/PII。 ## 隔离策略（agent 自动选） | 项目状态 | 策略 | 落地 | |---|---|---| | git 仓、`git worktree` 可用、主树干净 | **worktree（默认）** | **兄弟目录** `../<proj>-exp-<slug>` + 分支 `exp/<slug>`（不嵌在主树内）| | git 仓、主树有未提交改动 | 先 commit/stash → worktree | worktree **看不到**未提交改动 | | git 仓、小改动就地 | **branch**（`--mode branch`）| 直接切 `exp/<slug>` | …
Read the whole file at its exact version.
How to install
mdr add ninjasln-labs/agent-skills/experiment-handoff@sha256:c9c09e1681b98087The line at the top of this page pins the label v1.1.0, 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_ixduwcyplfawiw5u)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 3 versions of this file, between Sep 18, 2026 and Sep 29, 2026, about one every 6 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.1.0 latest | 2026-09-29 | 0febb7a | 9,780 B | A | view · diff |
| v1.0.4 | 2026-09-22 | 75c75c0 | 8,451 B | A | view · diff |
| v1.0.2 | 2026-09-18 | cbc6719 | 8,493 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 (9780 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
ninjasln-labs/agent-skills · 3 stars · license none declared · pushed 2026-10-05 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ixduwcyplfawiw5u GET https://markdownregistry.com/api/v1/resolve?ref=ninjasln-labs/agent-skills/experiment-handoff GET https://markdownregistry.com/api/v1/blob/c9c09e1681b980871ae42cdc58ea872ecb99a2f6c046930096fb5d89b91c73bf
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.