stage-gate SKILL.md skillA
stage-gate 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/stage-gate@v1.1.1Pins v1.1.1 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
stage-gate/SKILL.md- Versions recorded
- 4
- Latest version
- v1.1.1, committed Sep 29, 2026
- First version recorded
- Aug 16, 2026
- Size
- 9,634 bytes
- Repository stars
- 3
- License
- none declared
Run a stage-completion gate for staged delivery (spec-kit): read the stage spec's DoD assertions and execute each one — unit tests, dual tsc, interaction tests, behavioral acceptance, coverage matrix, open audit items, push state — reporting PASS/FAIL per assertion with fresh command evidence. Verifies only, never fixes. Use when a stage is claimed complete or the user asks to run the stage gate. NOT for: verifying one completion claim in isolation, or carrying out a written plan task by task.
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
# Stage Gate（阶段门禁执行）
## 定位
NeonForge 阶段完成检查器——把「声称完成」变成「逐条可验证」（spec-kit/evaluator 模式）。
每个 S 阶段有一份 stage-spec（`docs/design/stage-specs/S{N}.md`）承载机器可验证的 DoD 断言；
本技能逐条执行这些断言，输出 PASS/FAIL + 证据。**只验不修**：FAIL 报告差异，交回开发。
## 何时使用
- 用户/agent 声称某 S 阶段完成（「S2 完成了」「阶段完成」）
- 请求「跑阶段门禁」「stage gate」「过门禁」
- 阶段收口前自查（此时跑出的 FAIL 就是待办清单）
## 输入
- stage-spec：`docs/design/stage-specs/S{N}.md`（DoD 节 = 断言清单）
- 仓库：`apps/desktop`（所有门禁命令的工作目录）
- 关联资产：`docs/tests/coverage-matrix.md`（覆盖矩阵）、`.scratch/neonforge-v1/audit-items/`（审计项）、`docs/decisions/`（决策日志）
## 硬约束（不可妥协）
1. **只验不修**——FAIL 一律报告差异，不修代码/不补测试/不改 spec。
2. **证据先行**——每条断言必须带本次运行的新鲜证据（命令输出尾部/exit code/测试结果）；「上次跑过」「应该没问题」不算。
3. **不编造通过**——命令跑不出来、CI 查不到、人工验收未做 → 判 **未验证**（不算 PASS，不算 FAIL，单独列出）。
4. **全量逐条**——DoD 节每条 `- [ ]` 断言都要执行，不许抽样、不许跳过。
## 流程
```
- [ ] 1. 定位 spec：docs/design/stage-specs/S{N}.md（N 由用户给出或从语境推断）
- [ ] 2. spec 缺失 → 直接报告「无 spec，阶段无法门禁」（这本身就是发现——spec 未写）
- [ ] 3. 读 DoD 节 → 提取全部 `- [ ]` 断言（含嵌套子断言——行为验收下常有）
- [ ] 4. 逐条执行（分类方法见下节），每条记录：断言原文 / 判定 / 证据尾部
- [ ] 5. 汇总 → 写 gate 报告 docs/audits/stage-gate-S{N}-YYYY-MM-DD.md
- [ ] 6. 全绿 → 阶段可收（附基线信息）；有 FAIL/未验证 → 差异清单交回开发
```
## DoD 断言分类与执行方法
…Read the whole file at its exact version.
How to install
mdr add ninjasln-labs/agent-skills/stage-gate@sha256:2fcaafdd0a85a39fThe line at the top of this page pins the label v1.1.1, 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_bg5oftnao5y6qub6)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 4 versions of this file, between Aug 16, 2026 and Sep 29, 2026, about one every 15 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.1.1 latest | 2026-09-29 | 0febb7a | 9,634 B | A | view · diff |
| v1.0.2 | 2026-09-22 | 75c75c0 | 6,204 B | A | view · diff |
| v1.0.0 | 2026-09-18 | cbc6719 | 6,226 B | A | view · diff |
| git:20260816.abe0a4a | 2026-08-16 | abe0a4a | 6,170 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 (9634 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_bg5oftnao5y6qub6 GET https://markdownregistry.com/api/v1/resolve?ref=ninjasln-labs/agent-skills/stage-gate GET https://markdownregistry.com/api/v1/blob/2fcaafdd0a85a39f0051a38b09297ae2f43645a3fc0ddf1309cd6723b8df5a01
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.