skill-quality-gate SKILL.md skillA
skill-quality-gate from ooooooooooooooooooop/agent-tools is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add ooooooooooooooooooop/agent-tools/skill-quality-gate@git:20260817.d6c4635Pins git:20260817.d6c4635 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- ooooooooooooooooooop/agent-tools
- Path
skills/skill-quality-gate/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260817.d6c4635, committed Aug 17, 2026
- Size
- 2,637 bytes
- Repository stars
- 4
- License
- MIT
评估 Codex Skill 的触发边界、内部流程、输出契约、验证方式和回归质量。用于审查或优化现有 Skill、发布前做行为质量检查、比较修改前后的 Skill 质量，默认只读，不替代仓库结构校验或跨设备同步。.
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
# Skill 质量门禁 ## 适用范围 使用本 Skill 审查一个 Skill 包或一个 Skill 仓库的行为质量，重点关注： - 触发条件是否足够具体，是否明确不适用场景。 - 工作流程是否有顺序、边界和可执行的判断。 - 输出契约是否能让用户和测试复核结果。 - 安全边界、事实/假设区分和副作用控制是否完整。 - 示例、脚本和回归测试是否真正覆盖 Skill 的关键行为。 默认只读。用户明确要求修改时，先输出问题清单和最小改动面，再实施修改。 ## 不适用场景 - 只检查 `skills.json`、目录、链接或元数据完整性：使用 `skill-repository-maintainer`。 - 只需要执行一个已知 Skill，而不是评估 Skill 本身。 - 没有目标 Skill、示例或可观察输出，无法进行行为评估时；应报告证据不足，不得凭感觉打分。 ## 审查流程 1. 确认目标路径、版本、语言、依赖和本次审查范围。 2. 读取 `SKILL.md`、`agents/openai.yaml`、示例、引用资料和脚本；不把运行时文件当作 Skill 内容。 3. 评估触发、边界、流程、输出、验证和安全六个维度，分别记录事实、推断和缺失证据。 4. 优先运行包内已有的 smoke test、示例检查或质量脚本；失败时保留原始错误。 5. 按影响和修复成本排序，给出最小修复建议；不为了对称性重写整个包。 ## 输出契约 输出以下内容： 1. `PASS`、`PARTIAL` 或 `BLOCKED`。 2. 目标 Skill 和版本。 3. 通过项、失败项和证据路径。 4. 触发边界、流程、输出、验证、安全六维结论。 5. 按 P0/P1/P2 排序的改进项。 6. 未验证的行为、残余风险和明确不应修改的范围。 不要把“结构校验通过”写成“行为质量通过”，也不要把旧输出或旧哈希当作本次修改的证据。 ## 验证 对仓库内的 Skill 包运行： ```bash python3 skill-quality-gate/scripts/quality_report.py --root . --strict ``` 脚本只使用 Python 标准库，检查 frontmatter、长度、边界/输出/验证章节、UI 元数据和非空示例。复杂 Skill 仍需运行自己的回归测试；结构脚本不能替代真实任务前测。 详细评分维度见 [质量评分表](references/quality-rubric.md)。
Read the whole file at its exact version.
How to install
mdr add ooooooooooooooooooop/agent-tools/skill-quality-gate@sha256:79d170d53a4740f7The line at the top of this page pins the label git:20260817.d6c4635, 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_wbglw5itprvoo7rn)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Aug 17, 2026.
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 (2637 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
ooooooooooooooooooop/agent-tools · 4 stars · license MIT · pushed 2026-10-23 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_wbglw5itprvoo7rn GET https://markdownregistry.com/api/v1/resolve?ref=ooooooooooooooooooop/agent-tools/skill-quality-gate GET https://markdownregistry.com/api/v1/blob/79d170d53a4740f78ee8aa5f3276d4b83de5cc047c6e033f5fd7179c25cfd80d
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.
More from ooooooooooooooooooop/agent-tools
Every file in ooooooooooooooooooop/agent-tools