AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Skill Admission

skill-cloud99277-kitclaw-skill-admission · by cloud99277

|

No reviews yet
0 installs
31 views
0.0% view→install

Install

$ agentstack add skill-cloud99277-kitclaw-skill-admission

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-cloud99277-kitclaw-skill-admission)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
5mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Skill Admission? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

skill-admission — KitClaw Skill 收编验收

检查一个 skill 是否达到 KitClaw 公开仓库的准入标准。

准入标准(7 项检查)

| # | 检查项 | 级别 | 标准 | |---|--------|------|------| | 1 | lint | 必须 | frontmatter 格式正确,name hyphen-case,description 完整 | | 2 | security | 必须 | 无 API key、token、password 等敏感数据 | | 3 | no-personal-deps | 必须 | 无硬编码路径(/home/xxx、/mnt/x)、无用户名引用 | | 4 | agent-agnostic | 必须 | 不依赖特定 Agent(Claude Code hooks、OMC 等) | | 5 | self-contained | 必须 | SKILL.md 引用的 scripts/、references/ 文件全部存在 | | 6 | docs | 推荐 | body ≥5 行,有标题结构,


### 批量检查(全仓库)

```bash
python3 ~/.ai-skills/skill-admission/scripts/admit.py ~/.ai-skills --all

JSON 输出(给 CI/脚本用)

python3 ~/.ai-skills/skill-admission/scripts/admit.py ~/.ai-skills/ --format json

Strict 模式(推荐项也当必须)

python3 ~/.ai-skills/skill-admission/scripts/admit.py ~/.ai-skills/ --strict

收编流程

1. 运行 admission 检查(原件上跑,不修改原件)
2. 复制到公开仓库(cp -r)
3. 在副本上修复所有 FAIL 项
4. 路径通用化(/home/xxx → $HOME 或通用写法)
5. 删除非标辅助文件(README.md、banner 等)
6. 通过 KitClaw pre-commit hook(自动校验 frontmatter + 安全)
7. git add + commit + push

Frontmatter 校验规则(pre-commit hook)

KitClaw 的 validate_frontmatter.py 对不同文件有不同要求:

| 文件类型 | 必填 (阻塞提交) | 推荐 (warning, 不阻塞) | |---|---|---| | SKILL.md | name + description | tags, scope | | **references/\.md | frontmatter 存在即可 | 无 | | 其他 .md* | title | tags, scope |

SKILL.md 只需 name + description,与本地 skill 规范一致,不需要额外加 title

⚠️ 关键规则:不要动原件

公开仓库的 skill 必须从原件复制,绝不能修改 ~/.ai-skills/ 里的源文件。

原因:

  • ~/.ai-skills/ 是用户私有工作环境,包含个人路径、API key 引用、Agent 专属配置
  • 公开仓库需要通用化处理(去掉硬编码路径、适配多 Agent),但原件需要保留以便日常使用
  • KitClaw 治理 hook 已与本地规范对齐(SKILL.md 只需 name+description),两边标准一致

正确做法:

# 1. 从私有目录复制到公开仓库
cp -r ~/.ai-skills/my-skill ~/projects/kitclaw/core-skills/
# 或
cp -r ~/.ai-skills/my-skill ~/projects/ai-skills-hub/

# 2. 在公开仓库副本上做修改
#    - 去掉硬编码路径(/home/xxx → 通用写法)
#    - 满足目标仓库的治理标准(如加 title 字段)
#    - 删除非标辅助文件(README.md、banner.jpg 等)

# 3. 私有原件保持不动

决不能做的事情:

  • ❌ 直接修改 ~/.ai-skills/ 里的文件来适配公开标准
  • ❌ 从公开仓库反向覆盖私有原件
  • ❌ 在私有原件上运行目标仓库的 pre-commit hook

与其他 skill 的关系

| 关联 skill | 关系 | |------------|------| | skill-lint | admission 内部调用 lint 逻辑 | | skill-security-audit | admission 内部调用安全检查 | | skill-installer | 安装后跑 admission 确认合规 |

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.