Install
$ agentstack add skill-cloud99277-kitclaw-mcp-export ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo 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.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
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 →About
MCP Export — SKILL.md → MCP Tool JSON 导出
用途
将 Agent Toolchain 的 SKILL.md frontmatter 导出为符合 MCP 2025-03-26 规范的 Tool JSON schema。
> 只做导出,不做 MCP Server 运行时。 导出的 JSON 可被任何 MCP 兼容的 Agent/Client 消费。
使用方式
# 导出所有 skill 到 stdout(JSON 格式)
python3 ~/.ai-skills/mcp-export/scripts/export-mcp.py
# 导出到文件
python3 ~/.ai-skills/mcp-export/scripts/export-mcp.py --output tools.json
# 仅导出指定 skill
python3 ~/.ai-skills/mcp-export/scripts/export-mcp.py --skill translate --skill deep-research
# 查看统计信息
python3 ~/.ai-skills/mcp-export/scripts/export-mcp.py --stats
# Pretty-print 格式化输出
python3 ~/.ai-skills/mcp-export/scripts/export-mcp.py --pretty
输出格式
{
"schema_version": "1.0",
"mcp_spec_version": "2025-03-26",
"exported_at": "2026-03-14T19:00:00+08:00",
"tools": [
{
"name": "translate",
"description": "...",
"inputSchema": { "type": "object", "properties": {...}, "required": [...] },
"annotations": { "readOnlyHint": false, ... }
}
]
}
映射规则
详见 references/mcp-schema-mapping.md。
依赖
- Python 3(stdlib only,零外部依赖)
~/.ai-skills/.system/io-contracts/type-registry.json(IO 类型映射)
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: cloud99277
- Source: cloud99277/KitClaw
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.