Skill 与 AgentSKILLS & AGENTS· MCP-SERVER

stash

Fergana-Labs/stash

Open-source infrastructure for agents that learn from experience. Capture production traces and turn lessons into reusable knowledge and skills.

根据公开文档整理，未运行实测；费用以项目官网为准。Based on public documentation, without runtime testing. Check the project site for pricing.

适用平台Platforms: claude-code
已识别的要求Documented requirements: API key
许可LICENSE: MIT

打开仓库Open repository 官网Homepage

能力CAPABILITIES

它能帮你做成什么What it helps you do

上手GET STARTED

怎么装How to install

MANUAL-COPY

Stash works directly when dropped into any agent's `~/.claude/skills/` folder.

选择与你的环境对应的方式。命令来自项目文档，未运行实测。Choose the option for your environment. Commands come from project documentation and have not been run-tested.

打开项目文档Open project documentation ↗

使用限制LIMITATIONS

限制与风险Limits and risk

以下要求与风险来自文档静态检查，未执行项目代码；扫描没有命中，不代表使用安全。Risk here is evidence, not an alarm. These findings come from static scanning of the docs; we never execute a project’s code.

限制LIMITS

未知Unknown

01需要 API KeyREQUIRES API KEY: 是Yes
02需要本地环境NEEDS LOCAL RUNTIME: 未在文档中发现Not found in the docs
03需要 DockerNEEDS DOCKER: 未在文档中发现Not found in the docs
04难度DIFFICULTY: 需要 API KeyNeeds an API key

项目动态PROJECT ACTIVITY

它现在处在什么位置Where it stands right now

首次发现FIRST SEEN

03 OCT 202603 OCT 2026

增长GROWTH

+2.7%+2.7%

328 → 337 stars · 13 个快照328 → 337 stars · 13 snapshots

讨论DISCUSSION

1 SOURCES1 SOURCES

2 条外部提及2 external mentions

状态STATUS

持续活跃Active

相关讨论RELATED DISCUSSIONS

Show HN: Give your agents a personal internet based on what you've surfed
HN_STORY · 2 points · 0 comments
Show HN: Stash – CLI to search over your team's coding agent sessions
HN_STORY · 8 points · 1 comments

PROVENANCE · 这些结论的依据是什么Where these conclusions come from

来源 URLSource URL: https://github.com/Fergana-Labs/stash
原始数据哈希Raw data hash: a40ca65e0a29c26e78374532f36a780b
解析时间Parsed at: 2026-10-15T23:38:01.560Z
最后一次验证Last verified: 2026-10-15T22:12:35.708Z
增长测量时间Growth measured: —
发现查询Discovery queries: focus:token:repo:topic-context-engineering
分类来源Category source: rules
焦点Focus: token (5)

完整解析证据 JSONFull parse evidence JSON

{
  "agents": [
    {
      "agent": "claude-code",
      "evidence": "tree: .claude-plugin/"
    }
  ],
  "apiKey": "ew public lookups) require an API key: ``` Authorization: Bearer st_xxxxxxxxx",
  "docker": null,
  "taxonomy": {
    "scores": {
      "design": 0,
      "ai-tools": 4,
      "dev-tools": 4,
      "indie-web": 0,
      "skill-agent": 6,
      "productivity": 3
    },
    "primary": "skill-agent",
    "secondary": "mcp-server"
  },
  "localRuntime": null,
  "skillMdTotal": 6,
  "skillMdErrors": [
    {
      "path": "backend/static/SKILL.md",
      "error": "no frontmatter"
    }
  ],
  "treeTruncated": false,
  "categoryScores": {
    "data": 4,
    "agent": 3,
    "media": 0,
    "design": 1,
    "browser": 0,
    "devtool": 1,
    "security": 0,
    "marketing": 0,
    "productivity": 0
  },
  "classification": [
    {
      "signal": "5 SKILL.md with name + description",
      "weight": 0.95
    },
    {
      "signal": "python dependency on mcp / fastmcp + MCP framing",
      "weight": 0.8
    },
    {
      "signal": "README describes a Claude / Agent Skill",
      "weight": 0.7
    },
    {
      "signal": "Claude Code plugin manifest",
      "weight": 0.7
    }
  ],
  "scannedSources": [
    "readme",
    "backend/static/SKILL.md",
    "docs/skills/brief/SKILL.md",
    "docs/skills/cleanup/SKILL.md",
    "docs/skills/overview/SKILL.md",
    "docs/skills/resurface/SKILL.md",
    "docs/skills/slides/SKILL.md"
  ],
  "skillMdFetched": 6
}