SKILLS & AGENTS/Skill 与 Agent·MCP-SERVER
cwinvestments/memstack
Structured skill framework for Claude Code. 130 skills, persistent memory, TokenStack compression, localhost dashboard with 3-agent runner, real-time streaming, MCP tools.
怎么装:Install: /plugin marketplace add cwinvestments/memstack
02 / 现在的位置02 / Why now
首次发现FIRST SEEN
03 OCT 202603 OCT 2026
增长GROWTH
+0.0%+0.0%
422 → 422 stars · 2 个快照422 → 422 stars · 2 snapshots
状态STATUS
持续活跃Active
质量 B+Quality B+
03 / 它能帮你做什么03 / What it helps you do
04 / 安装04 / Install
$ README 里给出的安装方式。The installation method given in the README.
$ README 里给出的安装方式。The installation method given in the README.
两种装法选一个即可 —— 上面那条给命令行用户,下面那条给写代码的用户。Pick one of the two — the first is for command-line users, the second for people writing code.
05 / 限制与风险05 / Limits and risk
风险不是警告,是可信度的一部分。以下结论只基于文档静态扫描,我们不会执行项目里的任何代码。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
存在风险Risk found
静态扫描STATIC SCAN
01执行远程脚本Runs a remote scriptskills/deployment/hetzner-setup/SKILL.md
curl -fsSL https://get.docker.com | sh
02下载未知二进制Downloads an unknown binaryskills/deployment/hetzner-setup/SKILL.md
curl -1sLf 'https://dl.cloudsmith.io/public/caddy/stable/debian.deb.txt' | tee /etc/apt/sources.list.d/caddy-stable.list
03控制浏览器Controls a browserreadme
| `webapp-testing` | Produce Playwright end-to-end tests that verify real user flows in a browser for web application QA. |
04需要系统权限Needs system permissionsskills/deployment/hetzner-setup/SKILL.md
usermod -aG sudo deploy
05读取 API KeyReads an API keyskills/deployment/railway-deploy/SKILL.md
- **Port** reads from `process.env.PORT` or `os.environ["PORT"]`: Railway assigns this dynamically
06读取 API KeyReads an API keyskills/development/api-designer/SKILL.md
const stripe = new Stripe(process.env.STRIPE_SECRET_KEY!);
07控制浏览器Controls a browserskills/development/webapp-testing/SKILL.md
*Produces Playwright end-to-end tests that verify real user flows in a browser.*
这里只做静态扫描:读 README、SKILL.md 和依赖清单,不执行代码。没有命中不代表安全。This is static scanning only: we read the README, SKILL.md and dependency list, and never execute code. No findings does not mean safe.
{
"agents": [
{
"agent": "claude-code",
"evidence": "tree: .claude/"
},
{
"agent": "claude-desktop",
"evidence": "skills/automation/hosted-mcp-catalog/SKILL.md: …om/mcp\" } } } ``` **In Claude Desktop**: add to `claude_desktop_con…"
},
{
"agent": "vscode",
"evidence": "skills/deployment/docker-setup/SKILL.md: …ntrol .git .gitignore # IDE .vscode/ .idea/ *.swp *.swo # OS fil…"
}
],
"apiKey": "for per-branch secrets - Use `GITHUB_TOKEN` for GitHub operations (auto-provided)",
"docker": null,
"taxonomy": {
"scores": {
"design": 0,
"ai-tools": 0,
"dev-tools": 4,
"indie-web": 3,
"skill-agent": 7,
"productivity": 1
},
"primary": "skill-agent",
"secondary": "mcp-server"
},
"localRuntime": null,
"skillMdTotal": 87,
"skillMdErrors": [],
"treeTruncated": false,
"categoryScores": {
"data": 0,
"agent": 0,
"media": 0,
"design": 0,
"browser": 0,
"devtool": 2,
"security": 1,
"marketing": 1,
"productivity": 1
},
"classification": [
{
"signal": "60 SKILL.md with name + description",
"weight": 0.95
},
{
"signal": "skills/ directory with 91 markdown files",
"weight": 0.75
},
{
"signal": "Claude Code plugin manifest",
"weight": 0.7
},
{
"signal": "MCP topic + README",
"weight": 0.6
},
{
"signal": "description mentions AI",
"weight": 0.2
}
],
"scannedSources": [
"readme",
"skills/automation/api-integration/SKILL.md",
"skills/automation/content-pipeline/SKILL.md",
"skills/automation/cron-scheduler/SKILL.md",
"skills/automation/hosted-mcp-catalog/SKILL.md",
"skills/automation/n8n-workflow-builder/SKILL.md",
"skills/automation/webhook-designer/SKILL.md",
"skills/business/client-onboarding/SKILL.md",
"skills/business/contract-template/SKILL.md",
"skills/business/financial-model/SKILL.md",
"skills/business/freelancer-toolkit/SKILL.md",
"skills/business/gdpr/SKILL.md",
"skills/business/invoice-generator/SKILL.md",
"skills/business/licensing/SKILL.md",
"skills/business/proposal-writer/SKILL.md",
"skills/business/scope-of-work/SKILL.md",
"skills/business/sop-builder/SKILL.md",
"skills/compress/SKILL.md",
"skills/content/blog-post/SKILL.md",
"skills/content/email-sequence/SKILL.md",
"skills/content/landing-page-copy/SKILL.md",
"skills/content/newsletter/SKILL.md",
"skills/content/product-description/SKILL.md",
"skills/content/tiktok-script/SKILL.md",
"skills/content/twitter-thread/SKILL.md",
"skills/content/youtube-script/SKILL.md",
"skills/deployment/ci-cd-pipeline/SKILL.md",
"skills/deployment/docker-setup/SKILL.md",
"skills/deployment/domain-ssl/SKILL.md",
"skills/deployment/hetzner-setup/SKILL.md",
"skills/deployment/netlify-deploy/SKILL.md",
"skills/deployment/railway-deploy/SKILL.md",
"skills/development/api-designer/SKILL.md",
"skills/development/changelog-generator/SKILL.md",
"skills/development/code-reviewer/SKILL.md",
"skills/development/mentor/SKILL.md",
"skills/development/migration-planner/SKILL.md",
"skills/development/performance-audit/SKILL.md",
"skills/development/refactor-planner/SKILL.md",
"skills/development/test-writer/SKILL.md",
"skills/development/webapp-testing/SKILL.md",
"skills/diary/SKILL.md",
"skills/echo/SKILL.md",
"skills/familiar/SKILL.md",
"skills/forge/SKILL.md",
"skills/goal/SKILL.md",
"skills/governor/SKILL.md",
"skills/grimoire/SKILL.md",
"skills/humanize/SKILL.md",
"skills/marketing/competitor-analysis/SKILL.md",
"skills/marketing/facebook-ad/SKILL.md",
"skills/marketing/google-ad/SKILL.md",
"skills/marketing/launch-plan/SKILL.md",
"skills/marketing/lead-magnet/SKILL.md",
"skills/marketing/marketplace-submit/SKILL.md",
"skills/marketing/pricing-strategy/SKILL.md",
"skills/marketing/sales-funnel/SKILL.md",
"skills/marketing/webinar-script/SKILL.md",
"skills/product/feature-spec/SKILL.md",
"skills/product/feedback-analyzer/SKILL.md",
"skills/product/mvp-scoper/SKILL.md"
],
"skillMdFetched": 60
}