Raindrop Collection Governance — Security skill for Claude Code
Agent Skills-compatible skill: govern a Raindrop.io library's collection structure via raindrop-mcp — audit, confirmed restructuring & misplaced-bookmark relocation.
How to install Raindrop Collection Governance
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open ChosenXu/raindrop-collection-governance and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Raindrop Collection Governance does
Agent Skills-compatible skill: govern a Raindrop.io library's collection structure via raindrop-mcp — audit, confirmed restructuring & misplaced-bookmark relocation. Works with Claude Code, Codex CLI, Gemini CLI, GitHub Copilot, Cursor & WorkBuddy.
Alternatives in Security
- Anthropic Cybersecurity Skills — 734+ structured cybersecurity skills for AI agents · MITRE ATT&CK mapped · agentskills.io open standard · Work 3.8k ★
- Perplexity Super Skills — Complete collection of 12 Perplexity Computer Super-Skills merging Perplexity + Claude Code capabilities acros 346 ★
- AWS MCP Server — by alexei-led - Features multiple Python environment setup options with detailed code style guidelines, compre 182 ★
README
Raindrop Collection Governance
English | [简体中文](README.zh-CN.md)
An [Agent Skills](https://agentskills.io)-compatible skill: **govern the collection (folder) structure of a [Raindrop.io](https://raindrop.io/) library** — read-only audits, user-confirmed restructuring, and misplaced-bookmark relocation. Works in any agent that reads the Agent Skills standard (Claude Code, Codex CLI, Gemini CLI, GitHub Copilot, Cursor, WorkBuddy…).
What it does
Three phases, all write-gated:
- Audit (read-only) — deterministic scan of the whole library: duplicate collection names, fragmented / empty collections, unsorted backlog, naming inconsistencies, misfiled hierarchy. Output is a P0/P1/P2 report with machine-checkable evidence (collection ids, parent chains).
- Restructure (confirmed) — create / rename / re-parent / merge collections and move bookmarks, executed only after you confirm an operation plan. Every batch is snapshotted to an undo file and read back for verification.
- Relocate — find bookmarks stored in the wrong collection (Pro semantic diagnostics, or a tag/domain/title heuristic on the free plan) and move them through the same confirmation gate.
A deeper **framework-review mode** assesses the overall taxonomy: classification-axis mixing, granularity balance, semantically overlapping collection pairs, and extensibility warnings (e.g. flat top-level collections past the split threshold).
Reports are rendered in the language you asked in (Simplified Chinese or English, strictly monolingual) and are always written to `/tmp/` — never into the library or the repo.
Install
Clone this repository into your agent's skills directory:
| Agent | User-level directory | Project-level directory |
|---|---|---|
| Claude Code | ~/.claude/skills/ |
.claude/skills/ |
| Codex CLI | ~/.agents/skills/ |
.agents/skills/ |
| Gemini CLI | ~/.gemini/skills/ |
.gemini/skills/ |
| GitHub Copilot | ~/.copilot/skills/ |
.github/skills/ |
| Cursor |
Related Skills
MCP Govern
Run MCP governance audit — check 30 rules across security, access control, compliance, data governance, and op
Agent Brain Hub
Shared, brain-inspired memory for AI agents: 13 brain regions with awake/sleep loops, a live visualizer, agent
Harness Govern
End-to-end harness governance loop and single front door for the harness- family — measure (harness-budget + h
Managed MCP Doctor
Audit Claude Code MCP governance drift, catch when allowedMcpServers no longer covers managedMcpServers (2.1.2
Securevector AI Threat Monitor
Security & Observability for AI Agents — audit every tool call, enforce allow/block policies, catch prompt inj
Formalize Math Paper
Agent Skill for formalizing a mathematics paper in Lean 4 with Mathlib: prove it, audit it against the paper,
Related Agents
Fable5 Apfel Engineer
Heavy-lifting Fable-5 engineer for the apfel project (Apple on-device FoundationModels CLI + OpenAI-compatible
Codex CLI
Codex CLI → any OpenAI-compatible endpoint
Procedure Writer
Verification team member 8, procedure writer. Called by the team lead to write or adapt package install, rollb