/00. Claude Plugins
A Claude Code plugin is a folder of skills, agents, hooks, and slash commands that Claude installs per project. 28 plugins, 68 skills here.
/plugin marketplace add aiocean/claude-plugins
/plugin install <plugin-name>@aiocean-plugins
Skills load when their description matches your message, hooks fire on
tool-call events, agents spawn on the Agent tool. Idle plugins cost
nothing — browse plugins or read the guides.
Folders
Articles
- Send books to your BOOX from the terminal01
- Patching Claude Code: rebalance the built-in prompts (and more)02
- Install Claude Code plugins in two commands03
- My CLAUDE.md04
- Three Claude Code primitives, three different jobs05
- Writing CLAUDE.md: the sections that actually help06
- aio-architect-advisor07
- aio-architect-reference08
- aio-atlassian09
- aio-boox10
- aio-browser-cookie11
- aio-bun-fullstack-setup12
- aio-catch-me-up13
- aio-code-review14
- aio-dashboard-design15
- aio-debug16
- aio-discover17
- aio-doc-writer18
- aio-dream19
- aio-epub-analyze20
/02. aio-advisor
Curated decision-support reference for Claude Code — three independently-triggered knowledge bases behind one semantic-search shell. Each routes a problem to the most relevant entries, applies them, synthesizes an answer, and stress-tests it with a counter-frame.
Skills
| Skill | What it covers | Corpus |
|---|---|---|
| aio-mental-models | General reasoning & decision-making — first principles, inversion, second-order thinking, opportunity cost, probabilistic thinking, … | 54 models in 4 volumes |
| aio-threat-models | Security, privacy & AI/ML threat modeling — STRIDE, LINDDUN, PASTA, OCTAVE, Attack Trees, MITRE ATT&CK/ATLAS, Kill Chain, NIST AI RMF, OWASP LLM Top 10, K8s Threat Matrix | 27 frameworks in 7 volumes |
| aio-architect-advisor | Architecture decisions — a 5-step workflow that picks, applies, and stress-tests patterns for a system you're designing | — |
| aio-architect-reference | Architecture lookup — semantic search over the pattern encyclopedia; read full articles, compare patterns, browse by volume | 137 patterns in 10 volumes |
The aio-architect-* skills share the plugin-root scripts/ + volume-*/ corpus; aio-mental-models and aio-threat-models each carry their own self-contained scripts/ + volume-*/ inside their skill folder.
Install
/plugin install aio-advisor@aiocean-plugins
# or
npx skills add aiocean/claude-plugins -s aio-advisor
Semantic search setup
Each knowledge base ships a search-*.ts script that runs over a prebuilt embeddings.json. Where an embeddings file is gitignored, build it once with the skill's build-embeddings.ts before first search (see the individual SKILL.md).
Skills (4)
- aio-architect-advisor — Architecture decision advisor — guides pattern selection, application, synthesis, and stress-testing for system design, scaling, resilience, and migration decis…
- aio-architect-reference — Look up architecture patterns and concepts via semantic search — read the full article on demand, compare patterns side-by-side, or browse by volume.
- aio-mental-models — Decision and reasoning advisor — picks 2-3 relevant mental models, walks through applying each, and synthesizes a recommendation. Use proactively when facing a…
- aio-threat-models — Threat modeling framework advisor — selects the right framework(s) for the system (security, privacy, AI/ML, cloud, K8s), walks through application, and compose…