All nine kinds in one list: what an agent loads, what it runs, what it
reads and what bundles the rest. 418,037 of
them, each with its token cost per session, a security scan with the
line that triggered it, and whether it is the original or one of the
copies.
MCP server exposing Postgres, Redis, Elasticsearch, MySQL, MongoDB, and LDAP as tools, with lazy connection management, retry, circuit breaking, per-connection read-only mode, and optional database drivers. Runs locally from the mcp-server-db npm package.
★not rated 82 19d agoASocket: warn
tokens not measured
originalMIT
Archived KIP 1.x integration for historical reference. Persistent graph-based memory for AI agents via KIP (Knowledge Interaction Protocol). Provides retrieval-first memory operations (KQL), durable writes (KML), schema discovery (META), and memory hygiene patterns. Use whenever the agent needs to consult or update…
Generate or convert single-file HTML slide presentations with interactive components (flip cards, charts, tables, code blocks, stats, architecture flows, and more) or creative visual themes.
★not rated 82▲
+2 4mo agoA
tokens not measured
forkMIT
A task conductor for Claude Code: multi-agent orchestration with an enforced evidence contract, repo-specific learning, and update-safe local evolution.
★not rated 81
changed 3d agoA
tokens not measured
originalApache-2.0
Use this skill to bring any vision model from HuggingFace or NVIDIA NGC into an NVIDIA DeepStream pipeline with end-to-end automation: ONNX download, SafeTensors export, TRT engine build, custom nvinfer bbox parser, multi-stream benchmark, and PDF report. Object detection models only.
OOP architecture planning and progress tracking for software projects. Generates Mermaid UML (class, sequence, component, state, and ER diagrams) inside CLAUDE.md with full typed signatures, visibility markers, and implementation status on every class/method/relationship. Triggers on: 'plan the architecture', 'design…
★not rated 81 4mo agoA
tokens not measured
originalMIT
Institutional memory for AI coding agents: deterministic decision capture and pre-task warnings about previously REJECTED approaches, backed by your self-hosted RoBrain stack.
★not rated 81 1mo agoA
tokens not measured
originalApache-2.0
Control MSW mocks at runtime via msw-cli (open session, add/update/remove handlers). Use when mocking APIs, changing mock responses, or debugging MSW without restarting the app.
The team-architecture factory for Claude Code and Codex — a meta-skill that turns a domain description into an agent team and the skills they use, with six team patterns (Pipeline, Fan-out/Fan-in, Expert Pool, Producer-Reviewer, Supervisor, Hierarchical Delegation), a two-layer quality gate (internal QA + external…
★not rated 81
changed 10d agoA
tokens not measured
originalApache-2.0
Manage long-running background jobs and interactive workflows on Windows using PowerShell Jobs (Start-Job, Receive-Job) — the Windows equivalent of tmux sessions.
MCP server "supabase" as configured in TradingGoose/TradingGoose.github.io. Launched with wsl npx -y @supabase/mcp-server-supabase@latest --read-only --project-ref=${VITE. Needs 1 environment variable to run.
★not rated 81▲
+2 5mo agoA
tokens not measured
AGPL-3.0
Comprehensive toolkit for developing with the CocoIndex library. Use when users need to create data transformation pipelines (flows), write custom functions, or operate flows via CLI or API. Covers building ETL workflows for AI data processing, including embedding documents into vector databases, building knowledge…
Expert guidance on Swift Testing best practices, patterns, and implementation. Use when developers mention: (1) Swift Testing, @Test, #expect, #require, or @Suite, (2) "use Swift Testing" or "modern testing patterns", (3) test doubles, mocks, stubs, spies, or fixtures, (4) unit tests, integration tests, or snapshot…
MCP server "hwatu" as configured in hongnoul/hwatu. Launched with https://github.com/hongnoul/hwatu/releases/download/v0.6.0/hwatu-mcp-linux-x86_6.
★not rated 81▲
+1 29d agoA
tokens not measured
AGPL-3.0
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: