All nine kinds in one list: what an agent loads, what it runs, what it
reads and what bundles the rest. 414,419 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.
Use when a long coding or research task should be managed with statem state-machine runbooks, including creating specs, starting or resuming runs, checking current state, transitioning with goto, saving progress, and reading history.
Use when user requests diagrams, flowcharts, architecture charts, or visualizations. Also use proactively when explaining systems with 3+ components, complex data flows, or relationships that benefit from visual representation. Generates .excalidraw files and exports to PNG/SVG via Kroki API or locally using…
Plan a feature or task in fast, full, or ultra mode. Ultra creates an indexed multi-file bundle with deeply specified phases for execution by a smaller model. Use for "plan", "new feature", "start feature", "create tasks", or exhaustive implementation planning.
Blueprint authoring workflow for the Flopperam Unreal Engine MCP. Covers the full create, author, commit, verify cycle using the narrow bp tool surface. Use when creating or editing Blueprints, adding variables/components/events/functions, wiring graphs, or debugging compile errors.
Building or editing Simulink (.slx) models that stream signals in frames using DSP System Toolbox — audio, vibration, radar, comms. Use when the prompt names a Simulink block (Discrete FIR Filter, Buffer, Unbuffer, Rate Transition, Downsample, Upsample, Sample-Rate Converter, FIR Decimation, Time Scope, Spectrum…
★not rated 1.1k▲
+31 3d agoASkillSpector: pass159 tokens
A guided assistant for turning chat records and personal details about a former partner into a digital persona skill that imitates their communication style. The instructions are in Chinese and describe importing WeChat or iMessage records, analysing them, previewing conversations, and writing a skill file.
This plugin is a thin adapter between OpenClaw and LycheeMem. It does not replace memory-core, does not claim plugins.slots.memory, and does not duplicate LycheeMem algorithms.
Security scanning for MCP servers using YARA rules, LLM analysis, and Cisco AI Defense. Detect prompt injection, tool poisoning, and other threats in MCP tools, prompts, and resources.
★not rated 1.1k▲
+6 yesterdayA
tokens not measured
originalApache-2.0
Create conversation adapters for importing AI chat history from different tools (Claude Code, Cursor, Warp, Codex, etc.). Covers the adapter.Adapter interface, caching strategies, incremental parsing, watch/FD management, and performance standards. Use when creating a new adapter, modifying adapter behavior, or…
Set up Raindrop AI traces for an agent and verify they flow into Workshop. Use when the user says "set up traces", "add tracing", "instrument my agent", "wire Raindrop", "Workshop is empty", or "make traces show up in Workshop." Guides unknown repos by discovering runtime and telemetry setup, using current Raindrop…
A Chinese-language guide for planning product analytics tracking: the events, fields, trigger times, definitions, and checks used to collect product data.
Run Arbor's hypothesis-tree research workflow inside Claude Code using your own model — no API key. Bundles the Arbor Agent Skill suite and registers the keyless arbor mcp tools (Idea Tree, evaluation, worktrees, guarded merges, reports).
★not rated 1.1k▲
+7 5d agoA
tokens not measured
originalApache-2.0
Use this agent when the user needs to understand open-source libraries, find implementation details in codebases, locate specific source code with GitHub permalinks, research the history or context behind code changes, or get authoritative answers backed by actual code evidence. This agent excels at navigating large…
Output styles that make Claude answer-first, plain, and easy to skim, plus a /tldr transform. Attention-kind, Spartan, and Rundown ship as both output styles and user-invoked skills.
★not rated 1.1k▲
+77 6d agoA
tokens not measured
AGPL-3.0
A reference skill for a canonical schema: a consistent definition of fields and record types for data such as email and calendar entries. It also covers provider formats and Gmail REST resource shapes.
Use when the user asks to install, configure, troubleshoot, or understand Snow CLI itself — Profile/API setup, MCP servers, Skills, Hooks, sub-agents, sensitive commands, proxy/browser, third-party relay, LSP/ACE, Team mode, SSE, privacy, plugins, or docs paths. Loads official bundled usage docs via progressive…
★not rated 1.1k▲
+2 yesterdayA85 tokens
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: