All nine kinds in one list: what an agent loads, what it runs, what it
reads and what bundles the rest. 433,670 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.
Precise local semantic code search via MCP. Indexes your codebase with Go AST parsing, embeds with Ollama or LM Studio, and exposes vector search to Claude through an MCP server — no cloud, no npm.
A set of development rules for building WorkDSH workbench plug-ins with the official Creator tools and WorkDSH's business software kit. It explains how to handle plug-in context, permissions, data, files, and user approval without replacing the host's built-in features.
Use for Nim symbol navigation, diagnostics, and type resolution. MANDATORY: Use specialized MCP tools (nimFindSymbols, nimFindReferences, nimListSymbols, nimCheckFile, nimCheckProject, nimFindTypeDefinition) first; fall back to grep only on error or user confirmation.
Process documents with Blockify API to create optimized IdeaBlocks for RAG. Search external ChromaDB knowledge bases with 100k+ blocks. Use when processing documentation, creating knowledge bases, improving AI context retrieval, or when user mentions Blockify, IdeaBlocks, or knowledge distillation.
MCP Server for interacting with Elasticsearch and OpenSearch. Runs locally from the elasticsearch-mcp-server Python package. Needs 5 environment variables to run.
★not rated 316▲
+2 3d agoASocket: warn
tokens not measured
originalApache-2.0
Apply Edward Tufte's principles to any data visualization, chart, dashboard, or infographic. Use when the user asks to produce, design, critique, or improve a chart, graph, dashboard, KPI tile, table-with-data, sparkline, small multiple, time series, distribution plot, choropleth, or any other visual that communicates…
Use when a researcher is choosing, framing, refining, or stress-testing a research question, hypothesis, thesis topic, project idea, grant direction, paper angle, or stalled research direction.
Run mobile automation, app testing, and interact with iOS and Android devices, simulators, emulators, and apps using the mobilecli CLI tool or JSON-RPC API. Trigger this skill whenever the user wants to list connected devices, boot or shut down simulators/emulators, take mobile screenshots, start screen recordings…
Use this skill for Memory Palace durable-memory work in this repository: saving facts for later, recalling cross-session memory, deciding create vs update, handling guardaction or guardtargeturi, or using readmemory("system://boot"), searchmemory, compactcontext, rebuildindex, or indexstatus. Also use it when the user…
Fetch and extract full article content from URLs. Returns complete text with structure (headings, links, lists) instead of summaries. Multiple extraction strategies, browser impersonation, cookies, crawling, custom selectors, 200-700ms.
Tells an agent what changed on a server since it last looked - plus status, Docker, backups, Proxmox. Every tool is classed read, write or destructive, so an agent can tell a look from a change before it makes the call.
Wrap an agent loop with step limits, cost caps, human approval gates, and a full trace. Use whenever building or reviewing any tool-calling agent before it touches real systems.
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: