sap-cap
Query @cap-js/mcp-server before writing CDS entities, types, aspects, services, or CAP service handlers. Triggers on schema and service files in db/ and srv/.
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Agents & models
25,663 results
gemini-computer-use
Build and run Gemini 2.5 Computer Use browser-control agents with Playwright. Use when a user wants to automate web browser tasks via the Gemini Computer Use…
windows-automation
Guidance for semantic-first Windows automation with the bundled windows-mcp server. Use when automating desktop apps, choosing UI Automation vs screenshots, or…
cost-optimized-llm
Implement cost-optimized LLM routing with NO OpenAI. Use tiered model selection (DeepSeek, Haiku, Sonnet) to achieve 70-90% cost savings. Triggers on "LLM…
improve-coverage
Improve test coverage by identifying gaps and generating meaningful tests
scan-issues
Scan repositories and identify issues that Claude Code can efficiently handle
pr-automate
Run as a background subagent after a PR is created or pushed. Acts as a continuous quality gate, watching CI and mergeability, and catching, answering and…
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's…
automation-first
Use when a workflow asks the user to copy, edit, approve, restart, configure, repair, or verify steps that software may be able to perform.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in…
build-mcpb
This skill should be used when the user wants to "package an MCP server", "bundle an MCP", "make an MCPB", "ship a local MCP server", "distribute a local MCP",…
capability-profiles
Use when making or modding games, building web/UI or 3D assets, preparing publication, combining skills with MCPs, selecting task profiles, or diagnosing…
capability-routing
Use before writing a crawler, scraper, parser, browser-automation layer, API client, or any wrapper around work an installed tool already does; when a fetch…
context-compaction-fidelity
Use when long-running work requires summarization, compaction, handoff, or context reduction without losing requirements or state.
diagnosing-superpowers
Use when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't…
dispatching-parallel-agents
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
fictional-adult-modding
Use when the user wants OStim or SexLab work, adult outfits or body slots, revealing armor, SOS or slot 52, adult follower scenes, explicit EditorIDs, or the…
local-model-ops
Run a local LM Studio model as a Hermes provider - context floors, VRAM budget, aliases, and keyless web search. Load before wiring local inference or when an…
melty-mashups
Use when building, packaging, remixing or publishing a game mashup or mod on Melty (melty.gg), or when melty MCP tools are present in the session.
prompt-cache-discipline
Use when repeated model calls share large instructions, tools, context, or prefixes and cache efficiency materially affects cost or latency.
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an…
using-superpowers
Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions
verification-before-completion
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output…
koala-strategy
KOALA v1.0.0 — Set-and-Forget Trail HODL. The simplest possible Senpi agent. Pick an asset (default BTC). Fire LONG once on deploy. Hold with an ultra-wide DSL…