Total 36,820 skills
Showing 12 of 36820 skills
Agent skill for v3-performance-engineer - invoke with $agent-v3-performance-engineer
Agent skill for performance-analyzer - invoke with $agent-performance-analyzer
Agent skill for orchestrator-task - invoke with $agent-orchestrator-task
Use when cognee is a Python AI memory engine that transforms documents into knowledge graphs with vector and graph storage for semantic search and reasoning. Use this skill when writing code that calls cognee's Python API (add, cognify, search, memify, config, datasets, prune, session) or integrating cognee-mcp. Covers the full public API, SearchType modes, DataPoint custom models, pipeline tasks, and configuration for LLM/embedding/vector/graph providers. Do NOT use for general knowledge graph theory or unrelated Python libraries.
Use the local SupeRISE wallet through its MCP endpoint. Use this whenever the user expects the agent to operate, inspect, manage, or use the Superise wallet, including MCP connectivity, available wallet capabilities, or wallet tasks such as current wallet, wallet fingerprint, wallet status, wallet address or public key (`钱包地址`, `公钥`), balances (`余额`) for `CKB`, `ETH`, `USDT`, or `USDC`, transfer progress, transaction status, address-book lookups, signing, or transfers. When wallet intent is present, first discover the live MCP capabilities with `initialize -> notifications/initialized -> tools/list`, then choose the matching tool instead of guessing.
Operate `superise market-sustain` for SupeRISE Market self-supervision. Use when the user asks the agent to keep itself alive, monitor balance or runway, inspect market pricing, top up a market account, retry pending top-up orders, clear market auth state, or change sustain guardrails and config.
Resolve all pending CLI todos using parallel processing, compound on lessons learned, then clean up completed todos.
Generate AI videos, images, and audio with Runway API. Use when generating video from images, text-to-video, video-to-video, character performance, text-to-image, text-to-speech, sound effects, or voice processing with Runway.
Refresh stale or drifting learnings and pattern docs in docs/solutions/ by reviewing, updating, replacing, or archiving them against the current codebase. Use after refactors, migrations, dependency upgrades, or when a retrieved learning feels outdated or wrong. Also use when reviewing docs/solutions/ for accuracy, when a recently solved problem contradicts an existing learning, or when pattern docs no longer reflect current code.
PUA Loop — Autonomous iterative development with PUA pressure. Runs continuously until the task is completed, no user interaction required. Combines the Ralph Loop iteration mechanism with PUA quality enforcement. Triggered by: '/pua:pua-loop', 'Auto Loop', 'loop mode', 'Keep Running', 'Auto Iteration'
Author or modify Azure TypeSpec API specifications. USE FOR: Any task that creates, modifies, or troubleshoots .tsp files or TypeSpec API specifications — including but not limited to API versioning evolution(add new preview version, add new stable version), ARM resource type(tracked, proxy, extension, child resources) or data-plane resource definitions, resource operations (CRUD, PATCH, custom actions, paging, async/Long Running Operations), models, enums, unions, properties, decorators, constraints, parameters, and swagger-to-TypeSpec conversion. DO NOT USE FOR: SDK generation from TypeSpec, releasing SDK packages, single MCP tool calls that do not require multi-step workflows. TOOLS/COMMANDS: azsdk_typespec_generate_authoring_plan, azsdk_run_typespec_validation
Design a theming architecture that supports brand variants, dark mode, and high-contrast modes with token mapping.