Total 40,307 skills
Showing 12 of 40307 skills
SPARC development workflow: Specification, Pseudocode, Architecture, Refinement, Completion. A structured approach for complex implementations that ensures thorough planning before coding. Use when: new feature implementation, complex implementations, architectural changes, system redesign, integration work, unclear requirements. Skip when: simple bug fixes, documentation updates, configuration changes, well-defined small tasks, routine maintenance.
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.
PUA Shot — v2 Original Concentrated Version (449 lines full injection), the complete single-file version before splitting, with the strongest flavor. Zero dependencies and zero references, injects all content into the context at once. Suitable for sub-agent injection, scenarios requiring the strongest PUA effect, or those who don't want progressive loading. Triggers on: '/pua:shot', '/pua shot', 'PUA Concentrate', 'Shot Mode', 'Max PUA', 'Full Injection'. Also great for injecting into sub-agents via Read tool since it's self-contained.
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'