Loading...
Loading...
Found 5,568 Skills
[QwenCloud] Generate and edit images using Wan and Qwen Image models. Supports text-to-image, image editing (style transfer, subject consistency, text rendering), and interleaved text-image output. TRIGGER when: user wants to create illustrations, product images, artistic designs, posters, text-to-image generation, edit/transform existing images, apply style transfer, generate images based on reference photos, interleaved text-image content, mentions Wan/Qwen Image models/AI art creation, or explicitly invokes this skill by name (e.g. use qwencloud-image-generation). DO NOT TRIGGER when: user wants to understand/analyze existing images or OCR (use qwencloud-vision), video generation (use qwencloud-video-generation), text-only tasks.
Run Codex, Claude Code, and Gemini CLI reviews against the current branch concurrently, deduplicate the findings, and report only the review comments that are still valid for the current codebase.
Run Codex code review against the current branch and report only the review comments that are still valid for the current codebase, without applying fixes.
Run Claude Code review against the current branch and report only the review comments that are still valid for the current codebase, without applying fixes.
Transition from static LLM chats to autonomous agents that execute multi-step tasks. Use this when you need to automate cross-platform reports (e.g., Snowflake to Google Docs), build self-service tools for non-technical teams, or create "anticipatory" engineering workflows that draft PRs based on Slack discussions.
Learn a programming concept by exploring real examples in the current codebase. Builds a teaching tour that progressively explains the concept from simple to complex.
Codex-facing entry point for building with Alchemy. Routes to `alchemy-api` for API key-based access or `agentic-gateway` for gateway-based access when the user has not chosen an auth path yet.
Guides the agent through installing, authenticating, configuring, and using the Capawesome CLI (@capawesome/cli). Covers installation, interactive and token-based authentication, project linking via capawesome.config.json, the full command reference (app management, native builds, live updates, certificates, environments, channels, deployments, destinations, devices), CI/CD integration with token auth and JSON output, and diagnostics via the doctor command. Do not use for Capawesome Cloud feature setup (native builds workflow, live updates workflow, app store publishing) — use the capawesome-cloud skill instead.
Design products around price using Madhavan Ramanujam's "Monetizing Innovation" methodology—determine willingness to pay before you build, not after. Use when: **Set pricing for a new product** before or during development; **Validate willingness to pay** before investing in features; **Structure pricing tiers** (Good-Better-Best) for different segments; **Choose the right monetization model** (subscription, usage-based, freemium, etc.); **Diagnose why a product isn't monetizing** as expected
Augments Trailmark code graphs with external audit findings from SARIF static analysis results and weAudit annotation files. Maps findings to graph nodes by file and line overlap, creates severity-based subgraphs, and enables cross-referencing findings with pre-analysis data (blast radius, taint, etc.). Use when projecting SARIF results onto a code graph, overlaying weAudit annotations, cross-referencing Semgrep or CodeQL findings with call graph data, or visualizing audit findings in the context of code structure.
Expert blueprint for First-Person Shooters (Doom, Quake, Battlefield, Overwatch) focusing on physics-based movement, acceleration/friction, camera sway, weapon bobbing, and high-precision hit registration. Use when building tight, responsive FPS combat with advanced camera mechanics. Keywords FPS, movement physics, weapon bobbing, camera sway, hitscan, ground detection, air control.
Targeted Chat Room: Recommend experts based on topics or accept user-specified experts to simulate multi-role conversations. Trigger methods: /定向聊天室, 「定向聊天室」