Loading...
Loading...
Found 498 Skills
Remove signs of AI-generated writing from text. Use when editing or reviewing any content to make it sound more natural and human-written. Catches patterns like inflated language, rule of three, em dash overuse, vague attributions, copula avoidance, negative parallelisms, synonym cycling, filler phrases, excessive hedging, and soulless structure. Use when someone says "humanize this", "this sounds like AI", "make this sound human", "remove the AI", "clean this up", "de-AI this", "this reads like ChatGPT", or when reviewing any AI-assisted draft before publishing. Also use as a final pass on content from other skills like boring-remix or social-content. World Code integrated — applies voice.md rules when available.
Develop, debug, and optimize SGLang LLM serving engine. Use when the user mentions SGLang, sglang, srt, sgl-kernel, LLM serving, model inference, KV cache, attention backend, FlashInfer, MLA, MoE routing, speculative decoding, disaggregated serving, TP/PP/EP, radix cache, continuous batching, chunked prefill, CUDA graph, model loading, quantization FP8/GPTQ/AWQ, JIT kernel, triton kernel SGLang, or asks about serving LLMs with SGLang.
Benchmark vLLM or OpenAI-compatible serving endpoints using vllm bench serve. Supports multiple datasets (random, sharegpt, sonnet, HF), backends (openai, openai-chat, vllm-pooling, embeddings), throughput/latency testing with request-rate control, and result saving. Use when benchmarking LLM serving performance, measuring TTFT/TPOT, or load testing inference APIs.
Jamie platform help — bot-free AI meeting note-taker, REST API with personal and workspace keys, webhook automations, CRM sync to HubSpot/Salesforce/Attio, MCP server for Claude/ChatGPT/Cursor. Use when setting up Jamie for a sales team, connecting Jamie webhooks to Make.com or a custom endpoint, pulling meeting transcripts and summaries via Jamie API, syncing Jamie action items to Asana or CRM, troubleshooting Jamie not recording or missing speakers, comparing Jamie pricing tiers, or configuring Jamie speaker recognition. Do NOT use for choosing between note-takers (use /sales-note-taker) or reviewing a specific call for coaching (use /sales-call-review).
There's an AI for That (TAAFT) platform help — #1 AI tools directory (42,000+ tools, 3-4M monthly visits, DR76 dofollow, 1M+ newsletter subscribers). Covers tool submissions ($347 paid, free monthly X thread), featured PPC ads (bid-based positioning), highlighted listings, listing optimization, $300 TAAFT-first launch bonus, newsletter inclusion, and ChatGPT plugin API. Use when submitting an AI tool to TAAFT, wondering if the $347 listing is worth it, trying to get featured on TAAFT, want to optimize your TAAFT listing for clicks, comparing TAAFT with Futurepedia or Altern, or need to understand TAAFT's PPC ad system. Do NOT use for multi-directory launch coordination (use /sales-launch-directory). Do NOT use for other AI directories like Altern (use /sales-altern) or Futurepedia (use /sales-futurepedia).
Single-image generation skill for posters, key art, and editorial illustrations. Defaults to gpt-image-2 but is provider-agnostic — the same workflow drives Flux, Imagen, or Midjourney via the active upstream tooling. Output is one or more PNG/JPEG files saved to the project folder.
Upgrade a coded website to award-tier, editorially-crafted design using fal.ai. Takes a local HTML file or a dev-server URL, screenshots it, has an opus-4.7 vision model write a gpt-image-2 edit prompt, uses fal-ai/gpt-image-2/edit to produce the redesigned reference image, then opus-4.7 vision writes a Markdown build-spec with a "Hard constraints" section + a tokens.json. Also supports iterate (screenshot implemented site → delta-spec vs reference) and greenfield generate (brief → mockup → single-file HTML). Invoke when the user says "improve the design", "make it world-class", "redesign this landing page", "upgrade this site", "design pass", or points at a local HTML / dev server for a visual review.
Universal AI voice / text-to-speech skill supporting OpenAI TTS (gpt-4o-mini-tts, tts-1), ElevenLabs multilingual TTS with voice cloning, Bailian Qwen TTS (qwen-tts / qwen3-tts-vd with voice-design custom voices, long-text chunking built in), MiniMax speech-02-hd, SiliconFlow CosyVoice / SenseVoice, and PlayHT 2.0. Use this skill whenever the user asks to read text aloud, synthesize speech, generate narration, create voice-over, dub a script, or turn any text into audio (mp3 / wav / ogg / flac). Typical phrases include "read this aloud", "generate voice for ...", "create a narration of ...", "tts this", "把这段念出来", "做个配音", "合成语音", or mentions of voices / TTS model names like Alloy, Ash, Cherry, Rachel, CosyVoice, PlayHT. Always use this skill even if the user does not specify a provider — pick one from EXTEND.md defaults or available env keys.
Create or update content for the agegr/mindmap-ppt static presentation project from a prose draft, article, speech, report, or notes. Use when Codex needs to turn a written document into the project's project/source.js Markdown mind-map data, choose which nodes need illustrations, generate or request GPT Image 2 illustrations matching the project's restrained presentation style, place assets under project/, and validate the result with npm run check.
Provides image recognition capabilities for non-multimodal models (such as pure text models like deepseek-v4-pro, GLM-5.1, mimo-v2.5-pro, etc.). This skill is automatically triggered when the main model cannot recognize images, when users send screenshots/design drafts/UI screenshots for analysis, or when users say 'Look at this image', 'Analyze this screenshot', 'What's wrong with this image'. It also applies to any scenario where users paste images but the current model does not support image input. Supports simultaneous recognition of multiple images, with primary-backup fallback achieved by configuring multiple image recognition models. It can also be manually triggered using the commands /skill:vision-support or /vision. Iron Rule: The models configured for this skill are only used for image content recognition and will never participate in main logical reasoning. Note: If the current model is itself a multimodal model (such as Claude Sonnet 4, GPT-4o, Gemini, etc. that can directly recognize images), do not use this skill; let the main model recognize directly.
Build and deploy an MCP server from an OpenAPI / Swagger spec using the mcp-use TypeScript SDK. Use this skill whenever the user wants to "turn this OpenAPI spec into an MCP server", "make this API usable from Claude/ChatGPT", "wrap this Swagger doc as MCP tools", "expose this REST API to an LLM", "generate MCP tools from a spec", or pastes/attaches an `openapi.yaml`, `openapi.json`, or `swagger.json` and asks for a Claude-compatible version. Trigger even if the user doesn't say "MCP" — if they describe an existing HTTP API (REST endpoints, an internal service, a third-party API they have a key for) and want an LLM to call it, this is the right skill. Covers spec ingestion (file path, URL, or pasted), operation-to-tool mapping, auth wiring (apiKey, bearer, basic, OAuth bearer), scaffolding with `create-mcp-use-app`, tool generation with proper zod schemas, live testing in the mcp-use inspector, and deploying to Manufact / mcp-use cloud.
Edit opencode.json, AGENTS.md, and config files. Use proactively for provider setup, permission changes, model config, formatter rules, or environment variables. Examples: - user: "Add Anthropic as a provider" → edit opencode.json providers, add API key baseEnv var, verify with opencode run test - user: "Restrict this agent's permissions" → add permission block to agent config, set deny/allow for tools/fileAccess - user: "Set GPT-5 as default model" → edit global or agent-level model preference, verify model name format - user: "Disable gofmt formatter" → edit formatters section, set languages.gofmt.enabled = false