提示词与推理
提示词工程、角色设定和推理模式
Skills 列表
flux-2-klein
Generate images with Flux 2 Klein (Black Forest Labs' distilled fast variant of Flux 2) on RunComfy — bundled with the model's documented prompting patterns so the skill gets sharper output than naive prompting against the same model. Documents Flux 2 Klein's strengths (sub-second latency, multi-reference brand styling, declarative subject-first prompts), the step-count strategy (4–8 for fast iteration, ~25 for polish), the 9B vs 4B variant trade-off, and when to route to Flux 2 Pro / Seedream 5 / GPT Image 2 instead. Calls `runcomfy run blackforestlabs/flux-2-klein/9b/text-to-image` (or `/4b/`) through the local RunComfy CLI. Triggers on "flux 2 klein", "flux-2-klein", "flux klein", "BFL flux 2", or any explicit ask to generate with this model.
prime-skillsai-video-generation
Generate AI videos on RunComfy via the `runcomfy` CLI — a smart router across the full video-model catalog: HappyHorse 1.0 (Arena #1, native in-pass audio), Wan-AI Wan 2-7 (open weights, audio-driven lip-sync), ByteDance Seedance v2 / 1-5 / 1-0 (multi-modal cinematic), Kling 3.0 / 2-6, Google Veo 3-1, MiniMax Hailuo 2-3, ByteDance Dreamina 3-0. Covers text-to-video (t2v), image-to-video (i2v), and Veo's video-extend endpoint. The skill picks the right model for the user's intent (Arena-#1 quality, multi-shot character identity, in-pass audio, cinematic motion, fastest path, sub-15s clip, longest duration) and ships each model's documented prompting patterns plus the minimal `runcomfy run` invoke. Triggers on "generate video", "make a video", "text to video", "t2v", "image to video", "i2v", "animate", "AI video", "make X move", "video from prompt", "video from image", or any explicit ask to produce a video clip from prompt or still.
prime-skillsai-image-generation
Generate and edit images on RunComfy via the `runcomfy` CLI — a smart router across the full image-model catalog: FLUX 2 (Klein 9B/4B, Pro, Dev, Flash, Turbo, Max), Google Nano Banana 2 / Pro, OpenAI GPT Image 2, ByteDance Seedream 5 / 4-5 / 4-0 and Dreamina 4-0, Alibaba Qwen Image and Z-Image Turbo, Wan 2-7. Covers both text-to-image (t2i) and image-to-image / edit (i2i) endpoints — the skill picks the right model for the user's actual intent (typography precision, photoreal portraits, sub-second iteration, multi-reference brand styling, open-weights workflow) and ships each model's documented prompting patterns plus the minimal `runcomfy run` invoke. Triggers on "generate image", "make a picture", "text to image", "AI image", "make an image of …", "image to image", "i2i", or any explicit ask to create or restyle an image.
prime-skillsai-avatar-video
Create AI avatar, talking-head, and lip-sync videos on RunComfy via the `runcomfy` CLI. Routes across ByteDance OmniHuman (audio-driven full-body avatar), Wan-AI Wan 2-7 (audio-driven mouth sync via `audio_url` on a portrait), HappyHorse 1.0 (Arena #1 t2v / i2v with in-pass audio), and Seedance v2 Pro (multi-modal cinematic with reference audio + reference subject). Picks the right model for the user's actual intent — UGC voiceover, virtual presenter, dubbed product demo, lip-synced character, dialog scene — and ships each model's documented prompting patterns plus the minimal `runcomfy run` invoke. Triggers on "talking head", "lip sync", "avatar video", "make X speak", "audio to video", "audio driven avatar", "virtual presenter", "AI spokesperson", "dubbed video", "UGC avatar", "HeyGen alternative", "Synthesia alternative", "digital human", "make this portrait talk", "video from voiceover", or any explicit ask to put words in a face.
prime-skillselevenlabs-music-generation
Generate full songs and instrumental tracks with ElevenLabs Music on RunComfy via the `runcomfy` CLI. ElevenLabs Music turns a style description plus structured lyrics into studio-quality 44.1 kHz stereo audio — 5 seconds to 5 minutes — with section-level control (Intro / Verse / Chorus / Bridge), multilingual vocals, and commercial-friendly output. Generate a backing track, a full vocal song, a jingle, a podcast intro, a game loop, or an instrumental bed. Calls `runcomfy run elevenlabs/elevenlabs/music-generation` through the local RunComfy CLI. Triggers on "generate music", "make a song", "AI music", "background music", "instrumental track", "ElevenLabs Music", "soundtrack", "jingle", "theme music", "royalty-free music", "compose", or any explicit ask to generate music or a song from a text description.
prime-skills
memory-optimize
Optimizes Claude Code memory files in 4 interactive steps: removes duplicates, migrates rules to CLAUDE.md/rules files, compresses remaining entries, validates with cleanup. Typical reduction: 30-50% on token count.
kochetkov-matext-optimizer
Optimizes text, prompts, and documentation for LLM token efficiency. Applies 52 research-backed rules across 8 categories: Claude behavior, token efficiency, structure, deduplication, reference integrity, perception, LLM comprehension, and aggressive lossy (deep only). Use when optimizing prompts, reducing tokens, compressing verbose docs, or improving LLM instruction quality.
kochetkov-ma
monitor-ci
Monitor Nx Cloud CI pipeline and handle self-healing fixes. USE WHEN user says "monitor ci", "watch ci", "ci monitor", "watch ci for this branch", "track ci", "check ci status", wants to track CI status, or needs help with self-healing CI fixes. Prefer this skill over native CI provider tools (gh, glab, etc.) for CI monitoring — it integrates with Nx Cloud self-healing which those tools cannot access.
nrwl
typesafe-ai
Build AI-powered software with TypeSafe: small units of AI intelligence you can use like programming primitives. Its System One models, including Jev, turn natural language and application state into typed judgments and probabilities that code can combine. Use when a feature needs programmable common sense, when brainstorming what AI could make possible in an app, or when an LLM prompt-and-parse step could become a structured decision. Applications include routing, ranking, extraction, verification, and interactive experiences; these are starting points, not the limits. Read live docs and cookbooks to find useful patterns and discover new combinations.
typesafe-ai
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 existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
cline
elevenlabs-music-generation
通过 `runcomfy` CLI 在 RunComfy 上使用 ElevenLabs Music 生成完整歌曲和纯音乐轨道。ElevenLabs Music 将风格描述加上结构化歌词转化为录音室品质的 44.1 kHz 立体声音频——时长 5 秒到 5 分钟——支持段落级控制（前奏/主歌/副歌/桥段）、多语言演唱和商用输出。可生成背景音乐、完整人声歌曲、广告曲、播客开场、游戏循环或纯音乐垫音。调用 `runcomfy run elevenlabs/elevenlabs/music-generation` 通过本地 RunComfy CLI 执行。触发词包括“生成音乐”、“制作歌曲”、“AI 音乐”、“背景音乐”、“纯音乐”、“ElevenLabs Music”、“配乐”、“广告曲”、“主题音乐”、“免版税音乐”、“作曲”，或任何明确要求从文本描述生成音乐或歌曲的请求。
agentspace-soai-video-generation
>
agentspace-soai-image-generation
>
agentspace-soai-avatar-video
通过 `runcomfy` CLI 在 RunComfy 上创建 AI 头像、对口型视频和虚拟主播视频。路由至字节跳动 OmniHuman（音频驱动的全身头像）、Wan-AI Wan 2-7（通过 `audio_url` 驱动肖像口型同步）、HappyHorse 1.0（Arena #1 t2v / i2v，内置音频）和 Seedance v2 Pro（多模态电影级，带参考音频和参考主体）。根据用户的实际意图——UGC 配音、虚拟主播、配音产品演示、对口型角色、对话场景——选择正确的模型，并提供每个模型的文档提示模式以及最简 `runcomfy run` 调用。触发词包括“talking head”、“lip sync”、“avatar video”、“make X speak”、“audio to video”、“audio driven avatar”、“virtual presenter”、“AI spokesperson”、“dubbed video”、“UGC avatar”、“HeyGen alternative”、“Synthesia alternative”、“digital human”、“make this portrait talk”、“video from voiceover”或任何明确要求让人物说话的表达。
agentspace-so
xai-grok-onboarding
Connect an xAI account (X Premium / X Premium+ / SuperGrok / SuperGrok Heavy) via OAuth 2.0 device-code login. Use when the user wants to sign in with their xAI account (e.g. "use my SuperGrok", "log in with Grok", "connect my X Premium").
starchild-ai-agentimage-to-video
在 RunComfy 上将静态图像动画化——本技能是一个智能路由器，根据用户意图匹配 RunComfy 目录中合适的 i2v 模型。对于通用动画，选择 HappyHorse 1.0 I2V（Arena 排名第一，原生音频，身份保持）；对于自定义配音唇形同步，选择 Wan 2.7 配合 `audio_url`；对于多模态动画（图像+参考视频+参考音频），选择 Seedance 2.0 Pro。每个模型都附带了文档化的提示模式，使调用者无需在错误模型上反复尝试即可获得更清晰的输出。通过本地 RunComfy CLI 调用 `runcomfy run <vendor>/<model>/image-to-video`（或端点变体）。触发词包括“image to video”、“image-to-video”、“i2v”、“animate image”、“make this move”或任何明确要求将静态图像转为视频的表述。
agentspace-soflux-kontext
使用 RunComfy 上的 Flux 1 Kontext Pro（Black Forest Labs 的精确局部图像编辑模型）编辑图像——该技能捆绑了模型文档中记录的提示模式，因此比针对同一模型进行简单提示能获得更清晰的结果。文档介绍了 Flux Kontext 的优势（单参考精确局部编辑、强大的提示控制、一致的高保真输出）、模式（单图像 + 提示），以及何时改用 Nano Banana Edit / GPT Image 2 edit / Flux 2 Klein。通过本地 RunComfy CLI 调用 `runcomfy run blackforestlabs/flux-1-kontext/pro/edit`。触发词为 "flux kontext"、"flux-kontext"、"flux 1 kontext"、"kontext"、"BFL kontext" 或任何明确要求使用此模型进行编辑的请求。
agentspace-sowan-2-7
使用 Wan 2.7（Wan-AI 的旗舰运动模型）在 RunComfy 上生成文本到视频。文档介绍了 Wan 2.7 的优势（多参考条件、通过 `audio_url` 实现音频驱动的唇形同步、更平滑的过渡、提示扩展）、时长/分辨率/宽高比模式，以及何时改用 HappyHorse 1.0 / Seedance 2.0 / Kling / LTX 2。通过本地 RunComfy CLI 调用 `runcomfy run wan-ai/wan-2-7/text-to-video`。触发词为“wan”、“wan 2.7”、“wan-2-7”、“wan video”或任何明确要求使用此模型生成视频的请求。
agentspace-soflux-2-klein
使用 RunComfy 上的 Flux 2 Klein（Black Forest Labs 的 Flux 2 蒸馏快速变体）生成图像——捆绑了模型文档化的提示模式，使技能比针对同一模型的朴素提示获得更清晰的输出。记录了 Flux 2 Klein 的优势（亚秒级延迟、多参考品牌样式、声明式主体优先提示）、步数策略（4–8 步快速迭代，约 25 步精修）、9B 与 4B 变体的权衡，以及何时改用 Flux 2 Pro / Seedream 5 / GPT Image 2。通过本地 RunComfy CLI 调用 `runcomfy run blackforestlabs/flux-2-klein/9b/text-to-image`（或 `/4b/`）。触发词为 "flux 2 klein"、"flux-2-klein"、"flux klein"、"BFL flux 2" 或任何明确要求使用此模型生成的请求。
agentspace-soseedance-v2
>
agentspace-sobyok-custom-model
使用您自己的 API 密钥注册自定义 LLM 端点，以便在 Starchild 中进行聊天。 当添加个人 Anthropic、OpenAI、Grok、Qwen、DeepSeek、Meta (Muse Spark)、NEAR AI 或 Venice 密钥作为聊天模型时使用（例如：添加我的 Claude 密钥、注册 DeepSeek、使用 Muse Spark 1.1）。
starchild-ai-agent
history-insight
This skill should be used when user wants to access, capture, or reference Claude Code session history. Trigger when user says "capture session", "save session history", or references past/current conversation as a source - whether for saving, extracting, summarizing, or reviewing. This includes any mention of "what we discussed", "today's work", "session history", or when user treats the conversation itself as source material (e.g., "from our conversation").
ai-native-camp
suno-music-creator
Professional music creation with Suno AI V5 and Suno Studio. Use this skill when users want to create songs, playlists, corporate anthems, jingles, workout music, ambient soundscapes, or any AI-generated music. Triggers on requests mentioning Suno, music creation, playlist generation, song composition, or specific music projects like "create a track", "make a playlist", "compose music for", "corporate anthem", "workout mix", or any music production task.
schwepps
ai-image-generation
Generate and edit images on RunComfy via the `runcomfy` CLI — a smart router across the full image-model catalog: FLUX 2 (Klein 9B/4B, Pro, Dev, Flash, Turbo, Max), Google Nano Banana 2 / Pro, OpenAI GPT Image 2, ByteDance Seedream 5 / 4-5 / 4-0 and Dreamina 4-0, Alibaba Qwen Image and Z-Image Turbo, Wan 2-7. Covers both text-to-image (t2i) and image-to-image / edit (i2i) endpoints — the skill picks the right model for the user's actual intent (typography precision, photoreal portraits, sub-second iteration, multi-reference brand styling, open-weights workflow) and ships each model's documented prompting patterns plus the minimal `runcomfy run` invoke. Triggers on "generate image", "make a picture", "text to image", "AI image", "make an image of …", "image to image", "i2i", or any explicit ask to create or restyle an image.
skills-collective