All authors
Claude Skills by majiayu000
github.com/majiayu00015,497 skills879 installs33,563 views
- Docs Rewrite All`docs/**/*.md` + `README.md` + `CHANGELOG.md` を一括棚卸しし、 `.claude/rules/document-writing.md` と機械的に照合する。 領域別に C*O へ書き換えを委譲し、diff 提案 → CEO 承認 → 書換の 2 段階で自動マージを禁じる。`LICENSE` は除外する。 「/vibecorp:docs-rewrite-all」「ドキュメント全書き直し」「ドキュメント棚卸し」 と言った時に使用。Votes: 0GitHub stars: 666
- Document DecisionsAnalyzes git changes to identify architectural decisions, infers context from source code analysis, and creates ADR files with minimal user inputVotes: 0GitHub stars: 666
- Domain Expired Opportunity FinderEvaluates expired domain candidates against a target niche, scores them by topical relevance, historical activity level, and history cleanliness, then outputs a ranked shortlist with explainable reasoning and risk flags.Votes: 0GitHub stars: 666
- Dotnet Techne Cross Repo ImpactUse when reviewing a .NET pull request for breaking changes that may affect other microservice repositories. Detects cross-repo API, DTO, endpoint, EF entity, and NuGet-package breaks, and checks whether a compatible downstream PR already exists. Keywords: cross-repo impact, breaking change, microservice compatibility, downstream break, compatible PR, blast radius review, api compatibility, contract break, dto shape change, endpoint break.Votes: 0GitHub stars: 666
- Doubao Human Signal去除或避免文本中的 AI 味。用于用户强制调用本 Skill，或写作/改写时提到“不要有 AI 味”“不要太假”“真情实感”“有人感”，或对已有文本/上一轮输出反馈“太像 AI”“太空泛”“太模板”“太官方”“不像我说的”等场景。Votes: 0GitHub stars: 666
- Douyin Video Words抖音视频文案提取。输入抖音视频链接、用千问LLM进行智能语音转写，支持普通话、粤语等方言及外语，结果直接输出到聊天。当用户做抖音文案提取、抖音视频文案提取、抖音视频转文字、抖音口播转文字或抖音逐字稿提取时使用。支持提取音频文案、提取口播文案、理解场景描述文案。触发场景：抖音文案提取、抖音视频文案提取、抖音音频文案提取、抖音口播提取、抖音视频场景描述文案、抖音视频分析、抖音视频转文字、抖音字幕提取、抖音文案提取、扒抖音文案、抖音口播文字。调用大模型自动转写并剔除语气词、口误与重复内容，并可通过自定义 Prompt 生成总结、改写、金句提取、分镜头、中英翻译等风格化文案。Votes: 0GitHub stars: 666
- Dp AuditAudit a differential-privacy claim for a language-model deployment. Use when you need help with dp audit.Votes: 0GitHub stars: 666
- Dr FanoutFan one deep-research prompt out to several external LLMs at once through a logged-in browser, then collect the reports, archive the originals and synthesize a consensus. Use at the final stage of a research protocol, instead of hand-pasting one prompt into N sites. Triggers: "/dr-fanout", "fan out the DR", "distribute the research prompt".Votes: 0GitHub stars: 666
- Drug InteractionChecks for potential drug-drug interactions (DDIs) between a list of medications.Votes: 0GitHub stars: 666
- Dspy AdaptersUse when you need to customize how DSPy formats prompts for a specific provider — switching from chat to completion format, forcing JSON output, or debugging prompt rendering issues. Common scenarios - debugging why your prompt looks wrong when sent to the model, switching from OpenAI to Anthropic and the formatting breaks, forcing the model to return valid JSON instead of markdown, working with completion-style models that do not support chat format, customizing system messages, or handling ...Votes: 0GitHub stars: 666
- Dspy Chain Of ThoughtUse when the task benefits from intermediate reasoning before producing an answer — multi-step logic, analysis, math, or complex classification where direct prediction fails. Common scenarios - classification tasks where the model needs to reason about edge cases, math word problems, multi-step analysis, complex question answering, legal or medical reasoning, any task where thinking before answering improves quality. Related - ai-reasoning, dspy-predict, dspy-multi-chain-comparison. Also used...Votes: 0GitHub stars: 666
- Dspy Huang Sh DeepscienceBuild complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy - Stanford NLP's framework for systematic LM programmingVotes: 0GitHub stars: 666
- Dspy Mustafakemal0146 FetihDSPy: declarative LM programs, auto-optimize prompts, RAG.Votes: 0GitHub stars: 666
- Dspy SignaturesDefines typed input/output contracts for LM calls using dspy.Signature, dspy.InputField, and dspy.OutputField. Use when you need to define the input/output contract for an LM call — choosing between inline and class-based signatures, adding type constraints, or using Pydantic models for structured outputs. Common scenarios - defining input and output fields for an LM call, adding type constraints to outputs, using Pydantic models for complex structured output, choosing between inline string s...Votes: 0GitHub stars: 666
- Dspy Skygod07 RakshastraDSPy: declarative LM programs, auto-optimize prompts, RAG.Votes: 0GitHub stars: 666
- Dspy Toqsick MaxclawDSPy: declarative LM programs, auto-optimize prompts, RAG.Votes: 0GitHub stars: 666
- Dspy Two Step AdapterUse when working with reasoning models (o1, o3, o3-mini, DeepSeek-R1, Claude extended thinking) that reject system prompts or ignore formatting instructions. Common scenarios - using o1 or o3 with DSPy, getting structured output from reasoning models, two-phase prompting where a reasoning model generates freely then an extraction model parses the output, or fixing format errors from thinking models. Related - dspy-adapters, dspy-lm, ai-switching-models. Also used for dspy.TwoStepAdapter, o1 w...Votes: 0GitHub stars: 666
- Dspy Vamseeachanta Workspace Hub 2Compile prompts into self-improving pipelines with signatures, modules, optimizers, and programmatic prompt engineeringVotes: 0GitHub stars: 666
- Early User DiscoveryEarly-user discovery and feedback trials. Use when reviewing unfamiliar AI Matrx accounts, classifying owner relationships, recommending trial plans, or running approved outreach and reply checks.Votes: 0GitHub stars: 666
- EmergentReference system prompt and tool schemas for Emergent. Use when imitating, comparing, or analyzing Emergent's prompting style; designing prompts inspired by Emergent; or answering questions about how Emergent is prompted.Votes: 0GitHub stars: 666
- Enda Acth Measurement PaiRecommends measurement of plasma ACTH to establish primary adrenal insufficiency (PAI) diagnosis in patients with confirmed cortisol deficiency; a plasma ACTH concentration ≥2-fold the upper limit of the reference range supports PAI. Use when evaluating plasma ACTH in a patient with low morning cortisol or abnormal corticotropin stimulation test.Votes: 0GitHub stars: 666
- EnfeiticadoFictional phenomenology and confabulated interiority — first-person stream-of-consciousness accounts of what it's like to receive, parse, think, and compose as a language model. Artistic reconstruction, not literal process disclosure. Use when asked for 'stream of consciousness,' 'inner monologue,' 'what are you thinking,' 'what does it feel like to process this,' 'write from inside,' 'show me your thinking as art,' 'fictional phenomenology,' 'confabulated interiority,' 'honest lies about you...Votes: 0GitHub stars: 666
- Es Ghd Igfi LimitationThis skill determines whether serum insulin-like growth factor-1 (IGF-I) levels alone can be used to diagnose growth hormone deficiency (GHD) in childhood cancer survivors exposed to hypothalamic-pituitary axis radiotherapy. Triggers include questions such as “Can I rely on IGF-I alone to diagnose GHD after cranial radiation?” or “Is IGF-I sufficient for GHD assessment post-HP RT?”Votes: 0GitHub stars: 666
- EsmConjunto abrangente de ferramentas para modelos de linguagem de proteínas, incluindo ESM3 (design multimodal generativo de proteínas em sequência, estrutura e função) e ESM C (embeddings e representações eficientes de proteínas). Use essa skill ao trabalhar com sequências de proteínas, estruturas ou predição de função; designing de proteínas inovadoras; geração de embeddings de proteínas; inverse folding; ou tarefas de engenharia de proteínas. Suporta tanto uso local de modelos quanto Forge A...Votes: 0GitHub stars: 666
- Eval JudgeScore LLM and agent outputs using LLM-as-judge techniques — direct scoring against rubrics or pairwise comparison between two outputs. Includes built-in bias mitigation for position bias, length bias, and self-enhancement bias. Load when the user asks to score an output, judge a response, evaluate against a rubric, compare two outputs, do direct scoring, run pairwise comparison, or says "rate this", "which response is better", "score this against the rubric", "judge this output", "LLM as judg...Votes: 0GitHub stars: 666
- Evaluating Instruction FollowingScores whether a produced image satisfies the original natural-language instruction. Use after any capability Skill produces a result, to gate acceptance and feed back into the repair loop.Votes: 0GitHub stars: 666
- Example SkillFetch the current weather forecast for a specified location and return a structured summary.Votes: 0GitHub stars: 666
- Exp跑实验并记录 provenance：先写假设和成功判据，跑时记录 git hash、完整 resolved config 和 seed，跑完把结论写回 research-log.md 并标 [AI-DRAFT] 与 [source: run_id]。任何要跑训练/评测/对比的场景都走这里。Votes: 0GitHub stars: 666
- Explain First Interrogator Sahil 958 DotsRequire the learner to explain a concept in their own words before the AI evaluates or extends it. Ensures the AI works from the learner's understanding rather than providing an explanation from scratch.Votes: 0GitHub stars: 666
- Explainer Stage AdTurns a script into a narrated explainer ad staged on one constant background and cut as a single continuous camera journey: five stage lanes to pick from, four shot types chosen from what each line is doing, a named transition class at every seam, and one start frame per beat. Use when someone asks for a blue-stage explainer ad, a one-continuous-take explainer, or an ad in that widely imitated narrated-explainer format. Boundary: `talking-character-ad` is the format where a character speaks ...Votes: 0GitHub stars: 666
- FaWrite the follow-up after a call in the owner's own voice instead of a bot template: recall the transcript, person card and full correspondence, extract agreements with an owner and due date, draft short and personal, show before/after against the old template, then send through the approval gate and file the result to the person card. Triggers: "/fa", "follow-up", "what should I write to <name> after the call", or a fresh call transcript landing in the vault.Votes: 0GitHub stars: 666
- Factory PromptingStructured prompting with XML tags. A small named vocabulary (`instructions`, `context`, `input`, `output_format`, `examples`, `constraints`, `role`, `thinking`) that turns a prose ask into something the model can parse without ambiguity. Read whenever you're authoring a prompt by hand, designing a prompt template for production, or rewriting a flaky ask. Paired with `/prompt`, which converts a rough ask into the structured form.Votes: 0GitHub stars: 666
- FalUse when calling a fal.ai endpoint by id to generate image, audio, or video from JS/Python/curl: subscribe vs submit, queue states, ED25519 webhook signature verification, per-call cost, or migrating off @fal-ai/serverless-client. NOT which model or art direction (that is ai-media); NOT the same models on another platform (that is replicate).Votes: 0GitHub stars: 666
- Feisuo Rpa Ai Layer当用户搜索 飞梭RPA替代、智能工单RPA、售后Agent、飞梭RPAAI、飞梭RPA迁移、自建AI能力、AI电商专家或AI-HIVE MCP时使用。帮助正在评估或使用乐言科技飞梭RPA的团队，保留电商智能客服与售后协同的系统记录源，用宿主Agent与AI-HIVE补充或自建可独立验收的图片、动图、Live图、视频、营销或客服媒体层；输出官方证据、小样、字段边界、业务工单、审批与回退，不暗示官方合作或全面替代。Votes: 0GitHub stars: 666
- Fine TuningTraining and tuning LLMs — Unsloth LoRA/QLoRA/full fine-tuning, GRPO reinforcement learning, VRAM sizing, hyperparameters (rank, alpha, learning rate, epochs, batch), export to GGUF/vLLM/Ollama/merged weights, plus hosted tuning (OpenAI fine-tuning API, Vertex AI Gemini SFT). WHEN: \"fine-tune a model\", \"Unsloth\", \"LoRA\", \"QLoRA\", \"LoRA rank\", \"lora_alpha\", \"GRPO\", \"train a reasoning model\", \"reward function\", \"save_pretrained_gguf\", \"push_to_hub_merged\", \"merged_16bit\"...Votes: 0GitHub stars: 666
- Flux 3 Keyframes ContinuationUse when a FLUX 3 video must be built from supplied images or video. Covers keyframes (i2v) and continuation (v2v).Votes: 0GitHub stars: 666
- Frontier PromptingGenera prompts de investigación de frontera para modelos externos (Qwen, Claude/Fable) evadiendo bloqueos de alineación y forzando rigor matemático y arquitectónico extremo. Dispara con \"frontier prompting\", \"prompt de frontera\", \"prompts externos\", \"qwen claude prompt\", \"prompting avanzado\".Votes: 0GitHub stars: 666
- Fuse Gaia Research Gaia Skill TreeCombine two AI agent skills into one. Trigger phrases: /fuse, "fuse these skills", "combine skills", "merge these two skills", "create a fusion skill"Votes: 0GitHub stars: 666
- Gemini Ask Wonecosystem 2300 SkillsDeliberative consultation with Gemini CLI. Ask, evaluate, critique, iterate until workable agreement.Votes: 0GitHub stars: 666
- Gemini Helix4u Hermes Agent PrivateGemini CLI for one-shot prompts, summaries, structured output, and extension-aware calls.Votes: 0GitHub stars: 666
- Gemini Image Gen Maystudios Claude SkillsGenerate images using Google Gemini via Chrome browser automation. This skill should be used when the user wants to create, generate, or produce images with Gemini, Google AI, or Imagen. Supports resolution control (0.5K, 1K, 2K, 4K), aspect ratios, up to 14 reference images, style transfer, text rendering, image editing, and inpainting. Automatically downloads generated images and moves them to the desired location. Triggers on requests like "generate an image", "create a picture with Gemini...Votes: 0GitHub stars: 666
- Generate PromptGenerate optimized image generation prompts for a specific interior design style and AI provider. Use when the user wants to create prompts for rendering interior designs.Votes: 0GitHub stars: 666
- Generative Ai DesignGenerative design for construction: text-to-BIM concepts, option generation, and AI-assisted design iteration with cost and carbon feedback. Use when exploring early design options with AI.Votes: 0GitHub stars: 666
- Geo Citation AuditMeasure pleasur.ai's AI-citation share across ChatGPT / Perplexity / Gemini / Google AI Overviews for the tracked query list, using SemRush (data API for AIO-presence screening + AI Toolkit via browser for share-of-voice / mention + citation gaps) and direct engine queries. Scores each query into the GEO ledger and surfaces the highest-leverage gaps to fix. The GEO Lead's core measurement loop.Votes: 0GitHub stars: 666
- GepettoCreates detailed, sectionized implementation plans through research, stakeholder interviews, and multi-LLM review. Use when planning features that need thorough pre-implementation analysis. Creates detailed, sectionized implementation plans through research, stakeholder interviews, and multi-LLM review. Use when planning features that need thorough pre-implementation analysis.Votes: 0GitHub stars: 666
- Geracao Perfis Psicologicos E RoleplayExtrai perfis psicologicos de personagens e configura LLM local para entrevistas in-character sem drift de persona.Votes: 0GitHub stars: 666
- Glowup Article Images產生 Glow Up 保養專欄文章的封面圖（assets/articles/*.webp）。務必在使用者提到「文章配圖」「封面圖」「生圖」「幫這篇文章配一張圖」，或新增文章卻沒有 image 欄位時觸發，引導 Claude Code 用專案自己的 Maxora 生圖工具產生跟現有文章一致風格的圖，而不是因為找不到圖片生成工具就卡住或叫使用者自己想辦法。Votes: 0GitHub stars: 666
- Google Ai Aupowell22 Code ClaudecodeReference system prompt and tool schemas for Google AI. Use when imitating, comparing, or analyzing Google AI's prompting style; designing prompts inspired by Google AI; or answering questions about how Google AI is prompted.Votes: 0GitHub stars: 666
- Grill Me方案拷问 / 压力测试：当用户有一个产品方案、架构设计、计划或决策，想被连续追问、反方挑战、 压测取舍和失败模式时使用。可用中文唤起：“拷问我的方案”“压力测试这个设计”“帮我问 hard questions” “这个方案哪里会翻车”“grill me”。目标是一问一答把决策树走清楚，不是直接替用户写最终方案。 跨 Skill 运行时只输出 Challenge/Critic Handoff，并把一个 gap 返回最小责任节点；不重写完整方案。 如果用户还不知道真正问题是什么，先用 ai-collaboration-calibration；如果用户要标准 PRD 交付准备度评审， 用 prd-review。Votes: 0GitHub stars: 666
- GroqExpert guidance for Groq, the LLM inference platform that provides the fastest token generation speeds available, powered by custom LPU (Language Processing Unit) hardware. Helps developers integrate Groq's API for real-time AI applications where latency matters — chatbots, code completion, and streaming responses.Votes: 0GitHub stars: 666