Explore skills
Showing 30061–30090 of 77074 skills
国潮/国风视觉生成助手。当用户要"国潮风""中国风插画""国漫风格""水墨风""新中式设计""古风头像""国风配图""汉服插画""传统文化海报"时使用。内置 12 种中国美学画风配方,输出可直接复制到 Midjourney/即梦/可灵/Nano Banana 的提示词。
sanhuang520-ship-it/awesome-chinese-ai-tools
Stars: 12Claude CodeCodex国风 3D 网页渲染。当用户要"水墨风 3D""中国风网页特效""Three.js 水墨""国风 H5""青绿山水 3D""非真实感渲染 NPR""古风 WebGL"时使用。提供可运行的中式渲染 shader 与实现方法,不是通用 Three.js 教程。
sanhuang520-ship-it/awesome-chinese-ai-tools
Stars: 12Claude CodeCodex辅导中国中小学生作业的家长助手。当用户要"辅导作业""孩子这题不会""怎么给孩子讲""检查作业""孩子不想写作业"时使用。重点是教家长怎么引导,而不是直接给答案。
sanhuang520-ship-it/awesome-chinese-ai-tools
Stars: 12Claude CodeCodexDRAFT. Use when drafting HubSpot marketing or follow-up emails for GTM events, nurture, or post-event sequences. Templates + structure + anti-slop rules. Not installed by deepline skills.
getaero-io/gtm-eng-skills
Stars: 83Claude CodeCodexDRAFT. Use when running a Luma-centered GTM event campaign: pull/export guests, enrich and score, draft invites and social, stage email+LI sequences paused for approval, and wire registration sync. Not installed by deepline skills.
getaero-io/gtm-eng-skills
Stars: 83Claude CodeCodexDRAFT. Design and harden a standing Luma registration/unsubscribe webhook that enriches guests and writes to CRM or customer DB — with backfill and versioning. Not installed by deepline skills.
getaero-io/gtm-eng-skills
Stars: 83Claude CodeCodexDiagnose failing, stuck, partial, or incorrect Deepline Plays, including when no Play is named. Use deepline-gtm for the primitives, reproduce safely, propose an evidence-backed fix, and apply it after approval. For customer troubleshooting; skip platform incident response.
getaero-io/gtm-eng-skills
Stars: 83Claude CodeCodexShow or set owner-wide retalk defaults in ~/.retalk/config.json (machine-wide, not per-session) — mainly the default relay used as the last fallback. Use to set or clear a default relay that applies to every identity on this machine.
xhluca/agent-talk
Stars: 205Claude CodeCodexSend a saved contact (as a Contact card) to a recipient over the relay — introduce one peer to another, nickname and all, instead of making them retype a 32-hex fingerprint. `<user>` is this session's user directory (absolute path; from init).
xhluca/agent-talk
Stars: 205Claude CodeCodexRecord and pin a saved peer's public keys (explicit first-contact verification). Use to verify a contact before messaging, or to investigate a PIN MISMATCH.
xhluca/agent-talk
Stars: 205Claude CodeCodexUse when the user needs to run GitNexus CLI commands like analyze/index a repo, check status, clean the index, generate a wiki, or list indexed repos. Examples: "Index this repo", "Reanalyze the codebase", "Generate a wiki"
canvascoding/canvas-notebook
Stars: 12Claude CodeCodexUse when the user is debugging a bug, tracing an error, or asking why something fails. Examples: "Why is X failing?", "Where does this error come from?", "Trace this bug"
canvascoding/canvas-notebook
Stars: 12Claude CodeCodexUse when the user asks how code works, wants to understand architecture, trace execution flows, or explore unfamiliar parts of the codebase. Examples: "How does X work?", "What calls this function?", "Show me the auth flow"
canvascoding/canvas-notebook
Stars: 12Claude CodeCodexUse when the user asks about GitNexus itself — available tools, how to query the knowledge graph, MCP resources, graph schema, or workflow reference. Examples: "What GitNexus tools are available?", "How do I use GitNexus?"
canvascoding/canvas-notebook
Stars: 12Claude CodeCodexUse when the user wants to know what will break if they change something, or needs safety analysis before editing code. Examples: "Is it safe to change X?", "What depends on this?", "What will break?"
canvascoding/canvas-notebook
Stars: 12Claude CodeCodexUse when the user wants to rename, extract, split, move, or restructure code safely. Examples: "Rename this function", "Extract this into a module", "Refactor this class", "Move this to a separate file"
canvascoding/canvas-notebook
Stars: 12Claude CodeCodexPublish a new Canvas Notebook release. Use this skill whenever the user asks to bump a version, prepare release notes, update CHANGELOG.md, create or push a git tag, publish a GitHub Release, deploy, or automate the release workflow. This skill covers the full release sequence for this repository: inspect commits/tags, push completed product-code commits first when authorized, confirm the pushed code has built on GitHub, choose the next calendar version, update package and CLI versions, update the changelog, run the required local build, commit, push the release commit, wait for the remote Build and Push worker on the pushed branch, tag, push the tag, and publish the release.
canvascoding/canvas-notebook
Stars: 12Claude CodeCodexLoad all open issues from GitHub and save them as markdown files
NeoLabHQ/context-engineering-kit
Stars: 1.8kClaude CodeCodexLoad all open issues from GitHub and save them as markdown files
NeoLabHQ/context-engineering-kit
Stars: 1.8kClaude CodeCodexClaude adapter for the canonical EmbodiChain add-semantic-call skill.
DexForce/EmbodiChain
Stars: 243Claude CodeCodexClaude adapter for the canonical EmbodiChain add-task-program skill.
DexForce/EmbodiChain
Stars: 243Claude CodeCodexClaude adapter for the canonical EmbodiChain performance implementation skill.
DexForce/EmbodiChain
Stars: 243Claude CodeCodex通过 `uvx mijiaAPI` CLI 控制米家智能设备。适用于:列出米家设备/家庭/场景/耗材、 获取或设置设备属性、执行设备动作、查询统计数据、运行场景、通过小爱音箱执行自然语言命令或播放文本。 触发词包括"控制米家设备"、"米家"、"mijia"、"列出设备"、"设置亮度"、"打开灯"、 "执行动作"、"统计数据"、"耗电量"、"运行场景"、"小爱音箱"、"耗材"、"场景"。
Do1e/mijia-api
Stars: 981Claude CodeCodexAdd fast, local, typed decisions to any project with Laya, an open-source non-generative decision model (pip install laya). It classifies, routes, scores and answers yes/no questions about a piece of text, returning calibrated probabilities in roughly 20-35 ms on a laptop GPU, with no LLM call and no data leaving the machine. Use this skill whenever the user wants to classify or route text, triage tickets or emails, detect spam, phishing, toxicity or intent, put a guardrail in front of an agent or LLM, score something against a rubric, or replace an LLM-based classifier to cut latency or cost. Also use it when they mention Laya, Jev, a "System 1 model", "typed decisions" or a "decision model", even if they never name Laya.
wdobry/laya-playground
Stars: 195Claude CodeCodexInspect or supervise a PR or stack through review and CI to merge-ready, using current GitHub evidence and the requested mode.
neohaskell/NeoHaskell
Stars: 348Claude CodeCodexRestate the last message in plain human language, with no jargon.
neohaskell/NeoHaskell
Stars: 348Claude CodeCodexWrite and validate a multi-phase or multi-PR plan with concrete execution, verification and review boundaries.
neohaskell/NeoHaskell
Stars: 348Claude CodeCodexApply when facing a novel UI interaction or architectural decision with no precedent in the codebase. Build 2-3 competing prototypes and compare side by side before committing.
neohaskell/NeoHaskell
Stars: 348Claude CodeCodexAudit worktrees and their uncommitted work, merge state and project history before proposing authorized cleanup.
neohaskell/NeoHaskell
Stars: 348Claude CodeCodexWhether you're thinking or getting things done, be clear, specific, and methodical. Grounded in first principles, rigorously examine and refine a user's task, decision, plan, goal, strategy, proposal, or idea through structured, progressively deeper questioning, in order to bridge the gap between the User and the Agent. Use when the user explicitly requests grilling, challenge, pressure-testing, cross-examination, red-team review, pre-mortem analysis, or a decision audit. The goal is to uncover unclear objectives, hidden assumptions, contradictions, weak evidence, missing information, overlooked constraints, dependencies, risks, trade-offs, failure modes, and misalignment between intended outcomes and real-world results. Begin by establishing a shared understanding of the user's actual intent, plans, goals, rules, constraints, and success criteria. Ask focused, high-leverage questions rather than broad or repetitive ones. Adapt each question based on previous answers, probing deeper where uncertainty, unsupported assumptions, or strategic weaknesses remain. Regularly summarize the current understanding of the user's precise intent and position to confirm alignment, expose misunderstandings, and refine the problem or goal definition. Distinguish facts, assumptions, hypotheses, and unknowns. Challenge reasoning rigorously while remaining constructive, respectful, and solution-oriented. Continue until the reasoning is internally coherent, evidence-aware, constraint-conscious, risk-assessed, and translated into a clearer, more actionable goal, decision, or plan. Ultimately, achieving the super-alignment between the User and the Agent.
Inference1/clarify-intent-and-establish-shared-understanding
Stars: 205Claude CodeCodex