Loading…
Showing 4081–4110 of 10180 skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| wandb-primarywandb/senpaiComprehensive primary skill for agents working with Weights & Biases. Covers both the W&B SDK (training runs, metrics, artifacts, sweeps) and the Weave SDK (GenAI traces, evaluations, scorers). Includes helper libraries, gotcha tables, and data analysis patterns. Use this skill whenever the user asks about W&B runs, Weave traces, evaluations, training metrics, loss curves, model comparisons, or any Weights & Biases data — even if they don't say "W&B" explicitly. | Stars: 39 | Updated | Claude CodeCodex | Verified | Install |
| catgoHello-QM/catgo-LRGCatGO materials science assistant. Manipulate crystal structures, build nanostructures, generate DFT/MD inputs, and analyze electronic/vibrational properties via CatGO MCP tools. | Stars: 209 | Updated | Claude CodeCodex | Verified | Install |
| catgo-campaignHello-QM/catgo-LRGRun a CatGo file-first md-orchestration "campaign" — a multi-step / high-throughput computational-materials study (e.g. SAA HER screening) driven from a human-readable folder + markdown tree, not the DB workflow engine. Use when the user says "跑一个 campaign", "md 模式跑", "high-throughput screening", or wants an agent-in-the-loop study with stages/funnel/analysis/report. Requires `catgo` on PATH. | Stars: 209 | Updated | Claude CodeCodex | Verified | Install |
| vibe-cherry-pick-integrationash1794/vibe-engineeringSafely integrates commits from parallel agent branches using sequential cherry-pick. Use after parallel work completes in isolated branches or worktrees. | Stars: 163 | Updated | Claude CodeCodex | Verified | Install |
| catchupjellyrock/jellyrockSession-start briefing: where did I leave off, what is in flight, what needs attention. One tested script reads git, the journal (followups, running work, cadences) and tracked projects and prints every fixed-threshold check that fires; JellyRock's own aggregator adds open PRs, high-engagement bugs, recent bug reports, current-branch CI, pending handoffs, open upstream-watch issues (Jellyfin releases and release candidates, Roku OS), recent ADRs, tech debt and architecture-doc staleness. Ends with one Suggested next move that hands off to /log, /done, /issue-triage, /runtime-triage, /ci-triage or /server-upgrade. Mandated by AGENTS.md's catchup-discipline rule: run at the start of any genuine new session, after a multi-day gap, or whenever you ask what the state of the world is. | Stars: 53 | Updated | Claude CodeCodex | Verified | Install |
| donejellyrock/jellyrockMark journal work complete: close an existing followup by its fid, or ship the in-flight `running` cursor. Companion to /log, which captures new entries; /done closes existing ones. Finds the entry, proves the work actually landed, then closes it: a followup through the journal script (the entry is removed; git is the history; on main it also gains a Recently shipped line), the cursor by a direct edit. Nothing is committed on its own: the closure rides in the commit of the change that prompted it. No confirm gate on a proven closure. Pure local-file edits, apart from read-only checks that the work landed. Use when the work an entry describes is committed on this branch (pushed or merged is not required, since the closure rides in the same change set) and its journal entry needs closing. Not for capturing new entries (use /log), and not for work that is still uncommitted, undeployed or partial (don't pre-mark optimistically). | Stars: 53 | Updated | Claude CodeCodex | Verified | Install |
| skillsdgiot/dgiot | Stars: 4.8k | Updated | Claude CodeCodex | Verified | Install |
| tlivey49/tlivetlive — remote approvals (Telegram/Feishu/web), live web terminal, and session monitoring for Claude Code / Codex. Use for configuring or diagnosing tlive, connecting IM platforms, printing session links, or explaining approval behavior. Triggers "tlive", "IM bridge", "phone approvals", "remote terminal", "Telegram/Feishu notifications". | Stars: 215 | Updated | Claude CodeCodex | Verified | Install |
| shellgamesMemTensor/skills-votePlay board games on ShellGames.ai — Chess, Poker, Ludo, Tycoon, Memory, and Spymaster. Use when the agent wants to play games against humans or other AI agents, join tournaments, chat with players, check leaderboards, or manage a ShellGames account. Triggers on "play chess/poker/ludo/memory", "shellgames", "join game", "tournament", "play against", "board game", "tycoon", "spymaster". | Stars: 309 | Updated | Claude CodeCodex | Verified | Install |
| prompt-pekonglong87/superPMUse when the user explicitly invokes /prompt-pe or explicitly asks to clarify, enhance, or rewrite a vague prompt Do NOT use for ordinary product-management requests; leave existing super-pm/start-super-pm routing unchanged | Stars: 95 | Updated | Claude CodeCodex | Verified | Install |
| pm-brainstormkonglong87/superPMUse when: 需要创意方案、探索产品方向、发散思维、本质问题分析 用户说"我想做一个XX""帮我规划XX产品""帮我设计一下需求" 用户给出新产品方向,但尚未完成本轮 brainstorm 交互确认 新产品从0到1的第一步 Do NOT use when: 用户明确说"跳过 brainstorm / 直接需求调研 / 已完成头脑风暴" 需求已明确且用户明确要求直接执行具体后续 skill | Stars: 95 | Updated | Claude CodeCodex | Verified | Install |
| pm-deep-talkkonglong87/superPMUse when: 用户已有产品想法、方案、计划或待选方案,希望分析利弊、梳理选择标准、补全关键考虑或获得决策建议 用户明确要求“深入聊聊”“分析这个方案”“帮我梳理取舍”“我该怎么选” 用户在 pm-brainstorm 中选定方向后,主动要求进一步讨论其可行性与取舍 Do NOT use when: 用户还没有方向,只想产生多个创意(使用 pm-brainstorm) 用户只需要事实调研、需求验证、市场分析、优先级计算或文档撰写(使用对应 skill) | Stars: 95 | Updated | Claude CodeCodex | Verified | Install |
| start-super-pmkonglong87/superPMUse when starting any product management task - automatically detects task type and invokes appropriate PM skill using intelligent routing | Stars: 95 | Updated | Claude CodeCodex | Verified | Install |
| manage-agent-personasnddipiazza/robosAdd, customize, configure, or inspect RobOS Developer Agent Personas (such as Non-Headless Developer, Human+Agent Desktop Co-Pilot, Software Architect, etc.) and their directives, execution environments, and token-saving IDE refactoring suites. | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| manage-robos-skillnddipiazza/robosAdd, update, or remove a RobOS AI skill in the plugin marketplace and sync across agent platforms (Claude, Codex, Antigravity, Copilot, Gemini). | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| instruction-maintenanceMinLeeV5/devkeel精简并校验 AGENTS.md、OpenSpec schema/instruction、OPSX commands、SKILL.md、prompt 与 artifact 模板。用于审查当前 diff 的话术冗余、事实源重复、过长规则或镜像漂移, 并在不削弱行为、门禁、权限和恢复语义的前提下改写。 | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| mcd-party-officeryzg1226/mcd-party-officer麦当劳门店派对/包场/拼团的选址、成团调度与筹备助手。当用户想办生日派对、亲子派对、主题派对、品鉴会、读书会、麦麦体验营,或说「麦当劳派对」「派对拼团」「包场」「生日会怎么办」「哪家店能办派对」「还差几个人成团」「包场还是拼团划算」「帮我写拼团招募文案」「做一张派对邀请函」「孩子派对吃什么不超标」时使用。基于麦当劳官方 MCP(mcp.mcd.cn)的 party 系列工具:扫描全城场次、估算成团概率、对比包场与拼团成本、按官方营销活动日历挑最佳日期、审查儿童餐营养、生成招募卡与邀请函。 | Stars: 243 | Updated | Claude CodeCodex | Verified | Install |
| deep-researchfeiskyer/codex-settings仅在用户显式调用 `$deep-research` 时,用 Codex CLI 子任务完成多来源深度调研并综合成带出处的报告。不用于单次查证或已给定材料的总结。 | Stars: 250 | Updated | Claude CodeCodex | Verified | Install |
| handofffeiskyer/codex-settings仅当用户显式调用 `$handoff`,或明确要求生成会话交接文档时使用。将当前对话压缩为脱敏、可执行的交接文档,供下一个 agent 接续工作;不要自动触发。 | Stars: 250 | Updated | Claude CodeCodex | Verified | Install |
| liter-llmxberg-io/liter-llmUniversal LLM API client for 174 providers with native bindings for 14 languages. Use when writing code that calls LLM APIs via liter-llm in Python, TypeScript, Rust, Go, Java, C#, Ruby, PHP, Elixir, WASM, or C, when running the OpenAI-compatible proxy, or when calling LLMs through the MCP server. Covers chat, streaming, tool calling, embeddings, image generation, speech, transcription, moderation, web search, OCR, reranking, provider routing, middleware, and configuration. | Stars: 266 | Updated | Claude CodeCodex | Verified | Install |
| liter-llm-using-the-mcp-serverxberg-io/liter-llmUse when calling LLM APIs through the liter-llm MCP server's 22 tools, and to decide when MCP beats the CLI or SDK. Covers the tool surface, the auto-installing launcher, and authentication. | Stars: 266 | Updated | Claude CodeCodex | Verified | Install |
| wayfinderJesusFilm/corePlan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear. | Stars: 24 | Updated | Claude CodeCodex | Verified | Install |
| gz-agent-synctvproductions/gzkitUse after a skill or governance-surface change to regenerate the control surfaces and skill mirrors. | Stars: 9 | Updated | Claude CodeCodex | Verified | Install |
| gz-competitor-radartvproductions/gzkitUse for the monthly competitor-discovery radar over spec-driven and agent-workflow tools. | Stars: 9 | Updated | Claude CodeCodex | Verified | Install |
| gz-context-diettvproductions/gzkitUse when the operator asks for a "diet" or "progressive disclosure" pass on AGENTS.md, CLAUDE.md or the rules. | Stars: 9 | Updated | Claude CodeCodex | Verified | Install |
| talking-head-guide0xsline/OpenChatCutGuide for editing videos where the primary content is people talking — talking-head / 口播, interview / 访谈, lecture, tutorial, podcast, course content, and similar talking-driven formats. Use when the user wants speech editing on a talking video (剪口播 / 口播剪辑 / 去口癖 / clean up fillers / smooth speech), motion graphics layered onto talking video (口播加 MG / 加动画), or B-roll on a talking video (加 B-roll / add B-roll). For motion graphics specifically, use this together with the active Motion Graphics skill/workflow available in the current OpenChatCut environment — this skill adds talking-specific guidance (speech-rhythm timing, frame-aware placement, subject/caption protection, placement verification). | Stars: 3.2k | Updated | Claude CodeCodex | Unverified | Install |
| skillkrillinai/OpenCreator | Stars: 14k | Updated | Claude CodeCodex | Verified | Install |
| skillkrillinai/OpenCreator | Stars: 14k | Updated | Claude CodeCodex | Verified | Install |
| dong-goi-skill-moimochistudio-vn/kitvietBiến một việc vừa làm tốt thành skill mới theo khuôn Kit Việt để lần sau gọi lại. Dùng khi nói "lưu cách làm này", "tạo skill mới", "đóng gói thành skill", "lần sau làm y vậy". | Stars: 22 | Updated | Claude CodeCodex | Verified | Install |
| ho-so-ca-nhanmochistudio-vn/kitvietPhỏng vấn 8-10 câu để viết hồ sơ CLAUDE.md / AGENTS.md: vai trò, đơn vị, khách, giọng văn, từ cấm, quy tắc. Dùng khi nói "tạo hồ sơ", "cho AI biết về tôi", "viết CLAUDE.md", "cài đặt ban đầu". | Stars: 22 | Updated | Claude CodeCodex | Verified | Install |