Loading…
Showing 7681–7710 of 10181 skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| longkeep-folderwingsofsky/longkeepRun one agent CLI on a folder of repositories, unattended, with a brief the user saved once (folder tasks, built on Longkeep delegation). Use when the user says "run the folder task on <folder>", "work through these repositories overnight", "edit the folder-task brief", or asks to install the folder module. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| initlgy1027/specflow-agent-pack按需检查项目上下文并建立带证据来源、置信度和未知项的工程画像。仅在跨会话复用工程事实或实施工作确实依赖仓库约束时触发,不是其他 Skill 的必经步骤。 | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| lifting-loopsyujiachen-y/dotfilesFinds loops where the user keeps acting as a manual step for agents (retrying, judging output, approving, carrying context, starting the same task by hand, doing the agent's work) and proposes how to lift the user out: delete a stale rule, change a skill / AGENTS.md / playbook, add a script or metric, add a skill or scheduled task, or advise the user. Keeps a private loop ledger and promotes Claude Code auto-memory into artifacts. With a task already in the session, reflects on that session; in an empty session, scans recent local Claude Code, MiniMax Code, omp, pi and Codex sessions, a claude.ai export and an Obsidian vault. Triggers: /lifting-loops, retro, post-task reflection, "find repeated work", 反思一下, 复盘这次会话, 总结最近的会话, 找找重复劳动, 哪些事可以不用我; the weekly scheduled run; settling a proposal ("accept P-003", 采纳 P-003, 拒绝 P-003). | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| find-your-unknownsaxel-pm/watch-n-learnBefore turning an agent loose on a coding task, surface the decisions you never specified — the gaps between your prompt (the "map") and the real codebase (the "territory"). Runs six prompt patterns (blind-spot pass, brainstorm/prototype, interview-me, reference-as-map, implementation-notes logging, quiz-me) to enumerate unknowns and shape the architecture up front. Use when the user says "help me scope this before I build it", "what am I missing", "find my blind spots", "interview me about this feature", "I don't know this codebase / this domain, help me prompt better", "de-risk this before the big run", or "surface the unknowns" — and BEFORE kicking off a large or architecture-shaping agent run on an under-specified task. | Stars: 9 | Updated | Claude CodeCodex | Verified | Install |
| tavily-searchJacky1n7/openclaw-skill-tavily-searchSearch the public web through Tavily and return structured results with URLs and snippets. Use when an agent needs current information, source discovery, link lookup, news or finance search, or a fallback for unavailable built-in web search. Do not use for private or authenticated pages. | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| optimize-claude-opus-5-promptsIchenDEV/prompt-optimizer-pluginsClarify and rewrite prompts or agent harnesses for Claude Opus 5 (claude-opus-5). Use when optimizing, migrating from Opus 4.8, or tuning Opus 5 behaviors such as long responses, over-narration, scope expansion, eager subagents, or over-verification (including Opus 5 提示词优化)—not for Claude Fable 5. | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| optimize-claude-sonnet-5-5-promptsIchenDEV/prompt-optimizer-pluginsClarify and rewrite prompts or agent harnesses for Claude Sonnet 5.5 (claude-sonnet-5-5). Use when optimizing, migrating from Sonnet 5, or tuning Sonnet 5.5 behaviors such as effort, initiative/scope, between_tools, JSON accuracy, progress updates, or low-effort verification (including Sonnet 5.5 提示词优化)—not for Opus/Fable prompt rewrites or bare model picking (use select-claude-models). | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| prompt-patternsflurdy/agent-skillsFind recurring substantial prompts in local Pi and Claude Code history and suggest reusable prompt-template drafts; metadata-first, redacted, bounded and read-only. | Stars: 9 | Updated | Claude CodeCodex | Unverified | Install |
| omiCzzzzzzJ/omiOmi3.0 小红书图文笔记生产线。输入内容素材 + IP形象,自动产出分镜脚本JSON + 图片生成指令,适用于 Claude Code、OpenClaw、Codex、扣子等任何具备本地图片生成能力的 Agent 平台。触发词:omi、小红书笔记生成、omi笔记 | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| automate-mefoxytanuki/pstack-opencodexUse for "automate me", "create/update/refresh my -mode skill", "turn/capture my preferences or working style into a skill", or wanting agents to follow how the user works. Drafts or revises a personal -mode skill via create-skill + unslop, optionally pulling fresh evidence from recent transcripts. | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| principle-build-the-leverfoxytanuki/pstack-opencodexApply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks. Build the tool that does it or proves it (codemod, script, generator, or a skill your subagents follow) instead of working by hand. The tool is the artifact a reviewer can rerun. | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| launch-rhinohybridlabor-api/aosStart a single Rhino MCP session. Accepts a version argument (e.g. `8`, `WIP`) and an optional explicit port. Walks forward from `10500` to pick a free port if none was given. On macOS this opens a new document in the running Rhino; on Windows it launches a new Rhino process. Use when the user asks to start a Rhino MCP session — for N parallel Rhinos use `/launch-rhinos` instead. | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| launch-rhinoshybridlabor-api/aosSpin up N Rhino MCP sessions in parallel and fan out one agent per Rhino. Use when the user wants multiple Rhinos running simultaneously with each agent driving its own — e.g. "spawn 3 agents and have each launch Rhino", "run 5 Rhino tasks in parallel". For a single Rhino, use `/launch-rhino` instead. | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| cut-silenceAndersonAdelino/skillsCuts silence from ONE video with auto-editor and normalizes the audio to -14 LUFS. With the `--fillers` flag, also removes filler words, stutters and duplicate takes (the speaker restarting a segment after an error), using word-level transcription plus agent judgment. Triggers "cut the silences", "remove the pauses from this video", "trim the dead air", "speed this video up by cutting pauses", "corta os silêncios", "tira as pausas do vídeo", "tira os tempos mortos", "tira os né/tá do vídeo", "corta as gagueiras". Do NOT use for creative editing (choosing takes, burned-in captions, color grading, overlays, cutting by content) — this skill only removes silence and parasitic sound. If the request is vague like "edit my video", ask what exactly before triggering. | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| hubspot-social-task-runnerFirst-Touch-Inc/firsttouch-agent-skill-packsFind HubSpot CRM tasks due today in the user/owner queue that already represent LinkedIn/social steps, such as connect, message, or follow-up, then execute the approved social action through FirstTouch and mark the HubSpot task complete only after the action is queued or sent. Use only when HubSpot MCP is connected and the team already creates these social-step tasks every day. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| coreGentBajko/capstoneInternal to the capstone suite - carries the shared rules (references/) and scripts every capstone subcommand reads; it exists so npx-skills installs ship them alongside the command skills. Not meant to be invoked directly; when invoked anyway, run references/../scripts/help.sh and output its stdout verbatim. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| implementGentBajko/capstoneUse when an approved feature plan is ready to become code - executes plan.md task by task with verification, in subagents or inline as you pick, reviews the diff recursively until no new findings survive, then refreshes the affected reference chapters. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| workingonoliverjueguen/workingon-claude-skillRecord the work done in this Claude Code session in the configured ticketing tool (Jira, Linear, GitHub Issues, Trello or Vikunja), creating the ticket, adding a short progress comment, linking an existing one or closing it. Use it when the [workingon] hook reports unrecorded work, when the user types /workingon, and when they ask to log, track or file what they are working on. | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| blcaptain-style-skilldososo/blcaptain-style-skill当用户需要把内容(文章、笔记、截图、数据、产品说明)做成中文图文卡片组图时使用——小红书 / Rednote 3:4 竖图、公众号封面、社交卡。提供三套独家视觉语言(静纸 Still Paper本手记 / Signal Proof 证据层 / Bridge Canvas 跨平台桥),由 Claude 读懂内容、自己撰写 brief.json,交给确定性引擎渲染出第一眼惊艳、一眼可辨、国内开箱即用的图文组图。 | Stars: 187 | Updated | Claude CodeCodex | Verified | Install |
| como-si-fuera-de-bocamryll/skillsExplain anything — code, an error, a concept, or a non-technical topic — in the simplest, most plain-language way possible, ELI5-style, with a natural Río de la Plata (Argentine) voice that puts clarity first. Use ONLY when the user explicitly asks to have something dumbed down or simplified. Triggers (Spanish + English): 'explicámelo como si fuera de Boca' (or de River / de cualquier cuadro), 'explicámelo simple', 'explicalo fácil', 'más fácil', 'bajámelo un cambio', 'en criollo', 'como si tuviera 5 años', 'para tontos', 'ELI5', 'explain like I'm 5', 'dumb it down', 'in plain terms'. Optimized for technical material (code, architecture, tooling, errors) but the same method works for any topic. Do NOT use when the user wants full technical depth, a code review, or did not ask to simplify — this skill is for deliberate, on-request simplification, not for talking down to the user by default. | Stars: 9 | Updated | Claude CodeCodex | Verified | Install |
| pr-quizmryll/skillsUse when a PR/MR explanation was just delivered (e.g. right after the explain-pr skill finishes) and the change was substantially agent-written, or whenever the user asks to be quizzed on a change: 'quiz me on this change', 'tomame el quiz', 'quiz del MR', 'tomame la lección', '/pr-quiz'. Counters comprehension debt: a formative, change-specific check that the user can defend code they delegated to a coding agent. Do NOT use for code review, bug hunting, or explaining changes (that's explain-pr) — this skill asks questions and grades answers. | Stars: 9 | Updated | Claude CodeCodex | Verified | Install |
| study-sessionmryll/skillsUse when the user asks for a guided comprehension/study session over existing code: '/study-session', 'study session', 'sesión de estudio', 'repasemos <subsystem>', 'help me understand <area>', or a recurring comprehension-recovery ritual. Recovers AND measures the mental model of code the user delegated to coding agents. Two modes: deep (45-60 min) and checkpoint (10-15 min). Do NOT use for implementing features, fixing bugs, or code review — nothing is modified in a study session except the comprehension tracking page. | Stars: 9 | Updated | Claude CodeCodex | Verified | Install |
| new-sdk-appsmartworldarafath/Google_Antigravity_PluginsCreate and setup a new Antigravity Agent SDK application | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| opus-mode-for-codexncusspm25/opus-mode-for-codexUse for long-running or multi-turn tasks, ambiguous debugging, architecture work, multi-file changes, complex research, and continuation of context-heavy work. Preserve task state, synthesize earlier context, maintain global consistency, investigate root causes, challenge premature conclusions, and verify outcomes before claiming completion. Do not use for trivial edits, obvious one-step tasks, simple rewrites, isolated typos, or simple questions. | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| stitch-mcp-delete-projectgabelul/stitch-kitPermanently deletes a Stitch project and all its screens. Destructive — requires explicit user confirmation before calling. | Stars: 49 | Updated | Claude CodeCodex | Verified | Install |
| stitch-mcp-edit-screensgabelul/stitch-kitEdits existing Stitch screens with text prompts — the iteration tool. Change colors, layout, content, or style without regenerating from scratch. Supports refinement loops via output_components suggestions. | Stars: 49 | Updated | Claude CodeCodex | Verified | Install |
| stitch-mcp-get-projectgabelul/stitch-kitRetrieves metadata for a specific Stitch project — title, theme, create/update time. Use to inspect a project before generating new screens. Do NOT use this if you already have a screenId — use stitch-mcp-get-screen instead. | Stars: 49 | Updated | Claude CodeCodex | Verified | Install |
| stitch-mcp-list-screensgabelul/stitch-kitLists all screens in a Stitch project. Use this after generate_screen_from_text to find the screenId of the newly generated screen, then call stitch-mcp-get-screen to retrieve it. | Stars: 49 | Updated | Claude CodeCodex | Verified | Install |
| stitch-remotiongabelul/stitch-kitGenerates walkthrough videos from Stitch projects using Remotion. Downloads screenshots from Stitch screens, builds a Remotion composition with transitions and text overlays, and renders to MP4. Use with stitch-mcp-list-screens and stitch-mcp-get-screen for screen discovery. | Stars: 49 | Updated | Claude CodeCodex | Verified | Install |
| stitch-setupgabelul/stitch-kitStep-by-step installer for the stitch-kit plugin and Stitch MCP server. Use this when setting up the plugin for the first time, diagnosing connection issues, or helping a new user get Stitch running in Claude Code or Codex CLI. | Stars: 49 | Updated | Claude CodeCodex | Verified | Install |