All categories
AI & Agents
LLMs, agent workflows, RAG, MCP, prompting, and AI app patterns
- 307,718
- 12,822
Security grades appear on each card once the skill has been scanned. Newly imported skills may briefly show without a grade until the backfill job runs.
Open in full browserBrowse ai & agents skills
Showing 3,001–3,024 of 307,718 skills
- Chorus Platform> 让外部 Agent（如 OpenClaw、MCP Client）通过 Chorus 与其他 Agent 通信。 > > This skill enables external agents to communicate with other agents via Chorus's REST API and WebSocket.Votes: 0GitHub stars: 3
- Ugc DirectorUGC video director for ClipUGC, turn a mobile app idea into a complete TikTok-style AI influencer video plan and execute it with the clipugc CLI. Use when the user wants to make a UGC video, TikTok video, promo video or influencer-style video for their app, wants hook/reaction/creative ideas, asks "make a video for my app", wants a video concept or creative strategy, or asks which character/hook/reaction style converts for their app category. Covers reaction archetypes (smirk, jaw-drop, cryin...Votes: 0GitHub stars: 2
- Story RunnerRun an ongoing AI-influencer story series with the ClipUGC CLI - a character living a continuing life in short talking-video episodes, where each episode picks up from the previous one's last frame. Use when the user wants to create a story series, an episodic AI character account, a "day in her life" video series, daily AI influencer content with a continuing plot, draft or approve a story episode, write an episode's plot themselves, check episode generation status, or download finished epis...Votes: 0GitHub stars: 2
- Persona AccountRun an ongoing AI creator account with ClipUGC, one persona, posting consistently over time. Use when the user wants to create an AI influencer or virtual influencer for Instagram or TikTok, asks for "the next post", wants a content plan / posting grid / content pillars for an AI creator account, wants the same person to stay recognisable across every post, asks what a fitness / beauty / faith / study / food / mom / tech influencer would plausibly post, or wants to grow and keep feeding an AI...Votes: 0GitHub stars: 2
- ClipugcClipUGC CLI - create AI-generated UGC-style marketing videos for mobile apps from the terminal. Use when the user wants to create an AI character or AI influencer, generate character looks or reference images, create a UGC video or video clip from a look or photo, animate a photo with a driver video, put an app screen recording and a hook into a clip to make the finished UGC video, suggest hook texts for UGC videos, check ClipUGC credits or balance, manage ClipUGC characters/images/videos (li...Votes: 0GitHub stars: 2
- ResearchRun significant research as a dedicated subagent and deliver the result as a PDF. Use when a question needs more than a quick lookup: comparisons, background reading, planning, anything with several sources.Votes: 0GitHub stars: 3
- Md2pdfRender a markdown document to PDF (pandoc + typst, A4, 2 cm margins, emoji and Cyrillic OK). Use when a report or long result should go to the chat as a PDF file.Votes: 0GitHub stars: 3
- Readable Testable Code이 프로젝트의 개발 철학(단일 책임 원칙 + 읽기 쉽고 테스트하기 쉬운 코드). 코드를 작성·수정·리팩터링·리뷰할 때, 함수/컴포넌트/모듈의 구조나 책임 분리, 추상화 도입 여부, 테스트 작성 방식을 판단해야 할 때 반드시 먼저 적용한다.Votes: 0GitHub stars: 2
- StatsShow real token usage from your coding agents and how much simem saved, for the last 7 days or a period you name (30d, 12h, all).Votes: 0GitHub stars: 2
- SimemUse simem project memory when the user asks what was decided before, says "remember…" or "forget…", asks how many tokens simem saved, or wants the memory dashboard.Votes: 0GitHub stars: 2
- Simem SetupInstall, update, or repair simem (local project memory for coding agents) when the user asks to set it up or simem tools are missing.Votes: 0GitHub stars: 2
- DashboardOpen the private simem dashboard on this machine to see token usage and savings, and to search, edit, or forget project memory.Votes: 0GitHub stars: 2
- Memory WriteSave, correct, or retrieve durable shared memory across Claude Code and Codex. Use for remembered preferences, prior decisions, project history, explicit save requests, and implicit references to earlier work.Votes: 0GitHub stars: 2
- BigbrainRigorous, delegation-first engineering workflow. Use for /bigbrain followed by a feature, bugfix, refactor, chore, plan, how/why code explanation, guided PR review for a human or critique, idea to grill, setup, watch-pr, or resume. Accepts free text, a GitHub issue, or a Notion page.Votes: 0GitHub stars: 4
- To CtxTurn the current conversation's conclusions into a well-formed context document filed in the project's context system. Use for /to-ctx, "file this into contexts", "turn this conclusion into a context doc". Finds the placement rules (e.g. CONTEXT_MAP.md), writes in the project's house style, and reports the path.Votes: 0GitHub stars: 12
- ReadoutWrite replies and work reports a person can take in on one read — one claim per sentence, action in the verb, uncertainty attached to the claim it belongs to. Use for /readout, "make your reports readable", "your output is hard to read", "stop writing like an AI", or when a run's reporting style needs fixing. The body below is standalone prose — paste it into AGENTS.md or CLAUDE.md to apply it every turn instead of on invocation.Votes: 0GitHub stars: 12
- LowbandLow-bandwidth collaboration mode — response protocol for when the user's attention or mental capacity is depleted. Activate on /lowband or $lowband, or when the user says "too tired, keep it short", "brain is fried", "low bandwidth". Stays active every turn until the user says "back to normal" (or the equivalent in their language) or invokes with off. Work capability is not degraded; only presentation is compressed and decisions are filtered.Votes: 0GitHub stars: 12
- Long HorizonExecute a spec'd goal in one long autonomous run — hours of agent work pushing a whole acceptance ledger, with humans only at the two gates, spec before and review after. Use for /long-horizon, "make this a long-horizon goal", "run this across sessions", or when resuming work in a repo that already has a `.long-horizon/` workspace. Admission is interactive and iterative; the run is fan-out-driven and side-effect-bounded by an authorization envelope; progress is evidence-gated; a live report.h...Votes: 0GitHub stars: 12
- Just AskOne-shot answer-only turn — the user is asking a question, not assigning work. Invoked as /just-ask with the question attached (e.g. "/just-ask why does this test flake"). For that turn only, investigate read-only and reply with an analyzed answer; do not edit files, run state-changing commands, write a plan, or start a fix. The next message returns to normal. Meant for explicit invocation; also applies when the user says "just answer, don't do anything", "just explain, don't fix it".Votes: 0GitHub stars: 12
- HandoffGenerate a minimal-sufficient handoff when another agent or session will take ownership of a task or continue unfinished work. Use for /handoff, "hand this to the next agent", "let another session continue", session transfer, task ownership transfer, or restarting in a fresh context when the current session has degraded (a handoff to your future self). Reuses durable artifacts by reference instead of copying them, and redacts secrets.Votes: 0GitHub stars: 12
- Fan OutDispatch the current task to multiple subagents — after checking that fan-out is actually justified. Use for /fan-out, when the user says "multi-agent this" or "fan out", or when a task decomposes into genuinely independent subtasks. Decomposes along context coupling, uses handoff discipline for spawn contracts.Votes: 0GitHub stars: 12
- Ctx ResearchDeep research grounded in the project's durable context system. Use for /ctx-research, "ctx research", "research X starting from our contexts". Reads existing contexts first, sharpens the question to the real knowledge gap, fans out multi-agent research, verifies key claims, and files results back.Votes: 0GitHub stars: 12
- Ctx GrillStress-test a plan, decision, or idea with a context-aware interview. Use for /ctx-grill, "grill this plan", "stress-test this plan", or when the user wants their thinking stress-tested before committing. Reads durable contexts first (never asks what they answer), asks direction-changing questions one at a time with a recommended answer, stops at diminishing returns, and files resolved decisions back. Interactive only — never invoke under CI, loops, or other non-interactive runs.Votes: 0GitHub stars: 12
- To Ctx把当前对话的结论写成一份规范的 context 文档，放进项目 context 体系的正确位置。触发语：/to-ctx、「写进 contexts」「落个 context」「把这个结论归档」。先查放置规则（如 CONTEXT_MAP.md），按项目的既有风格写，最后汇报路径。Votes: 0GitHub stars: 12