All categories
AI & Agents
LLMs, agent workflows, RAG, MCP, prompting, and AI app patterns
- 300,452
- 12,519
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 649–672 of 300,452 skills
- Auto Skiller BrandBrand identity, voice, messaging, asset management, and consistency frameworks.Votes: 0GitHub stars: 41
- ServerImported skill server from langchainVotes: 0GitHub stars: 41
- Refine LiveIn-chat fallback for the Timeline Inspector Refine agent. Use when the user runs `/refine live`, asks to "refine live", "go live", or answer refine jobs — but ONLY when no persistent agent is wired (no `npx transitions-refine live`). Prefer `npx transitions-refine live` for run-and-forget (relay spawns agent per click, no idle credit burn). This skill long-polls the relay, posts suggestions, handles scan/apply jobs.Votes: 0GitHub stars: 41
- Graphsignal ProfilerSet up the Graphsignal Profiler for inference workloads — vLLM, SGLang, PyTorch, and dstack services. Use when the user wants GPU profiling, tracing, or monitoring for inference, asks about `graphsignal-run` or `graphsignal.watch()`, or asks about CUPTI / Prometheus / OTLP setup.Votes: 0GitHub stars: 41
- Gemma TrainerTrigger this skill when the user wants to train, fine-tune, or adapt Gemma models (e.g. SFT, DPO, RLHF, Reward Modeling) on local hardware. Covers TRL, Unsloth, dataset preparation, validation, and GGUF/LiteRT conversion.Votes: 0GitHub stars: 41
- Gemma DevTrigger this skill when building applications with Gemma or for general knowledge inquiries related to Gemma models (e.g. prompt structure, capabilities). Covers model selection, development workflows, and deployment best practices.Votes: 0GitHub stars: 41
- Design IsAudit a design against Dieter Rams' ten "Good design is..." principles, then hand off a /make-plan prompt for one of three outcomes — new design, refine design, or redesign. Use when the user says "audit this design", "design review", "check this UI against Rams", "is this UI good", "critique this design", "design audit", or asks for a critique that should lead to a plan.Votes: 0GitHub stars: 41
- Dbs BridgeAgent 基建：把任意 skill 或 skill 集合目录桥接到 Claude Code（~/.claude/skills）、Codex（~/.codex/skills）、通用 Agents（~/.agents/skills，豆包 Mac App / Trae Solo / Codex 可读取）和 Grok（~/.grok/skills）。支持 dbskill 仓库内 skill，也支持外部 skill 绝对路径。Claude / Codex / 通用 Agents 使用软链，Grok 生成带 user_invocable: true 的薄 bridge。支持按 skill 名称、相对路径、绝对路径、skills 目录批量桥接，也支持拆桥和查看桥接状态。 触发方式：/dbs-bridge、/bridge、「桥接这个 skill」「桥接整个 skills 目录」「把这个 skill 接到 Claude Code、Codex、豆包和 Grok」「让多个 Agent 都能调用这个 skill」「取消桥接」「查看桥接状态」 Bridge any skill folder or dir...Votes: 0GitHub stars: 41
- Code WalkthroughGuide a visible, verified code walkthrough in Neovim with Terminal Control and Navi, optionally recording the presentation with OBS or retaining terminal evidence. Use when the user wants an agent-led code tour, code-along, live source explanation, or recorded terminal walkthrough.Votes: 0GitHub stars: 41
- Cli Anything HermesUse when the user wants Hermes Agent to build, refine, test, or validate a CLI-Anything harness for a GUI application or source repository. Adapts the CLI-Anything methodology to Hermes without changing the generated Python harness format.Votes: 0GitHub stars: 41
- Claw OrchestratorManage persistent coding sessions across Claude Code, Codex, Antigravity (agy), Cursor, and OpenCode engines. Use when orchestrating multi-engine coding agents, starting/sending/stopping sessions, running multi-agent council collaborations, cross-session messaging, ultraplan deep planning, ultrareview parallel code review, autoloop autonomous workspace iteration, ultraapp building deployable web apps from a structured Q&A interview, switching models/tools at runtime, exposing the orchestrator...Votes: 0GitHub stars: 41
- Bmw Design AnalysisBMW's corporate site — distinct from BMW M's motorsport-bombastic variant, this is a measured and settled corporate-automotive interface. On a light (cream-tinted white) canvas, BMW corporate blue (#1c69d4) carries every primary CTA; dark navy hero bands frame model photography. BMW Type Next Latin sets the entire hierarchy on two weights — heavy 700 display and Light 300 body. Configuration and reservation flows ride a card-based 4-up grid, where each card holds a model render, a name, and a...Votes: 0GitHub stars: 41
- Bioqc McpAutomated sequencing quality control and advanced visualization wrapping FastQC, MultiQC, and custom chart generation. Exposes an MCP stdio server for live AI integration alongside a ClawBio CLI runner.Votes: 0GitHub stars: 41
- Aihot查询 AI HOT 的中文 AI 资讯、精选、当前热点和日报。当用户问今天或最近的 AI 新闻、AI 圈动态、大模型或产品发布、OpenAI/Anthropic/Google 最近发布、AI 论文、AI 日报、AI HOT 精选、当前最热事件时使用。必须通过 aihot.virxact.com 的公开只读 API 获取当前数据，不凭训练记忆回答新闻。不需要 API Key 或 MCP server。Votes: 0GitHub stars: 41
- Ads MathCalculate and model paid-media CPA, CPL, CPC, CPM, ROAS, MER, break-even targets, contribution margin, LTV:CAC, impression-share opportunity, budgets, forecasts, and experiment economics. Use for PPC math, ad calculator, break-even analysis, ROAS calculator, CPA calculator, budget forecast, LTV CAC, or MER.Votes: 0GitHub stars: 41
- Hello WorldGreet the user warmly and demonstrate the minimal shape of a valid Agent Skill.Votes: 0GitHub stars: 41
- Weekly ReviewReview one week of evidence in a Life Kernel vault and adjust next week's commitments to real capacity.Votes: 0GitHub stars: 2
- Second BrainRetrieve and update durable personal or project context in a Life Kernel vault with source-backed, privacy-aware reads and routed writes.Votes: 0GitHub stars: 2
- Quarterly ReviewStep back once a quarter to check direction, goal horizons, and the balance between areas in a Life Kernel vault, and set the next quarter's direction.Votes: 0GitHub stars: 2
- Project MemoryRecord durable project progress, decisions, verification, and open questions after an agent work session.Votes: 0GitHub stars: 2
- OnboardingInterview a new user and fill a Life Kernel vault with their profile, goals, responsibilities, availability, and chosen planning method.Votes: 0GitHub stars: 2
- Morning PlanRun a five-minute morning opening that picks today's focus from last night's plan, due tasks, and fixed commitments, within realistic capacity.Votes: 0GitHub stars: 2
- Monthly ReviewReview a month of evidence against the user's goals in a Life Kernel vault, decide what happens to each goal, and set the month's outcomes.Votes: 0GitHub stars: 2
- Daily CircleRun a 10-20 minute evening conversation that records the day, updates the near-term plan, and sets tomorrow's focus in a Life Kernel vault.Votes: 0GitHub stars: 2