工作流 类技能
Skill Atlas 收录的 工作流 类 AI Agent 技能，共 151 个，含用途说明、安装命令与安全审计状态。
按分类浏览
工作流 技能列表
- academy-guideStop and check this skill before finishing any reply to a question about how to use Claude or a Claude produ…
- career-opsOpen-source AI job search agent -- evaluate offers, generate CVs, scan portals, track applications. Use when…
- presentation-structureKnowledge about the presentation slide format, weight system, navigation, and section structure
- i-have-adhdShape output for a reader with ADHD: lead with the next action, number multi-step work, restate state across…
- ab-testingWhen the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentati…
- 13c-metabolic-fluxEstimates intracellular metabolic fluxes from steady-state carbon-13 isotope-tracing measurements using vali…
- 00-andruia-consultantUsar al iniciar o mejorar un proyecto de IA: diagnostica código y restricciones, propone skills existentes y…
- screen-reader-testingTest web applications with screen readers including VoiceOver, NVDA, and JAWS. Use when validating screen re…
- agentic-workflowsRoute gh-aw workflow design/create/debug/upgrade requests to the right prompts.
- invisible-playwrightUse the Dot's browser identities for any task on a website or search on the web: which identity to use, open…
- planning-with-filesPersistent file-based planning for multi-step AI-agent work. Keeps task_plan.md, findings.md, and progress.m…
- ablation-plannerUse when main results pass result-to-claim (claim_supported=yes or partial) and ablation studies are needed …
- install-memuInstall or uninstall memU for whatever agent you are — identify your host, print its packaged guide, and fol…
- implementing-llms-litgptImplements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi,…
- benchmark-paper-templateStructures Benchmark and Evaluation papers using the five-pillar framework (Research Gap, Construction Pipel…
- egm-bootstrapBootstrap directory README.md files across a repository subtree.
- article-sketchnote-editorial把一个概念铸成杂志专题档案——真问题→失败→转折→顿悟→命名, 6 个 layout 模具 + 4 字族对比 + 探案档案细节
- ai-visibilityMeasure real AI-engine visibility — traffic from ChatGPT, Perplexity, Claude, Gemini and which pages they ci…
- browser-act-skill-forgeForges reusable Skill packages (SKILL.md + scripts) from website exploration via browser-act — no re-explora…
- trace-claude-codeAutomatically trace Claude Code conversations to Braintrust for observability. Captures sessions, conversati…
- architectSketch types, signatures, and module structure before code, then stay in the loop while implementation fills…
- task-observerMonitors task execution for skill improvement opportunities: logs patterns, user corrections and methodology…
- onboardExplains the team's shared Claude Code setup
- a-philosophy-of-software-designApply John Ousterhout-inspired software design rules when reducing complexity, designing module boundaries, …
- agent-teamsCoordinate multiple Claude Code sessions as a team — lead + teammates with shared task lists, mailbox messag…
- research-add-fieldsAdd field definitions to existing research outline.
- nihaishaUse this skill when the user asks about Ni Haisha / 倪海厦 TCM course material, especially Shang Han Lun / 伤寒论,…
- babysit-babysitter-issuesThis skill should be used when the user asks to "babysit issues", "work on assigned issues", "check a5c-agen…
- loreSpecStory Lore - mine your SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and m…
- ariadocs-componentsBuild and customize docs UI with @ariadocs/components — the Docs.* layout (sidebar, mobile nav, table of con…
- openagentskill-registryDiscover, compare, audit, and safely install reusable AI Agent Skills with OpenAgentSkill. Use whenever an a…
- idea-analogist想法群聊室 — 类比者角色。被 idea-team 主编排器调用，或用户单独说"类比一下"、"别的行业有没有"、"yes-and 扩展"、"X 让你想到什么"、"跨界启示"时触发。**专门做跨界类比 + yes-an…
- agent-evaluationDesign reproducible evaluations for AI agents with representative task sets, explicit rubrics, appropriate g…
- telnyx-ai-assistants-curlAI voice assistants with custom instructions, knowledge bases, and tool integrations.
- ecommerce.1688-product-searchSearch and analyze products on the Chinese 1688 wholesale platform (Alibaba domestic B2B market) for sourcin…
- create-her将一个真实的人蒸馏为 AI Skill —— 她的声音、她的记忆、她的温度。 通过聊天记录、照片、文字叙述等原材料，构建一个完整的数字副本。
- presentation-stylingKnowledge about CSS classes, component patterns, and syntax highlighting in the presentation
- wcag-audit-patternsConduct WCAG 2.2 accessibility audits with automated testing, manual verification, and remediation guidance.…
- baoyu-article-illustratorAnalyzes article structure, identifies positions requiring visual aids, generates illustrations with Type × …
- alphaxivQuick single-paper lookup via AlphaXiv LLM-optimized summaries with tiered source fallback. Use when user sa…
- golden-chatUse when testing the golden_chat golden build
- mamba-architectureState-space model with O(n) complexity vs Transformers' O(n²). 5× faster inference, million-token sequences,…
- api-designerUse when designing REST or GraphQL APIs, creating OpenAPI specifications, or planning API architecture. Invo…
- egm-brainstormInteractive ideation and brainstorming skill for the Elephant & Goldfish Model (EGM). Helps turn half-baked …
- deck-blueprint奶油纸 + 锈红 + 蓝图网格 mask + 黑边硬卡片 + pipeline 盒
- competitor-gapFind keywords a competitor ranks for that the user's site doesn't — the content gap, prioritized by volume a…
- arenaSpawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. …
- five-whysFind the root cause of a bug by asking why five times
- clean-architectureApply Robert C. Martin-inspired architecture rules when separating business policy from frameworks, database…
- research-add-itemsAdd items (research objects) to existing research outline.
- audit-reproducibilityEnforce the replication-protocol.md rule by cross-checking numeric claims in a manuscript against the actual…
- workthreadsSpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (a…
- numa-programmingNUMA programming skill for multi-socket memory locality. Use when detecting NUMA topology, binding processes…
- telnyx-ai-assistants-javaAI voice assistants with custom instructions, knowledge bases, and tool integrations.
- SRT Card AnnotatorThis skill should be used when the user asks to "add reference cards to srt", "annotate srt with cards", "in…
- ecommerce.1688-search-by-imagePerform image-based product search on the 1688 platform. Use an image URL to find visually similar supplier …
- ci-cd-and-automationAutomates CI/CD pipeline setup. Use when setting up or modifying build and deployment pipelines. Use when yo…
- vibe-to-agentic-frameworkThe conceptual framework behind the presentation — what "Vibe Coding to Agentic Engineering" means, why the …
- aeonThis skill should be used for time series machine learning tasks including classification, regression, clust…
- 10-andruia-skill-smithUsar para crear o mejorar una skill de Andru.ia: define entradas y resultados, redacta SKILL.md con ejemplos…
- baoyu-compress-imageCompresses images to WebP (default) or PNG with automatic tool selection. Use when user asks to "compress im…
- golden-chat-emptyUse when testing the golden_chat_empty golden build
- distributed-llm-pretraining-torchtitanProvides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP)…
- architecture-designerUse when designing new high-level system architecture, reviewing existing designs, or making architectural d…
- drawio-reconstructionReconstructs reference images into high-fidelity, editable Draw.io files with rendered previews: native Draw…
- egm-draftDrafts a design document section-by-section using the concepts brief from egm-brainstorm (or user notes). Th…
- offensive-api-abuseAdvanced API exploitation methodology focused on business logic abuse and sophisticated attack patterns that…
- deck-dir-key-nav8 页单色背景, 160px display + 4px accent + Mono 箭头列表
- story-deslop网文去AI味。从表达、叙事用笔、故事因果三层诊断并修复文本，保留作者文风与已定剧情。触发方式：/story-deslop、/去AI味、「去AI味」「这篇太AI了」「网文去AI味」。
- 1688-product-detailExtracts comprehensive wholesale product data from 1688.com product detail pages: title, tiered pricing, SKU…
- agentica-infrastructureReference guide for Agentica multi-agent infrastructure APIs
- babysitWatch an open PR — fix failing CI, handle the straightforward review comments, and drive it to a mergeable s…
- review-checklistThe team's checklist for reviewing a change to linkcheck. Use before you commit or open a pull request.
- clean-codeApply Robert C. Martin-inspired clean code rules when improving readability, naming, function design, respon…
- blue-ocean-strategyCreate uncontested market space using value innovation instead of competing head-to-head. Use when the user …
- claude-delegateDelegate a coding task to a separate Claude Code CLI process or another Claude session as an implementer, th…
- research-deepRead research outline, launch independent agent for each item for deep research. Disable task output.
- fix-failing-pipelinesThis skill should be used when the user asks to "fix pipelines", "fix CI", "check staging pipelines", "fix f…
- mex-statechartExplain complicated existing behavior using checked state diagrams. Use when asked for a state diagram, to d…
- capture-environmentSnapshot the computational environment for a replication package — detects the analysis stack (R / Stata / P…
- ariadocs-openapiBuild an API reference from an OpenAPI 3.0/3.1/3.2 spec with @ariadocs/openapi — parse and validate a spec f…
- idea-research想法群聊室 — 调研员角色。被 idea-team 主编排器调用，或用户单独说"调研一下 X"、"X 的现状/竞品/数据"、"找 2026 数据"、"事实底"时触发。**用 WebSearch 拉真实 2026 数据…
- af-xdpAF_XDP skill for high-performance XDP sockets. Use when creating AF_XDP sockets, configuring UMEM and XSK ri…
- human-in-the-loopDesign and verify auditable human oversight, approval gates, escalation paths, and safe state transitions fo…
- SRT EnhancerThis skill should be used when the user asks to "enhance srt subtitles", "optimize srt with original script"…
- pr-review-agentFull PR review orchestrator. Use when asked to review a PR or check if it is ready to merge. Runs blast radi…
- input-token-overheadsUse when the context window fills too fast, per-turn input token cost is too high, or the aggregate input to…
- ecommerce.amazon-ads-api-accessAuthorize Amazon Ads accounts and inspect safe connection and profile metadata.
- competitive-ads-extractorExtracts and analyzes competitors' ads from ad libraries (Facebook, LinkedIn, etc.) to understand what messa…
- time-skillDisplay the current time in Pakistan Standard Time (PKT, UTC+5). Use when the user asks for the current time…
- alphagenomeLooks up precomputed AlphaGenome Atlas effects for any GRCh38 single-nucleotide variant (AVI score with Phre…
- 20-andruia-niche-intelligenceUsar tras definir el sector de un proyecto: prepara un dossier en español con contexto, normas aplicables, p…
- gws-chatGoogle Chat: Manage Chat spaces and messages.
- baoyu-cover-imageGenerates article cover images with 5 dimensions (type, palette, rendering, text, mood) combining 11 color p…
- golden-chat-singleUse when testing the golden_chat_single golden build
- huggingface-tokenizersFast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 second…
- figure-designerAdvises on the design of the three core figures in a technical paper: the Motivated Example (Figure 1), the …
- keyword-researchKeyword research from a seed topic — ideas, real Google volume/CPC, intent, difficulty, clustered into a pla…
- airbnb-listing-detailFetches complete Airbnb listing details for a given numeric listing ID via the internal GraphQL API, returni…
- agentica-promptsWrite reliable prompts for Agentica/REPL agents that avoid LLM instruction ambiguity