Explore

Query NCBI ClinVar for variant clinical significance. Search by gene/position, interpret pathogenicity classifications, access via E-utilities API or FTP, annotate VCFs, for genomic medicine.

Query ClinicalTrials.gov via API v2. Search trials by condition, drug, location, status, or phase. Retrieve trial details by NCT ID, export data, for clinical research and patient matching.

Comprehensive citation management for academic research. Search Google Scholar and PubMed for papers, extract accurate metadata, validate citations, and generate properly formatted BibTeX entries. This skill should be used when you need to find papers, verify citation information, convert DOIs to BibTeX, or ensure reference accuracy in scientific writing.

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use bioservices.

OpenProse VM skill pack. Activate on any `prose` command, .prose files, or OpenProse mentions; orchestrates multi-agent workflows.

Feishu document read/write operations. Activate when user mentions Feishu docs, cloud docs, or docx links.

本地直出可编辑 PowerPoint（.pptx）：用户要做 PPT / 幻灯片 / 演示文稿 / 汇报 / 方案时使用。先列大纲确认，再产结构化 deck 并按内容自动选主题，调 mcp_pptx_make_pptx 生成，产物必须上产物卡。

Author a new SKILL.md from a user prompt, or migrate an existing non-spec skill to the Anthropic Agent Skills format.

Read and write Linear issues, comments, projects, cycles, users, documents, initiatives, milestones, and more via the Linear MCP server. Attach chat-uploaded screenshots to issues.

Create, search, triage, label, assign, comment on, and close GitHub issues using the gh CLI, with a curl REST fallback.

Delegate coding work to the OpenAI Codex CLI for repository changes, reviews, and focused fixes.

Delegate coding work to Claude Code CLI for repository edits, reviews, and multi-turn implementation sessions.

Walk Sean through an incoming waku-agent PR or issue and present it his way — four fixed sections: what this is, why it matters, how HE can test it with you as copilot, and are we ready to merge / reply / close and why. Use whenever Sean asks to look at, test, triage, or decide on a pull request or an issue, and whenever a queue of them is being drained one at a time.

Cut a waku-agent release when main is ahead of the last tag. Check the gap, bump the version, tag, confirm PyPI, announce. Use when the last release is 14 or more days old, when 10 or more commits sit past the last tag, or when the user says release, cut a release, bump the version or tag.

Use when a task needs an app on the user's own screen — a native desktop application (instrument control software, Origin, GraphPad, ImageJ, a reference manager, a spreadsheet), or a desktop browser window that needs window-level control. Read before the first `computer` call. Covers the observe-act-observe loop, why element indexes go stale, which action to prefer for which control, what "unverified" means and why it must never be reported as success, and the recovery for each error code. Not for page-level web automation (use the browser connector) and not for anything that can be done from the shell.

Verify apps/desktop frontend changes visually without launching the Tauri app or a live model

Publish a new AlphaClaw release to npm and GitHub. Use when the user asks to cut a release, publish a version, write release notes, draft a release tweet, or close issues addressed in a release. Covers git history analysis, release note drafting, npm publishing, GitHub release creation, issue closing, and tweet drafting.

Generate or edit images using AI models (FLUX, Nano Banana 2). Use for general-purpose image generation including photos, illustrations, artwork, visual assets, concept art, and any image that is not a technical diagram or schematic. For flowcharts, circuits, pathways, and technical diagrams, use the scientific-schematics skill instead.

Query NCBI Gene via E-utilities/Datasets API. Search by symbol/ID, retrieve gene info (RefSeqs, GO, locations, phenotypes), batch lookups, for gene annotation and functional analysis.

Query ChEMBL bioactive molecules and drug discovery data. Search compounds by structure/properties, retrieve bioactivity data (IC50, Ki), find inhibitors, perform SAR studies, for medicinal chemistry.

Generate or edit images from text and local files, image URLs, or data URLs through image API. Use when the user asks to create an image, generate from one or more reference images, combine styles or elements across references, or edit a marked region while blending the result into the original scene.

Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.

Use when designing a GEO Signal Monitor, AI answer monitoring system, citation tracking plan, brand-fact correction loop, GEO monthly report, alert rules, dashboard fields, or cautious attribution framework for DeepSeek, Doubao, Qianwen, Kimi, Tencent Yuanbao, and similar answer engines.

Optimize an existing article or local article file into a GEO and AI-search-friendly rewrite with source-bound evidence, structure, semantic density, scoring, and change notes. Use for article rewriting and citation-readiness improvement; do not use for new articles, invented citations/data, compliance audits, ranking guarantees, or generic GEO strategy.

Design direction discovery and UX judgment for ima2 users. Use for UI/UX direction and design judgment — vague visual briefs, onboarding, empty/error/loading states, layout vocabulary, typography breaks, favicons, logos, and brand identity choices. Pairs with ima2-front: this skill decides the design direction, then load ima2-front to implement it. Triggers: make it look good, modern, clean, aesthetic, onboarding, empty state, error state, favicon, logo, design system, 깔끔하게, 모던하게, 감성적으로.

Frontend implementation skill for ima2 users. Use for any frontend, web UI, or visual implementation work — building, styling, or redesigning pages/components, responsive layouts, motion, component architecture, and production-surface polish. Pairs with ima2-uiux: load it first when design direction is vague; this skill implements the chosen direction. Triggers: 'frontend', 'UI', 'component', 'CSS', 'responsive', 'animation', 'React', 'Vue', 'Svelte', 'Tailwind', 'layout', 'styling', 'redesign', 'mockup', 'anti-slop', '프론트엔드', 'UI 작업', '반응형', '디자인 수정'.

Use the ima2-gen CLI/server to generate, edit, inspect, and manage local AI image generation jobs.

Interact with the Nerve Kanban board API. CRUD tasks, manage workflow (execute, approve, reject, abort), handle proposals, configure the board. All endpoints are under /api/kanban on the Nerve server.

Apply, review, and explain TypeScript variable conventions. Use automatically for tasks involving variable declarations, const assertions, enum alternatives, literal-union state modelling, boolean flags, or choosing between null and undefined.

Apply, review, and explain TypeScript type conventions. Use automatically for tasks involving inference, readonly data, type-safe constants, template literal types, any and unknown, assertions, type errors, type definitions, arrays, type imports, or generated service types.

Apply, review, and explain testing conventions from the TypeScript Style Guide. Use automatically for TypeScript and TSX test tasks involving test design, AAA, mocking, isolation, black-box testing, Testing Library queries, test descriptions, or snapshots.

Apply, review, and explain the opinionated conventions in the TypeScript Style Guide. Use automatically only when TypeScript conventions are part of the requested task, including type modelling, discriminated unions, function APIs, variables and state, naming, source organization, React props, component APIs, state management, data flow, or tests. Do not use for styling or layout alone.

Apply, review, and explain TypeScript source organization conventions. Use automatically for tasks involving feature-based organization, code colocation, import paths, import sorting, monorepos, or frontend and backend project structure.

Apply, review, and explain React conventions from the TypeScript Style Guide. Use automatically for TypeScript and TSX tasks involving prop-derived state, prop typing, component responsibilities, data flow, compound components, or client and server state.

Apply, review, and explain TypeScript naming conventions. Use automatically for tasks involving exports, identifiers, generic type parameters, acronyms, React props and handlers, hooks, comments, or TSDoc.

Apply, review, and explain TypeScript function conventions. Use automatically for tasks involving function responsibility, statelessness, purity, side effects, function arguments, function API design, or return types.

Apply, review, and explain discriminated unions in TypeScript. Use automatically for tasks involving mutually exclusive variants, invalid state prevention, exhaustiveness checking, variant-specific object properties, application state, function arguments, or React props.

Run GitHub Actions CI locally with Local CI to validate changes before pushing. Use when testing, running checks, or validating code changes.

Run local CI via the in-tree dev build of local-ci (`pnpm local-ci-dev`) to verify changes to this repo before completing work. Runs `pnpm local-ci-dev run --all` in the background, watches the log for step failures, and retries failed runners after fixes. Use before reporting work as complete, or whenever the user asks to validate, run CI, or check that changes pass. Distinct from the published `local-ci` skill, which targets downstream users via `npx run-local-ci`.

当用户提供一段演示文稿主题、内容大纲或会议材料，希望生成结构完整、视觉突出、每页有动画的 HTML 演示文稿时使用；从新内容生成 8 页单文件 HTML，不生成 pptx，也不改写已有案例。

在 DeepSeek Harness 中处理飞书数字员工对话，并使用飞书 MCP 创建真实任务。用户要求在飞书发布、安排、指派或创建任务时使用；普通寒暄只回复，不调用任务工具。

将长文拆成 1–10 张图文卡片，保留 12 种视觉风格、8 种布局和 3 套配色。用户提到图文卡片、知识卡片、微信图文、文章可视化、image cards 或要求生成系列信息图时使用。

只读分析本地 Excel 工作簿，完成数据剖析、清洗口径、结论提炼、图表选型、离线 HTML 报表生成和双端验收。用户要求理解或分析 .xlsx/.xlsm 数据、把 Excel 变成可视化报告、更新 Epoch AI 演示报表、选择合适图表或核对报表数据时使用。

Collect and curate public AI Agent, LLM, RAG, MCP, and AI application interview experiences for agent-interview-hub.

Sync table, format rules, and helptags command for the vimdoc. Use before editing doc/agentic.txt, init.lua, config_default.lua, theme.lua, or README install and keymaps; vimdoc must match.

Rules for ChatWidget window lifecycle. Use before editing ChatWidget show/hide/destroy, WidgetLayout, WidgetRegistry, WindowDecoration, BufferGuard, SessionRegistry.show_session, the hidden chat float, fallback windows, or any programmatic window close.

Rules for chat-buffer content and tool-call rendering. Use before editing MessageWriter, PermissionManager, tool-call block rendering, sender headers, thinking blocks, auto-scroll, folds, status rows, permission buttons, or chat- buffer tool-call tests.

mini.test red/green loop, revert check, and which test references to load. Use before creating, editing, or reviewing tests, and before TDD behavior changes.

Reviews a diff before commit: tests can fail, routed rules hold for changed files, unchanged siblings still hold. Runs no full gate. Use to review a diff: yours, a sub-agent's, or as plan-review loop reviewer.

Draft-first PR flow and single-commit CodeRabbit review rounds. Use before opening a PR, marking one ready for review, or handling a CodeRabbit review round and its findings.

Reads Neovim help and API docs from local files, falling back to online. Use for Neovim docs, features, or Lua API questions.

Enforced Lua style: class pattern, visibility prefixes (_private, __protected), optional-type syntax, LuaCATS annotations. Use before editing any .lua file; skipping it causes luals and selene failures.

Turns rule gaps into routed, verified rules and empties rules-report.md. Use when a rule was missing, wrong, or broken; a review finding was fixed or rejected; a sub-agent report has a "Rule gaps" list; or rules-report.md exists.

Creates, lists, and manages GitHub discussions in this repo through the GraphQL API. Use when the user asks to create, list, or manage a GitHub discussion.

Rules for writing agent docs: anti-staleness, rule-needs-a-test citation, router and .coderabbit.yaml sync, ADR template, glossary. Use before editing AGENTS.md, CONTEXT.md, docs/adr/**, .agents/skills/**, or .coderabbit.yaml.

Rules for the ACP client, transport, and provider flow. Use before editing ACPClient, ACPTransport, AgentInstance, ACP provider flow, tool-call parsing, permission requests, provider switch, reconnect, or ACP subprocess lifecycle.

Official ACP schema, events, and rules for this plugin's provider work. Use when the work depends on ACP data, or the user asks about ACP schema, events, rules, or docs.

Use when the user wants to polish academic prose, remove AI-generated patterns, improve clarity, or adapt English or Chinese writing to a target style or journal.

Use when the user wants to organize paper subsets, create workspaces, add or remove papers, search within a workspace, manage refs/papers.json, or export workspace BibTeX.