Generates complete Mendelian Randomization + single-cell transcriptomics (scRNA-seq) research designs from a user-provided direction. Always use this skill whenever a user wants to design, plan, or build a study combining MR and single-cell data — even if phrased as "help me write a paper on X", "design a bioinformatics study for Y", or "I want to study Z using MR and scRNA". Covers five study patterns (mechanism gene-set, key-cell, candidate-gene reverse validation, exposure-disease-cell triangulation, translational biomarker) and always outputs four workload configs (Lite / Standard / Advanced / Publication+) with recommended primary plan, step-by-step workflow, figure plan, validation strategy, minimal executable version, publication upgrade path, and a strictly verified reference literature retrieval layer with real references only.

A multi-stage workflow for writing long-form medical reviews; used when the user needs to build an outline based on PubMed literature, write chapter by chapter, perform supplementary searches, and format citations; input is the review topic and project directory, output is a c...

Triggered when the user wants to create, open, switch, move, delete, or rename OpenLoaf's "project" entity. Typical phrasings: "new project", "add ~/code/foo", "list all projects". **Not for**: reading/writing files inside a project (→ use Read/Edit/Write directly), discussing "project planning / requirement docs" (→ answer directly), routine Git operations (→ `Bash`).

当用户想要创建、编辑、改进或调试 OpenLoaf 自定义技能（Skill）时触发。典型说法："帮我创建一个技能"、"做一个新 skill"、"把刚才的操作封装成技能"、"写一个能自动 XX 的技能"、"改一下这个 skill"、"这个 skill 为什么不触发"、"编辑我的自定义技能"、"加个全局技能"、"给当前项目加个技能"。任何涉及 `.openloaf/skills/` 目录下 `SKILL.md` 的创建 / 修改 / 调优请求都应加载本技能。也适用于用户想理解技能格式、排查触发问题、或把对话里的工作流固化成可复用能力的场景。不用于：内置技能（如 file-ops、email-ops 等）的修改——那些是平台随版本发布的只读能力。

Triggered when the user asks the AI to directly operate their macOS desktop: open an app, click a button, fill a form inside a native window, read what's currently on screen, automate a local GUI flow. Typical phrasing: "in Finder, please…", "click X in the Y app", "what's on my screen right now". **Available only in OpenLoaf Desktop (macOS)**; other platforms return a desktop-only error — fall back to `BrowserAct` or hand the task back to the user. **Not for**: in-page web interaction (→ `browser-ops-skill`), local file I/O (→ `Read`/`Edit`/`Write`).

Audit an existing Sim knowledge base connector against the service API docs and repository conventions, then report and fix issues in auth, config fields, pagination, document mapping, tags, and registry entries. Use when validating or repairing code in `apps/sim/connectors/{service}/`.

Build a Docker Sandbox template image by extending docker/sandbox-templates. Use when writing a Dockerfile for sbx, choosing a base variant, building a family of templates with bake, or publishing and loading one with sbx template.

Generate and analyze DNA sequences using NVIDIA's Evo 2 BioNeMo NIM microservice. Use for Evo2/Evo 2, DNA generation, genomic sequence generation, hosted generation, local Docker deployment, local forward passes, layer outputs, logits, sampled probabilities, and BioNeMo NIM workflows.

Restructures code by extracting methods, renaming symbols, simplifying conditionals, removing duplication, and eliminating dead code — while running tests before and after each change to ensure behavior is preserved. Invoke immediately when user mentions refactor, refactoring, clean up, restructure, simplify, technical debt, code smell, DRY violations, or when code is messy, complex, or hard to maintain.

Interactive cross-feature navigation architect for Nicolify. Audits all routes and sidebar entries, maps user journeys across studios, detects orphaned features and dead-end flows, proposes navigation improvements with ASCII diagrams, generates clickable multi-page HTML prototypes on localhost:8888, and outputs FLOW-SPEC.md plus per-screen UI-SPEC updates for implementation agents. Use when the user asks about navigation coherence, user flows, journey mapping, orphaned features, dead-end screens, sidebar reorganization, cross-studio navigation, or feature discoverability. Triggers: 'flujo de usuario', 'navegación', 'journey', 'user flow', 'sidebar', 'rutas huérfanas', 'orphaned routes', 'dead end', 'flow audit', 'navigation audit', 'ux-flow', 'flow architect', 'cómo llega el usuario', 'discoverability', 'no encuentro', 'dónde está', 'reorganizar navegación', 'cross-feature flow', 'audita la navegación', 'mapa de rutas', 'flujos de la app'.

Manage Tessl tiles — search, install, update, and list versioned docs for project dependencies. Use when the user asks about Tessl tiles, adding or finding a tile, updating dependency docs, checking tile versions, or managing package documentation with Tessl. Covers add tile, find tile, tile version, dependency management, and curated version-pinned library docs.

Full-stack feature development pipeline for Nicolify. Orchestrates 6 specialized agents (architect, backend, agentic, backend-auditor, ux-designer, frontend) through 4 phases with user checkpoints. Use when building new features, adding CRUD endpoints, creating new UI screens, or implementing cross-stack functionality.

Auditor independiente. Toma T-{n}-result.md + corre tests él mismo (NO se fía del dev). Spawna agents auditor-{be,fe,agentic} según surface del ticket. Veredicto: APPROVED | CHANGES_REQUESTED | ESCALATED. Self-fix triviales (lint/typo/format) cap 2 iter. Diseño/security/arch → escala. Cuando todos tickets del story audit-passed, escribe REVIEW-final.md. Activa cuando user dice: '/auditor', 'auditá T-N', 'revisá ticket', 'verdict'.

Independently audit one immutable, Host-frozen PCB release candidate using the design's own editable source, its manufacturing reports, and board-frame measurements from `pcb.measure`. Use only for the Host-owned PCB release review that returns a prioritized Markdown report; do not use for PCB editing, routing, or fabrication export.

Review DXF and STEP/STP uploads for SendCutSend.com orders using its ordering guide, catalog, and specs. Use only for SendCutSend.com preflight reports covering upload readiness, selected material/SKU/thickness/service availability, and service-specific checks for laser cutting, CNC routing, bending, tapping, countersinking, hardware insertion, and finishing.

Evaluate the build trail of a PR — read the claude -p sessions the harness ran to build it, find where the project's context (Expert / AGENTS.md / skill / spec) served or failed the agents, then capture the learnings as evals (regression tests over the harness's own skills/context) and context fixes. Use when resolving a STUCK (diagnosis-first), auditing how a converged PR was built, or auditing a /learn memory PR. Human-driven and conversational — the trail-evaluating sibling of /evaluate-pr. Outcomes land on a branch (the PR's, or a fresh capture branch if you'll discard the PR) and reach memory via merge + /learn. Triggers - evaluate-sessions, evaluate sessions, review the build trail, diagnose stuck, audit how this was built, session observability.

Select and apply Patronum operators for Effector code with minimal, practical v2.x examples. Use when tasks involve choosing between Patronum operators, composing reactive state flows, replacing manual sample/combine boilerplate with Patronum utilities, explaining operator signatures and return types, or adapting legacy Patronum usage to modern v2 shorthand and import patterns.

Design, refactor, and review Effector state management using modern v23+ patterns. Use when tasks involve createStore/createEvent/createEffect modeling, dataflow with sample/attach/split, scope-safe SSR with fork/allSettled/serialize/hydrate, React integration with useUnit, Solid/Vue integration patterns, fixing scope loss, or replacing anti-patterns such as business logic in watch, imperative calls in effects, and direct getState business reads.

Resolve git conflicts (rebase, merge, cherry-pick, revert) using mergiraf, deterministic category handling, explicit intent inference, validation, and semantic-conflict auditing. Use when git status shows unmerged paths or an operation is paused with conflicts. Also decomposes an oversized PR or branch into smaller stacked PRs along functional/structural boundaries.

Authors and structures professional-grade agent skills following the agentskills.io spec. Use when creating new skill directories, drafting procedural instructions, or optimizing metadata for discoverability. Don't use for general documentation, non-agentic library code, or README files.