What to say while long work is still running, and what a legal mid-task stop looks like. Use during any run over a few minutes — migrations, sweeps, babysit loops, automations, deploys — and at the moment you are tempted to stop and ask, report a blocker, or answer "how's it going?".

Write a haiku about a topic and render it as a shareable card.

Migrate Claude Code, OpenClaw, Hermes, or custom Agent Skill directories into PilotDeck's global skills directory. Use when the user asks to migrate, import, copy, or consolidate skills into PilotDeck, or mentions ~/.claude/skills, ~/.openclaw, ~/.hermes, ~/.agents/skills, or ~/.pilotdeck/skills.

Create animation-rich browser-based HTML presentations from scratch, enhance existing HTML decks, or convert PowerPoint files into web presentations. Use only when the requested deliverable is HTML or a browser presentation; do not use when the user needs an editable native .pptx file.

가장 최근 윤문 결과를 2차로 다시 다듬는다 — 특정 카테고리·문단·강도 조정도 가능. humanize-korean strict 윤문(Phase B)을 기존 run_id에 재실행해 잔존 finding을 처리한다. 트리거 — "/humanize-redo".

Run bot acceptance tests to validate MCP tools work correctly from a real AI agent's perspective. Use when testing PRs, detecting regressions, or verifying tool changes end-to-end with Claude/Gemini CLIs.

Symbolicate a native VS Code crash dump (.dmp) using electron-minidump. Use when given a crash dump file, asked to symbolicate a crash, resolve missing method names in a native crash backtrace, or attach Electron/Insiders/Stable symbol files. VS Code team members only; requires macOS or Linux.

Use when running VS Code smoke tests or working on smoke-test CI steps. Covers npm run smoketest / smoketest-no-compile, grep filtering tests, and a temporary repeat-loop technique for tracking down flaky smoke tests in CI.

Identify all files a specific author contributed to on a branch vs its upstream, tracing code through renames. Use when asked who edited what, what code an author contributed, or to audit authorship before a merge. This skill should be run as a subagent — it performs many git operations and returns a concise table.

Design, evaluate, and improve agentic harnesses — the orchestration layer around LLM-powered tools, agents, assistants, copilots, workflow runtimes, and AI-driven product features. Use this skill whenever the user mentions building an agentic system, structuring tool use, adding permissions or approval gates, designing multi-step AI workflows, managing context windows or memory, making agents durable or resumable, evaluating or pressure-testing an existing harness, planning phased implementation for an AI product, reviewing agent architecture, improving agent UX or observability, or asking how to know if their harness is actually good. Also use when the user describes problems that imply harness gaps — like agents doing unexpected things, context getting stale, sessions not surviving crashes, tools running without permission, or costs spiraling — even if they do not use the word "harness."

Use in Claude Desktop when a user asks to read, analyze, summarize, or extract from a heavyweight file such as PDF, DOCX, PPTX, XLSX, CSV, or TSV. Avoid raw ingestion of bulky files. Ask for a converted markdown or CSV artifact first, or give the user exact conversion commands to run outside Claude Desktop.

Investor-first workflow for reviewing an existing financial model, forecast, or sensitivity analysis. Use for prompts like "review this model", "stress test these assumptions", "what breaks in this forecast", or "is this model decision-ready". Best when you have a spreadsheet export, pasted assumptions, key drivers, and the decision the model supports. Optional Open Brain search and capture can pull prior model context and store the final review memo.

Reconstructs reference images into high-fidelity, editable Draw.io files with rendered previews: native Draw.io elements carry text and structure, SVG covers simple icons that match the reference, and cropped or transparent PNGs preserve complex visuals. Use when the user wants a diagram image, research figure, architecture diagram, slide, UI screenshot, or image folder turned into `.drawio` XML; batch requests use a manifest with bounded parallelism when available and a full-fidelity serial fallback otherwise.

Helps understand and write EAS workflow YAML files for Expo projects. Use this skill when the user asks about CI/CD or workflows in an Expo or EAS context, mentions .eas/workflows/, or wants help with EAS build pipelines or deployment automation.

Submit compact Clinical Tables NCBI Gene requests for human gene lookup, pagination, and field selection. Use when a user wants concise autocomplete-style human gene search results

Build, run, and test SwiftPM macOS packages and executables. Use when the repo is package-first or has no Xcode project.

Browser automation CLI for AI agents. Use when the user needs to interact with websites, verify dev server output, test web apps, navigate pages, fill forms, click buttons, take screenshots, extract data, or automate any browser task. Also triggers when a dev server starts so you can verify it visually.

Audit SwiftUI runtime performance from code first. Use when diagnosing slow rendering, janky scrolling, expensive updates, or profiling needs.

Design new small-molecule binders with Boltz. Use when generating novel ligands or hits for a target without a fixed compound library. Not for screening existing molecules or one-off docking.

Design new protein binders with Boltz. Use when generating protein, peptide, antibody, nanobody, or custom binder candidates for a target. Not for screening existing proteins or small molecules.