菜单
Diagnostic in-memory compute backend. Use ONLY when the user explicitly asks to verify that the compute pipeline (Registry → IPC → renderer) is wired correctly without invoking real shells or remote services. Off by default — register via ENABLE_COMPUTE_STUB=1.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Create or revise high-quality academic and research presentation slides in Markdown using Marp, following a story-first multi-phase workflow. Use when the user needs conference talk slides, lab or group meeting decks, thesis defense presentations, research seminars, invited talks, mixed-audience or industry research talks, OR wants to create, revise, or edit a talk deck or a specific slide of it (e.g. 'revise slide 7 of my conference talk'). Starts from an audience-facing story spine before slide titles, frameworks, screenshots, or feature lists; then applies Assertion-Evidence and Mayer multimedia principles. For teaching/lecture slides use `teaching-marp-slides`; for written documents use `paper-writing` or `scientific-writing`; for individual figures use `scientific-visualization`.
Create or revise lecture/teaching slides in Markdown using Marp for upper-undergraduate and graduate courses across any academic discipline. Use when the user needs classroom lecture slides, course materials, tutorial slides, or workshop sessions — including a request framed as creating or editing a slides Markdown file (e.g. a '*_slides.md' in a course or week folder) for teaching a class — or wants to revise existing teaching slides. Enforces Cognitive Load Theory, worked-example effect, scaffolding, and retrieval practice principles. Produces both a lecture version and a handout version. For research/conference talks use `academic-marp-slides`; for written documents use `paper-writing` or `scientific-writing`.
Strategically revise an existing CS/AI/Systems conference paper draft for resubmission or submission readiness. Focuses on framing diagnosis, claim crystallization, narrative unification, evidence strengthening, reviewer defense, and venue-aware polish.
Write publication-ready ML/AI/Systems conference papers (NeurIPS, ICML, ICLR, ACL, AAAI, COLM, OSDI, NSDI, ASPLOS, SOSP). Use when the user requests a conference manuscript, needs conference-specific templates/checklists, or format conversion between venues. For journal articles or technical reports, use scientific-writing instead.
Core skill for high-quality research strategy, topic exploration, idea generation, scope/framing critique, contribution assessment, and mentor-style research direction refinement. Use when the user asks whether an idea is worth pursuing, wants brainstormed research directions, needs to pivot, sharpen a paper/proposal scope, evaluate novelty, identify the strongest objection, or turn a vague area into a concrete, testable research plan. Produces a small number of high-bar candidates with premise audits, nearest alternatives, decisive experiments, and kill criteria.
Prompt guidance for the generate_diagram tool — how to describe different scientific diagram types (flowcharts, pathways, architecture, circuits, networks, conceptual) so the tool produces publication-grade output on the first iteration.
| name | compute-stub |
| description | Diagnostic in-memory compute backend. Use ONLY when the user explicitly asks to verify that the compute pipeline (Registry → IPC → renderer) is wired correctly without invoking real shells or remote services. Off by default — register via ENABLE_COMPUTE_STUB=1. |
| category | Compute |
| tags | ["compute","diagnostic","stub","qa"] |
| triggers | ["diagnose compute","compute health check","verify pipeline","stub backend","test compute"] |
| license | MIT |
| metadata | {"skill-author":"Research Copilot"} |
Stub backend (backend: 'stub', toolPrefix: 'stub') is an in-memory no-op that simulates plan/run/stop without invoking any real subprocess or remote API. Available only when the developer sets ENABLE_COMPUTE_STUB=1.
Do NOT use for real work — there's no actual computation happening.
The stub parses keywords from the command string:
| Command contains | Behavior |
|---|---|
| (default) | Sleeps 100ms then completes with exit code 0 |
SLOW | Sleeps 5000ms (use to exercise stub_stop) |
FAIL | Sleeps 100ms then exits with code 1 + sets failure.code = COMMAND_FAILED |
Combine freely — e.g. SLOW job that may FAIL waits 5s then fails.
list_compute_backends() — confirm stub is registered.compute_plan({ backend: 'stub', command: 'health check' }) — no approval gate.stub_execute({ plan_id }) — kicks off the timer.stub_wait({ run_id }) — blocks until terminal.stub_stop({ run_id }) — cancels (useful for SLOW runs).If the stub flow succeeds end-to-end but local_* / modal_* flows don't, the bug is backend-internal (sandbox provider, Modal CLI, etc.), not registry/IPC/renderer plumbing.
lib/compute/backends/stub/stub-backend.ts is also the canonical
reference implementation for RFC §19 (Adding a new compute backend).
It demonstrates every ComputeBackend method against the simplest
possible state (a Map + setTimeout), so you can read the whole file
in under 5 minutes and see the contracts in action.