Skill Claude Code
A complete research workflow that covers idea discovery, implementation, review, and optional paper writing.
not rated 5 2mo ago A 83 tokens
Skill Claude Code
An end-to-end workflow that turns a vague research direction into a focused proposal and a detailed experiment roadmap.
not rated 5 2mo ago A 73 tokens
Skill Claude Code
A planning workflow that turns a broad research direction into a focused method plan with implementation details and awareness of current work.
not rated 5 2mo ago A 101 tokens
Skill Claude Code
Get a deep critical review of research from GPT via Codex MCP. Use when user says "review my research", "help me review", "get external review", or wants critical feedback on research ideas, papers, or experimental results.
not rated 5 2mo ago A 50 tokens
Skill Claude Code
A persistent research knowledge base for storing papers, ideas, experiments, claims, and links between them.
not rated 5 2mo ago A 73 tokens
Skill Claude Code
Workflow 5: orchestrate a text-only resubmit of a polished paper to a different venue under hard constraints (no new experiments, no bib edits, no framework changes, never overwrite prior submissions). Phase 0 physical isolation, Phase 0.5 health + anonymity check, Phase 1 audit (proof / claim / citation), Phase 2…
not rated 5 2mo ago A 176 tokens
Skill Claude Code
Use when experiments complete to judge what claims the results support, what they don't, and what evidence is still missing. Codex MCP evaluates results against intended claims and routes to next action (pivot, supplement, or confirm). Use after experiments finish — before writing the paper or running ablations.
not rated 5 2mo ago A 63 tokens
review
80Skill Claude CodeCodex
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/PRD asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use…
not rated 5 2mo ago A 95 tokens
reviewer
81Skill Claude Code
An independent reviewer role that examines plans, code, experiments, claims, or papers from the original input and returns a decision with supporting findings.
not rated 5 2mo ago A 37 tokens
Skill Claude Code
An experiment runner for machine-learning jobs on local machines, remote servers, Vast.ai, or Modal serverless GPUs.
not rated 5 2mo ago A 47 tokens
Skill Claude Code
Runtime Task protocol contract for dispatched Labline roles. Use when acting as or dispatching Leader, Planner, Coder, Deployer, Writer, or Reviewer so status snapshots, terminal decisions, and superseded/resolved task events are written consistently.
not rated 5 2mo ago A 54 tokens
Skill Claude Code
Search published venue papers (IEEE, ACM, Springer, etc.) via Semantic Scholar API. Complements /arxiv (preprints) with citation counts, venue metadata, and TLDR. Use when user says "search semantic scholar", "find IEEE papers", "find journal papers", "venue papers", "citation search", or wants published literature…
not rated 5 2mo ago B 80 tokens
Skill Claude Code
Run GPU workloads on Modal — training, fine-tuning, inference, batch processing. Zero-config serverless: no SSH, no Docker, auto scale-to-zero. Use when user says "modal run", "modal training", "modal inference", "deploy to modal", "need a GPU", "run on modal", "serverless GPU", or needs remote GPU compute.
not rated 5 2mo ago A 79 tokens
Skill Claude CodeCodex
Analyze skill dependency impact before modification. Shows upstream dependencies, downstream dependents, and artifact flow. Use when planning to modify, rename, or remove a skill, or when investigating skill relationships.
not rated 5 2mo ago A 43 tokens
Skill Claude Code
Per-page Codex review + targeted python-pptx / Beamer fixes for academic talk slides. Use AFTER /paper-slides (or any externally generated PPTX/Beamer) when the deck looks 'mostly OK' but the user wants a final pass that aligns visual weight with a reference, bumps PPTX fonts to projector-readable size, kills italic…
not rated 5 2mo ago A 136 tokens
Skill Claude Code
A workflow for writing a complete patent specification from patent claims and an invention disclosure.
not rated 5 2mo ago A 49 tokens
sync
89Skill Claude Code
A guided workflow for syncing a research project with a remote repository and deployment target. It bundles common version-control commands so users do not need to know Git.
not rated 5 2mo ago A 30 tokens
Skill Claude Code
Profile a target (script, process, GPU, memory, interconnect) using external tools and code instrumentation. Produces structured performance reports with actionable recommendations. Use when user says "profile", "benchmark", "bottleneck", or wants performance analysis.
not rated 5 2mo ago A 54 tokens
tdd
91Skill Claude CodeCodex
Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.
not rated 5 2mo ago A 45 tokens
to-issues
92Skill Claude CodeCodex
Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices. Use when user wants to convert a plan into issues, create implementation tickets, or break down work into issues.
not rated 5 2mo ago A 53 tokens
to-prd
93Skill Claude CodeCodex
Turn the current conversation context into a PRD and publish it to the project issue tracker. Use when user wants to create a PRD from the current context.
not rated 5 2mo ago A 36 tokens
Skill Claude Code
Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.
not rated 5 2mo ago A 35 tokens
vast-gpu
95Skill Claude Code
Rent, manage, and destroy GPU instances on vast.ai. Use when user says "rent gpu", "vast.ai", "rent a server", "cloud gpu", or needs on-demand GPU without owning hardware.
not rated 5 2mo ago A 46 tokens
Skill Claude CodeCodex
Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.
not rated 5 2mo ago A 35 tokens
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: