Skill Claude CodeCodex
Search, download, and summarize academic papers from arXiv. Use when user says "search arxiv", "download paper", "fetch arxiv", "arxiv search", "get paper pdf", or wants to find and save papers from arXiv to the local paper library.
Skill Claude CodeCodex
Workflow 1: Claim-stage pipeline, controlled by two orthogonal axes. BEHAVIORSOURCE selects the behavior stage: given (default; behavior taken from task.md and assumed to hold — no ideation, no novelty, no M0), given-validation (behavior taken from task.md but the experiment plan opens with an M0 phenomenon-validation…
Skill Claude CodeCodex
Workflow 1.5: Bridge between idea discovery and auto review. Reads EXPERIMENTPLAN.md, routes mechanism family inline (Phase 1.5), implements experiment code, deploys to GPU, and collects initial results. Use when user says "implement experiments", "experiment", "deploy the plan", or has an experiment plan ready to…
Skill Claude CodeCodex
Autonomous research review loop that consumes /auto-verify's four-state output (PASS / FAIL / INCONCLUSIVE / ZEROELIGIBLEVARIANTS / deferred) and routes each claim to the right back-edge — brief audit, two-phase FAIL handling (variant-integrity fix then optional claim-stage re-entry), main-experiment-script fix, or…
Skill Claude CodeCodex
Workflow 1.75: stress-test claims (regardless of main-experiment verdict) by swapping method, dataset, and model, then judging whether each variant agrees with the main experiment. Three stages with two integrity gates: Stage 1 audits the main experiment's eval method for every target claim; Stage 2 runs swap variants…
Skill Claude CodeCodex
Sub-skill of /auto-verify. Given a claim, choose one method swap, one dataset swap, and one model swap that most strongly stress-test the claim. Harvests candidates from existing research; calls /research-lit only when coverage is thin. Use when user says "pick swaps for claim", "choose alternatives", or when invoked…
Skill Claude CodeCodex
Autonomous pipeline: claim → experiment (mechanism routing folded in) → verify → iteration. Each stage is delegated to an isolated agent with its own context window and configurable model. Gates are AUTOPROCEED-governed; defaults run end-to-end without human input. Use when user says "auto pipeline", or wants the core…
Skill Claude CodeCodex
The single place for every data constraint an experiment must satisfy — dataset provenance (existing → adapted → constructed), clear train / validation / test splits, labels that reflect the target behavior, and the minimum data amount. Use whenever an experiment chooses, adapts, or constructs a dataset, defines…
Skill Claude CodeCodex
Audit the experimental methodology integrity for a specific claim (Checks A–F: GT provenance, score normalization, result-file existence, dead code, scope, eval-type). Uses cross-model review (external LLM reviewer via llm-chat MCP). The output overallverdict (PASS/WARN/FAIL) is THIS claim's verdict — i.e., whether…
Skill Claude CodeCodex
Turn a refined research proposal or method idea into a detailed, claim-driven experiment roadmap. Use after research-refine, or when the user asks for a detailed experiment plan, ablation matrix, evaluation protocol, run order, compute budget, or paper-ready validation that supports the core problem, novelty…
Skill Claude CodeCodex
SSH job queue for multi-seed / multi-config ML experiments with OOM-aware retry, stale-screen cleanup, wave-transition race prevention, and phase-dependency enforcement. Use when user says "batch experiments", "queue experiments", "run grid", "multi-seed sweep", "auto-chain experiments", or when /run-experiment is…
Skill Claude CodeCodex
Routing entry point for experiment-protocol tips that prevent silent reproducibility / overclaim failures. Use when EXPERIMENTPLAN.md is about to become runnable code and any of these is in scope: ImageNet / torchvision preprocessing, steering coefficient (α / dose / magnitude), steering block / layer / site…
Skill Claude CodeCodex
Fine-tuning LR protocol — full FT, LoRA / QLoRA / DoRA / PEFT adapter, across SFT, DPO, and GRPO / PPO / RL objectives. Fires on ANY fine-tune, including (especially) when the plan already fixes a learning rate or copies one from a reference paper: a fixed LR is one grid point, never the answer, so LR is always swept…
Skill Claude CodeCodex
Canonical ImageNet eval preprocessing — square 256×256 resize → 224 center crop → ImageNet mean/std — for CV experiments probing ImageNet-pretrained backbones (ResNet, ViT, VGG, EfficientNet). Use this skill whenever a torchvision.transforms / PIL pipeline is being written, audited, or debugged for inference-time…
Skill Claude CodeCodex
How to grade any multiple-choice / A-B / A-D letter task when the score is read out of the model's free-form output — any eval that maps a generation to a choice letter, whatever the domain. Use whenever the plan parses the letter with a regex like [A-D] / re.search(r"[AB]", ...). Covers why naive letter-regex is…
Skill Claude CodeCodex
How to choose where (and how many sites) to intervene for any operation on internal representations — activation patching, steering, CAA, DAS, SAE feature scaling, attribution patching. Use whenever the plan declares a target block / layer / site, especially when it hard-codes a single index (targetblock: 4, layer…
Skill Claude CodeCodex
How to set the strength of any additive intervention on internal representations — steering vectors, CAA, DAS dose-response, representation engineering, SAE feature scaling, ROME-style edits. Use whenever the plan pins a steering strength (α, β, dose, magnitude, scale, coefficient, k) to a fixed value or a narrow…
Skill Claude CodeCodex
Automated pipeline for generating and refining multiple research hypotheses.
Skill Claude CodeCodex
Generate and rank research ideas given a broad direction. Use when user says "brainstorm ideas", "generate research ideas", "what can we work on", or wants to explore a research area for publishable directions.
Skill Claude CodeCodex
Assess whether the research problem/behavior is important — its potential value and reach. Use when user says "impact check", "check impact", or wants to judge whether an idea/behavior matters before committing.
Skill Claude CodeCodex
Paper retrieval via the cloud SEARCH service. The Agent builds a decomposed query JSON from its task context (preferred) or submits a polished free-form English query; the cloud service performs multi-ranker retrieval and fusion. Use as one of an important paper sources.
Skill Claude CodeCodex
Audit the mechanistic experiment rigor for a specific claim. Catalogue currently has six slots A–F: A (steering coefficient sweep) is implemented; B–F are reserved for future checks (direction extraction quality, site/layer selection, neffective sufficiency, probe-vs-causal disentanglement, intervention scope). Uses…
Skill Claude CodeCodex
Mine behavioral regularities in neural-network (LLM / multimodal) models — the upstream half of the project's mission (find a behavior worth explaining, then investigate the mechanism behind it). Use this skill when the task is open-ended: surface a new behavioral phenomenon — a candidate claim / research direction …
Skill Claude CodeCodex
Macro-level strategic directions for investigating the mechanism behind a model behavior — the downstream half of the project's mission (mine LLM behaviors, then explain the mechanism behind them). Use once a phenomenon is observed in a model — whether already established/known or freshly mined by…