Menu
O SkillsMP coletou 84 skills de zjunlp/Mechanist. Abra uma skill para revisar a origem e os detalhes.
Mostrando 40 de 84 skills coletadas.
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…
Idioma do texto original: inglês
Autonomous research review loop that consumes /auto-verify's four-state output (PASS / FAIL / INCONCLUSIVE / ZERO_ELIGIBLE_VARIANTS / deferred) and routes each claim to the right back-edge — brief audit, two-phase FAIL handling (variant-integrity fix then…
Idioma do texto original: inglês
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 AUTO_PROCEED-governed; defaults run end-to-end without human…
Idioma do texto original: inglês
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…
Idioma do texto original: inglês
Workflow 1.5: Bridge between idea discovery and auto review. Reads EXPERIMENT_PLAN.md, routes mechanism family inline (Phase 1.5), implements experiment code, deploys to GPU, and collects initial results. Use when user says "implement experiments",…
Idioma do texto original: inglês
Automated pipeline for generating and refining multiple research hypotheses.
Idioma do texto original: inglês
Routing entry point for experiment-protocol tips that prevent silent reproducibility / overclaim failures. Use when EXPERIMENT_PLAN.md is about to become runnable code and any of these is in scope: ImageNet / torchvision preprocessing, steering coefficient (α…
Idioma do texto original: inglês
Routing entry point for eleven families of mechanistic-interpretability methods that localize *which* internal object (layer, attention head, neuron, SAE feature, weight, or input feature) drives a model's behavior, *how influential* it is, and *what changes*…
Idioma do texto original: inglês
Mechanist's single conversational front door, with three parallel tracks: (A) when the user wants to run an experiment, work out the research requirements through conversation, settle the two parameter axes of /auto (behavior-source × mechanism), write a…
Idioma do texto original: inglês
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*…
Idioma do texto original: inglês
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…
Idioma do texto original: inglês
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`,…
Idioma do texto original: inglês
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, n_effective…
Idioma do texto original: inglês
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…
Idioma do texto original: inglês
Representation and Parameter Analysis interprets and controls a model by directly manipulating its two kinds of internal objects — features (the hidden-state activations produced during a forward pass) and weights (the parameters of the target model). The…
Idioma do texto original: inglês
Workflow 1: Claim-stage pipeline, controlled by two orthogonal axes. BEHAVIOR_SOURCE 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…
Idioma do texto original: inglês
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…
Idioma do texto original: inglês
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…
Idioma do texto original: inglês
Magnitude Analysis methods serve as a fundamental heuristic in interpretability, operating on the premise that internal elements with larger numerical values often exert greater influence on the model’s computation. It scores internal objects via a scalar…
Idioma do texto original: inglês
Generate a structured, publication-quality research-history markdown article for a given topic. Uses the cloud `mechanic_database` SEARCH service via skill `/mechanic-db-search` (TWO PARALLEL passes — `temporal_mode=history` for the long arc +…
Idioma do texto original: inglês
Standalone one-shot multi-source literature search. Takes a single query and returns one merged, ranked result set + synthesized landscape from the internet (web + arXiv), local channels (Zotero, Obsidian, local PDFs), and the cloud mechanic-db SEARCH…
Idioma do texto original: inglês
Generate publication-quality figures and tables from experiment results. Use when user says "plot this", "make a figure", "generate figures", "paper figures", or needs plots for a paper. Also invoked by `/auto`'s Ledger Figures hook to produce per-claim…
Idioma do texto original: inglês
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…
Idioma do texto original: inglês
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.
Idioma do texto original: inglês
Search and analyze research papers, find related work, summarize key ideas. Use when user says "find papers", "related work", "literature review", "what does this paper say", or needs to understand academic papers.
Idioma do texto original: inglês
Get a deep critical review of research from an external LLM reviewer via llm-chat 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.
Idioma do texto original: inglês
Use this skill for feature-level steering of models — locating the internal feature that drives a target behavior, scoring and selecting it by its effect on the model's output, and directly amplifying or shrinking that feature's activation during generation…
Idioma do texto original: inglês
Vocabulary Projection methods interpret internal model states by projecting them through the unembedding matrix to obtain a distribution over the vocabulary. The core idea is that the unembedding matrix, which maps the final hidden state to output logits, can…
Idioma do texto original: inglês
Use when main results pass result-to-claim (claim_supported=yes or partial) and ablation studies are needed for paper submission. The external LLM reviewer (via llm-chat MCP) designs ablations from a reviewer's perspective, CC reviews feasibility and…
Idioma do texto original: inglês
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.
Idioma do texto original: inglês
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…
Idioma do texto original: inglês
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…
Idioma do texto original: inglês
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`…
Idioma do texto original: inglês
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]` /…
Idioma do texto original: inglês
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…
Idioma do texto original: inglês
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.
Idioma do texto original: inglês
Analyze and dissect factual recall in auto-regressive language models using attention knockout, hidden state analysis, and intervention techniques on GPT-2 and GPT-J models
Idioma do texto original: inglês
Use when analyzing neural network circuits, performing attribution patching, automated circuit discovery, or investigating model interpretability through edge attribution methods in transformer models
Idioma do texto original: inglês
Use this skill when you need to edit factual knowledge in large language models like GPT-2 or GPT-J, perform causal tracing to understand model behavior, or implement Rank-One Model Editing (ROME) to modify specific factual associations without retraining
Idioma do texto original: inglês
Causal Attribution methods constitute the gold standard for localization in Mechanism Interpretability. Unlike correlation-based analyses, these techniques identify which internal objects are causally responsible for a specific model behavior by…
Idioma do texto original: inglês