Menu
SkillsMP has collected 84 skills from zjunlp/Mechanist. Open a skill to review its source and details.
Showing 40 of 84 collected skills.
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…
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…
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…
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…
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",…
Automated pipeline for generating and refining multiple research hypotheses.
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…
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*…
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…
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*…
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…
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`,…
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…
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…
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…
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…
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…
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…
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…
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 +…
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…
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…
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…
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.
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.
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.
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…
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…
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…
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.
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…
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…
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`…
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]` /…
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…
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.
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
Use when analyzing neural network circuits, performing attribution patching, automated circuit discovery, or investigating model interpretability through edge attribution methods in transformer models
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
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…