Repository profile

Mechanist

Review Skills in zjunlp/Mechanist, with license, maintenance context, and source paths.

Skills
19
Repository stars
48
Identity status
Source-linked

Provenance

Source and identity

Source-linked
Profile type
Repository
Canonical name
Mechanist
Public sources
1
License context
MIT

Source entries

Agent Skills from Mechanist

Repository stars and maintenance signals provide context, but do not automatically become an individual Skill's quality score.

Computed 9348

zjunlp/Mechanist

ablation-planner

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 implements.

Computed 9648

zjunlp/Mechanist

auto-claim

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 task.md but the experiment plan opens with an M0 phenomenon-validation gate), or `discovery` (mine a NEW behavior via /mechanism-behavior-discovery + full ideation: research-lit → idea-creator → novelty-check → impact-check → research-review → re

Computed 9348

zjunlp/Mechanist

auto-experiment

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", "experiment", "deploy the plan", or has an experiment plan ready to execute.

Computed 9548

zjunlp/Mechanist

auto-iteration-loop

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 optional claim-stage re-entry), main-experiment-script fix, or variant-only fix — under a unified iteration budget. Configure the reviewer LLM via llm-chat MCP server or environment variables. Trigger with "auto review loop llm" or "llm review"

Computed 9348

zjunlp/Mechanist

auto-verify

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 only on the top-K admitted claims picked by importance (K = `MAX_VERIFY_CLAIMS`, default 1); Stage 3 judges (binary pass/fail per variant), audits the variants, and computes a per-

Computed 9148

zjunlp/Mechanist

auto

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 input. Use when user says "auto pipeline", or wants the core stages chained without confirmation.

Computed 9148

zjunlp/Mechanist

clip-dissect

Use this skill when you need to automatically describe or interpret the functionality of individual neurons in deep neural networks (DNNs) using CLIP-based semantic analysis, perform mechanistic interpretability research on vision models, dissect convolutional or transformer-based image classifiers, identify what visual concepts activate specific neurons, or compare neuron descriptions across different probing datasets and concept sets.

Computed 9448

zjunlp/Mechanist

experiment-queue

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 insufficient for ≥10 jobs that need orchestration. `/auto-experiment` Phase 4 auto-routes here when a milestone declares ≥10 jobs or has `depends_on`.

Computed 9148

zjunlp/Mechanist

experiment-tips

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 / dose / magnitude), steering block / layer / site selection, fine-tuning hyperparameters (full FT / LoRA / QLoRA / DoRA / PEFT — LR, capacity, target modules — across SFT / DPO / GRPO / PPO / RLHF objectives), or MCQ / A-B / A-D letter-par

Computed 9148

zjunlp/Mechanist

fastshap

Use this skill when you need to train amortized Shapley value explainers using FastSHAP, generate real-time local feature importance explanations for machine learning models (tabular or image), train surrogate models for feature masking, or understand how FastSHAP's KernelSHAP-inspired training objective works with PyTorch.

Computed 9348

zjunlp/Mechanist

idea-creator

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.

Computed 9548

zjunlp/Mechanist

mechanism-audit

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 sufficiency, probe-vs-causal disentanglement, intervention scope). Uses cross-model review (external LLM reviewer via llm-chat MCP). Complementary to `/experiment-audit` (which audits evaluation methodology, not mechanism tuning). The output `overal

Pinned paths

Every entry links to a specific source path and commit when available.

Repository context

Activity, license, and repository-level popularity are shown as context.

Open the source

Inspect the public repository