Agent Skills catalog · page 157
Standard HTML pagination keeps the complete catalog discoverable. Use the main directory for search, filtering, and comparison.
- Current page
- 157/209
- Entries on page
- 24
- URL status
- Self-canonical
richkuo/rk-skills
prd-to-issues
Use when the user wants a finished PRD broken into GitHub milestones and issues — "file the issues from the PRD", "/prd-to-issues", "break this into GitHub issues". Derives dependency-ordered milestones, files complete complexity-scored issues (github-issue-format), and stamps each with an Execution block (typed predecessors, build model, effort, fableplan, plan effort, review trigger). Stage 4 of the new-app-pipeline.
richkuo/rk-skills
validate-issue
Use when the user asks to validate, review, or check whether a GitHub issue is valid. Accepts an issue reference or defaults to the latest open issue, verifies every factual claim against current code, assesses non-trivial proposals, scores complexity, and returns a cited update decision.
zjunlp/Mechanist
paper-figure
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 figures embedded into `CLAIMS_LEDGER.md`.
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
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"
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
zjunlp/Mechanist
notify
Draft a research-progress briefing and dispatch it through whatever notification service the user has already configured. Channel-agnostic — this skill only drafts the briefing text and scans for a configured service; it does not hard-code or recommend any particular channel or tool. Opt-in: it does nothing unless task.md asks for notifications (e.g. email reminders). Every briefing is saved to notification/ (never overwritten). Called by /auto on an hourly cadence and at progress / done / halte
SpartanLabsXyz/simmer-sdk
simmer-skill-builder
Generate complete, installable OpenClaw trading skills from natural language strategy descriptions. Use when your human wants to create a new trading strategy, build a bot, generate a skill, automate a trade idea, turn a tweet into a strategy, or asks "build me a skill that...". Produces a full skill folder (SKILL.md + Python script + config) ready to install and run.
zjunlp/Mechanist
verify-pick-alternatives
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 by /auto-verify.
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`.
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.
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.
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-
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.
TserenTserenov/FMT-exocortex-template
skill-creator
Create a new IWE skill with proper frontmatter, gates, scaffold and verification. Use when the pilot says: /skill-creator or «создай скилл <name>». The skill enforces WP Gate precondition, Routing Gate, IntegrationGate hard-check, collects parameters in 4 short steps, generates a scaffold SKILL.md from a template, shows a draft, writes files, and reminds about verify-skill.sh.
SpartanLabsXyz/simmer-sdk
polymarket-fast-loop
Trade Polymarket BTC 5-minute and 15-minute fast markets using CEX price momentum signals via Simmer API. Default signal is Binance BTC/USDT klines. Use when user wants to trade sprint/fast markets, automate short-term crypto trading, or use CEX momentum as a Polymarket signal.
SpartanLabsXyz/simmer-sdk
polymarket-weather-trader
Trade Polymarket weather markets using NOAA (US) and Open-Meteo (international) forecasts via Simmer API. Inspired by gopfan2's weather trading approach. Use when user wants to trade temperature markets, automate weather bets, check forecasts, or run weather-based strategies.
zjunlp/Mechanist
research-refine
Turn a vague research direction into a problem-anchored, elegant, frontier-aware, implementation-oriented method plan via iterative external LLM review (llm-chat MCP). Use when the user says "refine my approach", "decompose this problem", "refine research plan", or wants a concrete research method that stays simple, focused, and top-venue ready instead of a vague or overbuilt idea.
SpartanLabsXyz/simmer-sdk
simmer-x402
Make x402 payments to access paid APIs and gated content. Use when a skill needs to fetch data from x402-gated endpoints (like Kaito mindshare API, Simmer premium endpoints, or any x402 provider). Handles 402 Payment Required responses automatically using USDC on Base.
zjunlp/Mechanist
steer-features
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 to control behavior. Applies to features read from the model's own activations or from a Sparse Autoencoder (SAE); the bundled demo scripts happen to use an SAE, but the method does not require one.
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.
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.
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
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.