Autonomous experiment loop that optimizes any file by a measurable metric. Inspired by Karpathy's autoresearch.
Set up and run an autonomous experiment loop for any optimization target. Gathers what to optimize, then starts the loop immediately.
Generates email sequences for different contexts. Currently supports event follow-up sequences. Produces ready-to-send emails with subject lines, body copy, and timing guidance.
Karpathy AutoResearch Pattern -- autonome Experiment-Loops die overnight 100 Iterationen ohne menschliches Eingreifen durchfuehren.
Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear optimization targets.
Autonomous UX violation fixer. Scans for hardcoded colors, Navigator.push, raw Material colors, missing Semantics. Fixes ONE file per iteration.
Autonomous orchestrator for green-light / overnight execution. Takes one task and runs the full engineering cycle (research → plan → sprint → audit → report) end-to-end without…
Observe the user's screen via screenpipe, detect repeated research workflows, match them against existing scientific-agent-skills, and draft new skills (or composition recipes…
Produces structured aviation law summaries with Bluebook citations covering U.S. and international regulatory frameworks, treaties, and case law.
Produces an enforcement-aware Animal Welfare Act compliance audit for USDA/APHIS-regulated facilities. Maps Form 7002 inspection citations to verified 9 C.F.R.
Turn Markdown, research notes, reports, or any content into a polished, self-contained single-file HTML document styled with the AwesomeDesignSystem.
Create a topic-specific GitHub awesome-list repository scaffold with a polished README, concise contribution rules, AI-agent instructions, URL verification, license, and reusable…
Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss.
Use when researching Apple frameworks, APIs, or WWDC sessions - provides techniques for retrieving full transcripts, code samples, and documentation using Chrome browser and…
Audit Axiom logs to identify and prioritize errors and warnings, research probable causes, and flag log smells.
Use when building ANY 2D or 3D game with SpriteKit, SceneKit, or RealityKit. Covers scene graphs, ECS, physics, actions, game loops, rendering, SwiftUI integration.
Expert SRE investigator for incidents and debugging. Uses hypothesis-driven methodology and systematic triage. Can query Axiom observability when available.
Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support — from axolotl-ai-cloud/diff-transformer
Expert knowledge for Azure Data Science Virtual Machines development including troubleshooting, decision making, architecture & design patterns, security, configuration,…
Expert knowledge for Azure Quantum development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security,…
Helps create, configure, and deploy Azure Static Web Apps using the SWA CLI. Use when deploying static sites to Azure, setting up SWA local development, configuring…
Use when actively investigating a hypothesis — running a sweep, dispatching multi-agent analysis, designing serial adversarial gates, enriching per-trade data for loss postmortem,…
Searches across your Notion workspace, synthesizes findings from multiple pages, and creates comprehensive research documentation saved as new Notion pages.
Run repeatable cross-forge repository backup jobs from one config instead of hand-scripting clone and export steps per provider.
Find the best backend architecture, database design, and API patterns using deep research. Use when user asks "best database for...", "optimize API", "backend architecture…
Use when when predicting one data modality (e.g., metabolite abundances) from another (e.g., microbiome composition) and you need to distinguish genuine microbe–metabolite…
通用期貨/股票回測框架。涵蓋策略開發、回測引擎、IS/OOS 驗證、robustness 評分、NH 計算、參數優化、視覺化。適用任何標的任何 K 線頻率。當使用者提到回測、策略、backtest、robustness、NH、optimize、autoresearch 時觸發。
Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.
Annotate bacterial and archaeal genomes and plasmids with Bakta's Prodigal/HMM/diamond pipeline. Identifies CDS, ncRNA, tRNA, rRNA, tmRNA, sORFs, CRISPR arrays, oriC/oriV/oriT,…
Steuere Bambu Lab 3D-Drucker (A1, P1P, X1) über MQTT. Nutze diesen Skill für Druck-Überwachung, Status-Abfragen, Steuerung (Pause/Stopp) und Benachrichtigungen bei Drucke — from…
Create banners using AI image generation. Discuss format/style, generate variations, iterate with user feedback, crop to target ratio.
Add or review a new bansos.dev listing efficiently. Use when an AI agent needs to research a promo/freebie/program source, convert it into validated bansos.dev data, run or…
Use when you have a coordinate-sorted BAM file from a single-cell ATAC-seq experiment (especially 10X Genomics platforms) and need to extract per-fragment information including…
Use when before peak detection on a composite or individual mass track when you need to filter out low-intensity noise and baseline drift without removing true signal.
Use when your research proposes a new spectral embedding, matching algorithm, or retrieval method and you need to quantify its improvement over known baselines.
Estimate baseline serum creatinine for AKI assessment in MIMIC-IV. Use for KDIGO staging, AKI research, or renal function baseline establishment.
A biomedical research topic designer that generates progressive experimental subtitles and detailed research outlines based on a given subject.
Performs and explains basic statistical calculations — percentages, percentage changes, per-capita rates, averages, medians, and ratios — from data you provide, showing the…
Use when after batch correction has been applied to metabolomics data using pooled SQC samples, and you need to retrieve the corrected ratios (compound / internal standard) for…
Designs experiments to minimize and account for batch effects using balanced layouts and blocking strategies.
Use when when you have a trained molecular classifier (like BitterPredict) that accepts structured descriptor input, and you need to understand which chemical descriptor subgroups…
Use when when ingesting spectra from multiple open mass spectrometry libraries (OMSLs) in .mgf, .msp, .json, or .csv format and you observe mixed experimental protocols,…
Helps choose the right battery type and charging solution for Arduino/ESP32/RP2040 projects. Use when user asks about battery options, charging circuits, power source selection,…
Use when you have experimental retention times (RTs) for a small set of calibration molecules (≥10) measured on both a source chromatographic method and a target method, and you…
Use when you have a pre-trained DNN RT predictor (e.g., trained on METLIN SMRT with 80,038 experimental RTs) and need to adapt it to predict retention times in a new or external…
Use when you need to transfer retention time predictions from one chromatographic method to another, but have access to only a small number (≥10) of molecules with known retention…
Bayesian approach to statistical inference and decision-making. Covers prior specification, likelihood functions, posterior computation, conjugate priors, Markov chain Monte Carlo…
Use when you have completed one or more LC-MS gradient runs, extracted separation efficiency metrics from the resulting MS1 and MS2 spectra, and need to incorporate those real…
Use when uncertainty must be updated after new evidence: start with a prior or base rate, estimate how strongly the evidence fits each hypothesis, update to a posterior, and…
Bayesian inference methods including prior selection, MCMC, and model comparison
Designs Bayesian clinical trials including Phase I dose-finding (BOIN, CRM, EWOC, mTPI-2), meta-analytic-predictive (MAP) priors with robust mixtures for external data bo — from…
Use when performing Bayesian statistical analysis, building probabilistic models, or when the task involves prior specification, posterior inference, or predictive checks.
Use at the START of any bug bounty hunting session, when switching targets, or when feeling lost about what to do next.
Skill para retornar estatísticas e dados sobre participantes do Big Brother Brasil de todas as edições, acompanhadas de um comentário que forneça mais contexto para o usuário.
Use on procedure terminal step, explicit customer close, session end, or pending-state submit-now branch.
Using BDD to validate architectural hypotheses in TMNL. Covers H1/H2/H3 hypothesis patterns from testbeds, connecting specs to acceptance criteria, and damage reports for…
Create Beamer-style academic PPTX presentations using python-pptx. Produces publication-quality .pptx files with navy-blue Metropolis theme (16:9, frame title bars, progress bar)…
BeatLab JSON contract for 16-step (0-15) pianoSequence & drumSequence. Use when generating or editing beats.
Deterministic BeatLab pipeline utilities (validate, render grid, export MIDI/WAV). Use for running scripts instead of reasoning about validation/rendering.
Extracts structured citation data from academic repositories using BeautifulSoup4 with lxml parser. Parses DOI metadata, author affiliations, and reference lists from PubMed,…