Loading...
Loading...
Found 1,140 Skills
Fine-tunes and evaluates OpenVLA-OFT and OpenVLA-OFT+ policies for robot action generation with continuous action heads, LoRA adaptation, and FiLM conditioning on LIBERO simulation and ALOHA real-world setups. Use when reproducing OpenVLA-OFT paper results, training custom VLA action heads (L1 or diffusion), deploying server-client inference for ALOHA, or debugging normalization, LoRA merge, and cross-GPU issues.
Use when the user needs to build AI agents — tool use patterns, memory management, planning strategies, multi-agent coordination, evaluation, and safety guardrails. Triggers: user says "agent", "build an agent", "tool use", "agent loop", "multi-agent", "memory management", "guardrails", "agent evaluation".
Find bugs in the Stitch SDK using a real API key. Covers standard functional edges and tricky situations.
Comprehensive Amazon product research and opportunity analysis. Evaluate market demand, competition intensity, profit potential, and entry barriers for any product category or niche. Uses BSR data, review analysis, and pricing patterns.
Analyze HTTP security headers of web domains to identify vulnerabilities and misconfigurations. Use when you need to audit website security headers, assess header compliance, or get security recommendations for web applications. Trigger with phrases like "analyze security headers", "check HTTP headers", "audit website security headers", or "evaluate CSP and HSTS configuration".
LoRA, full fine-tuning, DPO preference tuning, VLM training, function-calling tuning, reasoning tuning, and BYOM uploads on Together AI. Reach for it whenever the user wants to adapt a model on custom data rather than only run inference, evaluate outputs, or host an existing model.
25+ proven headline formulas that stop the scroll, capture attention, and drive clicks. Templates and examples for every situation. Use when: Writing headlines for landing pages, ads, or articles; Creating email subject lines that get opens; Crafting social media hooks; A/B testing headline variations; Overcoming headline writer's block
Time-boxed technical investigation with structured output. Use for feasibility studies, architecture exploration, integration assessment, performance analysis, or risk evaluation. Creates spike tasks in ohno, enforces time-boxing, generates spike reports, and creates actionable follow-up tasks.
Advance one runnable thread by one bounded round from the minimal continuation entry, stopping on dirty interrupt files, pending proposals, or contract overreach.
Use when approaching any animation task—establishing foundational thinking patterns, teaching animation principles, or when none of the specialized thinking styles quite fit the situation.
Main orchestrator for README-first AI repo reproduction. Use when the user wants an end-to-end, minimal-trustworthy reproduction flow that reads the repository first, selects the smallest documented inference or evaluation target, coordinates intake, setup, trusted execution, optional trusted training, optional repository analysis, and optional paper-gap resolution, enforces conservative patch rules, records evidence assumptions deviations and human decision points, and writes the standardized `repro_outputs/` bundle. Do not use for paper summary, generic environment setup, isolated repo scanning, standalone command execution, silent protocol changes, or broad research assistance outside repository-grounded reproduction.
Calculates CRAP (Change Risk Anti-Patterns) score for .NET methods, classes, or files. Use when the user asks to assess test quality, identify risky untested code, compute CRAP scores, or evaluate whether complex methods have sufficient test coverage. Requires code coverage data (Cobertura XML) and cyclomatic complexity analysis. DO NOT USE FOR: writing tests, general test execution unrelated to coverage/CRAP analysis, or general code coverage reporting without CRAP context.