Your agent can do more. Find the skill that makes it happen.
Find your next superpower If you are an agent, refer to our llms.txt for full access.Covers Newick/Nexus files, topology edits, pattern matching, Robinson-Foulds comparisons, evolutionary events, reconciliation, and taxonomy. Supports SmartView exploration and publication rendering; tree inference from raw sequences is outside its scope.
Uses Yahoo Finance to compare ETF market prices with net asset value. Decomposes daily surges into underlying NAV changes and structural factors such as dealer hedging, gamma squeezes, and blocked authorized participant arbitrage.
Retrieves EV charging-station locations, charger types, and current status by region, station, or location text in Korea. Supports follow-up actions through official interfaces in Dolsoe.
Queries the Environment Ministry's zero-emission vehicle portal for local EV subsidy notices, applications, deliveries, and remaining allocations. Covers passenger cars, trucks, and buses, including application availability, exhaustion or closure, planned extra funding, and model-based subsidy estimates.
Scores and compares completed agent results within an AgentHub session. Uses metrics or an LLM judge to rank outputs and select a winner.
Evaluate a local skill with the terum-skills CLI — hygiene, trigger evals and execution cases against a baseline, billed to the user's own Claude Code — after confirming the cost, and show the result as a Markdown board. Use when the user asks to eval, test, score or benchmark a skill, or to see whether an edit made it better.
Assesses whether an LLM evaluation system is trustworthy and surfaces gaps in its methods and metrics. Supports reviewing inherited systems or assessing where evaluation infrastructure is absent, rather than building a new evaluator.
Guides evaluation-driven development for AI applications, including Python projects that call LLMs. Defines criteria, instruments runs, builds golden datasets, evaluates behavior, and analyzes results to produce an improvement plan.
Inspects agent repositories and optional traces, gathers user requirements, and produces reviewed task specifications and Harbor tasks. Covers controlled environments, synthetic data, verifiers, calibration, benchmark maintenance, and reusable project knowledge skills.
Create golden evaluation sets, failure-specific graders, and base-model baselines before fine-tuning. Convert traces into evaluation data and calibrate judges against human labels.
Score LLM and agent outputs using LLM-as-judge techniques — direct scoring against rubrics or pairwise comparison between two outputs. Includes built-in bias mitigation for position bias, length bias, and self-enhancement bias. Load when the user asks to score an output, judge a response, evaluate against a rubric, compare two outputs, do direct scoring, run pairwise comparison, or says "rate this…
Orchestrator for the eval-output skill suite — evaluate LLM and agent outputs for quality, accuracy, helpfulness, and safety using structured rubrics and LLM-as-judge techniques. Load when the user says "evaluate this output", "score this response", "run an eval", "LLM as judge", "evaluate agent output", "how good is this response", "rate this answer", "eval this", or provides an LLM output that s…
Skills give your agent reusable instructions for a specific job. Pick one, read what it does, and bring it into your workflow.
A name only tells half the story. Search the full description and instructions to find the right fit.
Read the skill, visit its source, and see exactly what you’re adding to your agent.
Copy the install command from a skill page and run it in your project.
npx skillycli add owner/repo --skill name