1.4K skills · sorted by relevance
Evaluate LLM outputs using frontier models as judges. Use for pairwise model comparison, quality scoring with custom rubrics, and automated evaluation pipelines. Covers position bias mitigation, statistical significance, and generating preference data for DPO/RLHF.
The English summary is being prepared. Showing the original description.
Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language support, or measuring code generation quality. Industry standard from BigCode Project used by HuggingFace leaderboards.
The English summary is being prepared. Showing the original description.
Iterative lead optimization with analyze-reason-generate-verify-evaluate loop. Paper-backed (MT-Mol, DrugR, MultiMol).
The English summary is being prepared. Showing the original description.
Evaluate an interface from a UX perspective, assessing hierarchy, information architecture, emotional resonance, cognitive load, and overall quality with evidence-linked judgments and actionable feedback. Use when the user wants an overall design or UX review—not when the main need is measurable accessibility/performance diagnosis, or final micro-detail polish.
The English summary is being prepared. Showing the original description.
Help teams prepare materials for an SCF referral. Use when a team wants to approach a referrer (SCF Pilot, SDF staff, alumni who completed deliverables, ambassador, or ecosystem partner) with a strong package that makes it easy for the referrer to evaluate and endorse them. Covers the referral form fields, what referrers assess, and how to present your project for referral.
The English summary is being prepared. Showing the original description.
Evaluate system boundaries and architectural tradeoffs. Use for architecture decisions, design reviews, and ADRs.
The English summary is being prepared. Showing the original description.
When the user wants to plan, evaluate, or build a free tool for marketing purposes — lead generation, SEO value, or brand awareness. Also use when the user mentions "engineering as marketing," "free tool," "marketing tool," "calculator," "generator," "interactive tool," "lead gen tool," "build a tool for leads," or "free resource." This skill bridges engineering and marketing — useful for founders and technical marketers.
The English summary is being prepared. Showing the original description.
Evaluate AI model performance with metrics, benchmarks, and comparison. TRIGGERS - Use when user needs help with ai-model-evaluator related tasks.
The English summary is being prepared. Showing the original description.
Evaluate AI copilot performance. TRIGGERS - Use when user needs help with ai-copilot-evaluation related tasks.
The English summary is being prepared. Showing the original description.
Evaluate and implement agricultural technology solutions. TRIGGERS - Use when user needs help with agricultural-technology related tasks.
The English summary is being prepared. Showing the original description.
Evaluate AI agent performance and reliability. TRIGGERS - Use when user needs help with ai-agent-evaluation related tasks.
The English summary is being prepared. Showing the original description.
Evaluate third-party logistics providers. TRIGGERS - Use when user needs help with 3pl-evaluation related tasks.
The English summary is being prepared. Showing the original description.
Installs the CARLA Autonomous Driving Leaderboard (leaderboard.carla.org) at a chosen version — 1.0, 2.0 or 2.1 — together with the exact scenario_runner branch and CARLA build each one requires, then wires the four-root PYTHONPATH and verifies the whole stack imports. Detects which version an existing checkout is by reading its code, not its branch name. Use when the user asks to "install the leaderboard", "set up the CARLA challenge", "evaluate my driving agent", "reproduce my leaderboard score", or names a leaderboard version.
The English summary is being prepared. Showing the original description.
Runs the CARLA Leaderboard evaluator over a set of routes with your agent — routes/routes-subset/repetitions/track selection, checkpoint and live-results endpoints, resume after a crash, recording, and the debug levels — for leaderboard 1.0, 2.0 or 2.1. Preflights the whole stack (version pairing, maps, ports, agent class, sensor budget) before spending hours, and hands the world back in async mode. Use when the user asks to "run the leaderboard", "evaluate my agent", "run routes_training", "resume an evaluation", or "reproduce my submission locally".
The English summary is being prepared. Showing the original description.
Help a user talk through whether to change jobs, stay, or change something in their current work, starting from uncertainty, distress, a vague sense of stagnation, an offer in hand, a counter-offer from the current employer, or pressure from family or colleagues. Clarify what matters, separate deadlines that order the next steps from the decision itself, compare conditional options, and agree on a small next step and a time to revisit it. Use when someone asks whether they should quit, wonders whether leaving is just running away, has second thoughts after receiving an offer or being asked to stay, feels stuck because others say it would be a waste, wants to leave soon after joining, or wants advice before deciding to start a job search; do not make the final stay-or-leave decision, evaluate offer terms, plan the resignation, or predict hiring outcomes.
The English summary is being prepared. Showing the original description.
Read a Japanese job posting closely and report what it actually states: base pay separated from fixed overtime allowance, the range converted to an hourly basis, required versus preferred requirements, and the terms left ambiguous. Use when a user wants a 求人票 or job description examined before applying, wants two postings compared on the same basis, or wants questions prepared about pay and working conditions; do not use to judge whether the user will be hired, to infer duties the posting does not state, or to evaluate the employer's reputation.
The English summary is being prepared. Showing the original description.
Identify the first beachhead market segment for a product launch. Evaluates segments against burning pain, willingness to pay, winnable market share, and referral potential. Use when choosing a first market, targeting an initial customer segment, or planning market entry strategy.
The English summary is being prepared. Showing the original description.
Evaluates genome assembly quality across the three orthogonal axes - contiguity (QUAST auN/NG50/NGx, not bare N50), completeness (BUSCO/compleasm gene-space plus Merqury k-mer completeness), and correctness (reference-free Merqury QV, Inspector/CRAQ structural errors, asmgene false-duplication/collapse). Covers why N50 is the most-gamed metric, why QV measured on the polishing reads is circular, distinguishing uncollapsed haplotigs from real WGD, and the EBP/VGP 6.C.Q40 standard. Use when judging whether an assembly is good enough to annotate or publish, comparing assemblers, diagnosing a fragmented or duplicated assembly, or assessing a phased diploid assembly.
The English summary is being prepared. Showing the original description.
Evaluate deliverable quality — scorecard, outcome tracking, regression checklist, and aggregate stats.
The English summary is being prepared. Showing the original description.
Uncorrelated Evaluator — 4軸ルーブリック専門エージェント（functionality-reviewer・code-reviewer・design-reviewer・originality-reviewer）と security-reviewer を5並列実行し、成果物を多面的に独立評価します。PASS / NEEDS WORK / BLOCKED 判定を返します。Self-leniency 防止のため、実装エージェントのコンテキストを引き継がない新規エージェントとして起動します。「レビューして」「評価して」「実装を確認して」などのリクエストで起動します。
The English summary is being prepared. Showing the original description.
Find and evaluate influencers for brand partnerships, verify authenticity, and track collaboration performance across Instagram, Facebook, YouTube, and TikTok.
The English summary is being prepared. Showing the original description.
Claude Codeセッションの効率を分析・スコアリングするWebツール。セッションログ（JSONL）を解析し、7観点100点満点で「無駄の有無」を評価。npx session-evaluatorで起動し、ブラウザUIでセッション選択→分析→改善提案まで実行可能。
The English summary is being prepared. Showing the original description.
Systematically evaluate weak, stale, or low-conviction theses for upgrade, monitoring, or closure. Use when user says "prune", "kill list", "clean up theses", "what should I close", or "reduce portfolio".
The English summary is being prepared. Showing the original description.
Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.
The English summary is being prepared. Showing the original description.