Loading...
Loading...
Found 1,943 Skills
Use this skill for ANY question about creating test or evaluation datasets for LangChain agents. Covers generating datasets from traces (final_response, single_step, trajectory, RAG types), uploading to LangSmith, and managing evaluation data.
Design LLM-as-Judge evaluators for subjective criteria that code-based checks cannot handle. Use when a failure mode requires interpretation (tone, faithfulness, relevance, completeness). Do NOT use when the failure mode can be checked with code (regex, schema validation, execution tests). Do NOT use when you need to validate or calibrate the judge — use validate-evaluator instead.
INVOKE THIS SKILL when creating, running, or analyzing Arize experiments. Covers experiment CRUD, exporting runs, comparing results, and evaluation workflows using the ax CLI.
Evaluate a vendor — cost analysis, risk assessment, and recommendation. Use when reviewing a new vendor proposal, deciding whether to renew or replace a contract, comparing two vendors side-by-side, or building a TCO breakdown and negotiation points before procurement sign-off.
Deep research with cross-verification and source tiering. Use when investigating technologies, comparing tools, fact-checking claims, evaluating architectures, or any task requiring verified information. Triggers on "조사해줘", "리서치", "research", "investigate", "fact-check", "비교 분석", "검증해줘".
Tech Stock Earnings Deep Dive Analysis and Multi-Perspective Investment Memo System (v3.0). Covers 16 major analysis modules (A-P), 6 investment philosophy perspectives, institutional-grade evidence standards, anti-bias framework, and actionable decision system. When users mention topics such as tech company earnings analysis, quarterly/annual report interpretation, earnings call, revenue growth analysis, margin changes, guidance, valuation models, DCF, reverse DCF, EV/EBITDA, PEG, Rule of 40, management analysis, competitive landscape, position sizing, whether to buy/sell/add to a tech stock position, how to interpret a company's latest earnings, doing a deep dive, multi-angle valuation, how investment masters view a company, variant view, key forces, kill conditions, ownership structure, executive team, partner ecosystem, macro policy impact, etc., this skill should be used. Even if the user simply asks "help me look at NVDA's latest earnings" or "how did META do this quarter" or "should I keep holding MSFT," this skill should be triggered to provide comprehensive earnings analysis and a multi-perspective investment memo. This skill complements the us-value-investing skill — us-value-investing focuses on long-term value four-dimensional scoring, while this skill focuses on in-depth dissection of the latest earnings, comprehensive judgment across multiple investment philosophies, and actionable position decisions.
Use when validating subjective quality criteria that cannot be deterministically tested — applies LLM-based evaluation with structured rubrics for tone, aesthetics, UX feel, documentation quality, and code readability. Triggers: documentation quality check, error message tone review, UX copy evaluation, code readability assessment, design aesthetic review.
Writes graduate admissions CVs and resumes for master's, PhD, and study abroad applications from OfferClaw. Covers education, research, internships, publications, and awards. Supports PDF export. Use when asked to create, rewrite, polish, or tailor an admissions CV or resume for university application.
Apply structured critical thinking — identifying claims, evidence, reasoning chains, hidden assumptions, and logical fallacies — to evaluate or construct specific written arguments rigorously. Use this skill when the user presents a concrete argument, claim, op-ed, research finding, or piece of reasoning to be analyzed for logical validity or flaws, even if they say 'is this argument valid', 'what logical fallacies are in this', or 'what assumptions am I making in this thesis'. Do NOT use for casual plan review, trip planning, project risk brainstorming, or pre-mortems — 'poke holes in my plan' requests are red-team / risk review, not argument analysis.
Create and run orq.ai experiments — compare configurations against datasets using evaluators, analyze results, and generate prioritized action plans. Use when evaluating LLM agents, deployments, conversations, or RAG pipelines end-to-end. Do NOT use without a dataset and evaluators. Do NOT use for cross-framework comparisons with external agents (use compare-agents).
Generate and curate evaluation datasets — structured generation via dimensions-tuples-NL, quick from description, expansion from existing data, plus dataset maintenance through deduplication, rebalancing, and gap-filling. Use when creating eval data, expanding test coverage, or cleaning datasets. Do NOT use when sufficient real production data exists (use analyze-trace-failures instead). Do NOT use for evaluator creation (use build-evaluator).
Simulate a Nature-style reviewer assessment from the referee perspective rather than an author rebuttal. Use when the user wants a pre-submission review, reviewer report, peer-review style critique, novelty/significance/technical soundness assessment, reviewer-style manuscript evaluation, 审稿人视角评估, 预审稿意见, or Nature reviewer report. Return 3 reviewer reports plus a cross-review synthesis, grounded only in the local Nature reviewer source basis.