Skill Claude CodeCodex
Use when the user has changed a prompt (system prompt, RAG template, agent instruction, etc.) and wants to know whether the candidate is better or worse than the baseline. Also use when the user mentions prompt A/B testing, prompt comparison, prompt optimization validation, "did my prompt change help," or prompt…
Skill Claude CodeCodex
Use when the user wants to test their LLM/agent application for safety and security vulnerabilities — jailbreaks, prompt injection, PII extraction, harmful content generation, or evaluator gaming. Also use when the user mentions security testing, adversarial testing, red teaming, safety evaluation, ASR (Attack Success…
Skill Claude CodeCodex
Use when the user has nothing — no traces, no labels, no eval set — and needs to build a v0 evaluation from scratch. Also use when the user says "I need to start evaluating my app but don't know where to begin," "I want to set up eval for a new product," or has just identified failure modes and needs to turn them into…
Skill Claude CodeCodex
Discover and recommend combinations of agent skills to complete complex, multi-faceted tasks. Provides two recommendation strategies — Maximum Quality (best skill per subtask) and Minimum Dependencies (fewest installs). Use this skill whenever the user wants to find skills, asks "how do I do X", "find a skill for X"…
Skill Claude CodeCodex
Generate text, images, video, speech, and music via the MiniMax AI platform. Covers text generation (MiniMax-M3 model), image generation (image-01), video generation (Hailuo-2.3), speech synthesis (speech-2.8-hd, 300+ voices), music generation (music-2.6 with lyrics, cover, and instrumental), and web search. Use when…
Skill Claude CodeCodex
Build custom LLM evaluation pipelines using the OpenJudge framework. Covers selecting and configuring graders (LLM-based, function-based, agentic), running batch evaluations with GradingRunner, combining scores with aggregators, applying evaluation strategies (voting, average), auto-generating graders from data, and…
Skill Claude CodeCodex
Review academic papers for correctness, quality, and novelty using OpenJudge's multi-stage pipeline. Supports PDF files and LaTeX source packages (.tar.gz/.zip). Covers 10 disciplines: cs, medicine, physics, chemistry, biology, economics, psychology, environmentalscience, mathematics, socialsciences. Use when the user…
Skill Claude CodeCodex
Benchmark LLM reference recommendation capabilities by verifying every cited paper against Crossref, PubMed, arXiv, and DBLP. Measures hallucination rate, per-field accuracy (title/author/year/DOI), discipline breakdown, and year constraint compliance. Supports tool-augmented (ReAct + web search) mode. Use when the…
Skill Claude CodeCodex
Build RL reward signals using the OpenJudge framework. Covers choosing between pointwise and pairwise reward strategies based on RL algorithm, task type, and cost; aggregating multi-dimensional pointwise scores into a scalar reward; pairwise tournament reward for GRPO on subjective tasks (net win rate across group…
agentscope-ai/agentscope-spark-design
Skill Claude CodeCodex
Generates English pull request titles and bodies by comparing the current branch with main. Use when the user asks to draft PR content, summarize branch changes, or produce a PR title/body from git diff.
agentscope-ai/agentscope-spark-design
Skill Claude CodeCodex
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance…
agentscope-ai/agentscope-spark-design
Cursor rule Cursor
A set of Cursor editor rules covering AI instructions, Git commit rules, and rules for AI conversations. Cursor is a code editor with built-in AI assistance.
agentscope-ai/agentscope-spark-design
Cursor rule Cursor
A project rule showing a tree structure with node names and IDs. The supplied text does not explain a broader purpose.
agentscope-ai/agentscope-spark-design
Cursor rule Cursor
A project rule containing a short example of creating React components. The supplied text does not explain a broader purpose.
Skill Claude CodeCodex
This guide covers the design philosophy, core concepts, and practical usage of the AgentScope framework. Use this skill whenever the user wants to do anything with the AgentScope (Python) library. This includes building agent applications using AgentScope, answering questions about AgentScope, looking for guidance on…
Skill Claude CodeCodex
Guidelines and workflows for the agent to maintain persistent memory using native file tools (readfile, writefile, editfile) and standard OS commands for searching.
Skill Claude CodeCodex
A tool for calculating a change threshold from the natural variation in historical time-series data. A threshold is the boundary above which a change is treated as notable.
Skill Claude CodeCodex
A tool for finding unusually large rises or falls in a time-based series, such as daily visitor counts. It compares values across days or weeks against chosen limits.
Skill Claude CodeCodex
A business-analysis skill that measures how much each group or dimension value contributed to a metric's change. It supports totals that can be added directly, rates such as conversion rate, and weighted averages such as average order value.
Skill Claude CodeCodex
A business-analysis skill that links business events in reports, plans, release notes, or conversations with an unusual metric change. It produces and ranks possible causes supported by the available evidence.
Skill Claude CodeCodex
A business-analysis skill that places similar business objects—such as users, products, or shops—into groups. It can use a two-by-two matrix based on two measures or clustering based on several features.
Skill Claude CodeCodex
A business-analysis skill for quantitatively comparing metrics across times, groups, regions, channels, versions, targets, or competitors. It calculates absolute or percentage differences and can apply statistical tests when there are multiple samples.
Skill Claude CodeCodex
A tool for calculating the share of users who move from a starting action to a completed action. This share is called a conversion rate.
Skill Claude CodeCodex
A tool for turning business data analysis into an interactive HTML dashboard. The result is a single HTML file that can be opened offline and lets readers filter the data.