286 skills · sorted by relevance
Improve research through repeated Gemini reviews, code changes, experiments, and analysis. The workflow records full feedback and actions, then stops when both the score and readiness criteria are met or the round limit is reached.
Improve an existing LaTeX paper through two rounds of Gemini review, targeted edits, and PDF rebuilding. Check whether claims match the evidence, resolve notation and presentation issues, and retain review logs and PDF versions.
Create academic architecture diagrams and method illustrations with Gemini image generation. The workflow refines layout and visual style, then uses Claude to inspect arrows, labels, and readability and guide further revisions.
Explore hardware and electronic design configurations by repeatedly running programs, measuring results, and adjusting parameters. Track constraints and every trial, then report the best configuration found within the time and iteration limits.
Improve a compiled paper through two rounds of external model review, source edits, and PDF rebuilding. Check claims against evidence, resolve inconsistencies, and refine figures and layout, with optional checkpoints and restrictions on which edits are allowed.
Guides iterative improvement of AI agent prompts, skills, and memory using A-Evolve. It explains how to evaluate agents against benchmark tasks, apply changes, validate results, and track or roll back revisions with Git.
Build a website one page at a time with Stitch. Each round reads a task file, generates and integrates a page, updates the site plan, and leaves instructions for the next round.
Check generated PDFs against a page limit or target count, then adjust layout and regenerate as needed. Provides a repeatable workflow for tuning margins, images, tables, and text while respecting readability limits.
Inspect unfamiliar Excel workbooks before building extraction scripts. Map sheets, headers, columns, and row patterns, then use those findings to distinguish actual records from summaries and blank rows when extracting data.
Runs repeated reviews and fixes on a Claude Code skill until no critical or major findings remain. Tracks findings across rounds, checks change boundaries, and stops for a design decision when fixes stop making progress.
Co-write proposals, technical specifications, and decision documents through context gathering, section-by-section drafting, and revision. A fresh AI reader then tests the document to reveal unclear explanations, missing context, and contradictions before it is shared.
Review a branch's commits, combine adjacent changes that belong together, and improve commit messages. A rebuilt history is prepared separately and replaces the original branch only after the user reviews and confirms the proposed changes.
Structure delegated agent tasks with clear goals, success criteria, and a three-attempt limit. Provides handoff templates and coordinator checks, plus rules for escalating unresolved work and turning research findings into concrete follow-up actions.
Design studies that combine quantitative data, such as surveys, with qualitative evidence, such as interviews. It recommends a suitable design and outlines study phases, participant selection, timing, and ways to combine findings into an integrated interpretation.
Co-write proposals, technical specifications, and decision documents through context gathering, section-by-section drafting, and revision. A fresh AI reader then tests the document to reveal unclear explanations, missing context, and contradictions before it is shared.
Build and test scoring criteria for selecting relevant research papers. Refine the rules against your judgments, screen large sets of abstracts, and reassess saved papers when criteria change, with records of scores and revisions.
Turn a detailed outline into a philosophy or interdisciplinary manuscript. Draft chapters with repeated quality reviews, check terminology and arguments across sections, and prepare the manuscript, evaluation reports, abstract, and metadata for submission.
Turn written descriptions into scientific diagrams, including neural network architectures, biological pathways, and research flowcharts. Nano Banana 2 generates images, while Gemini 3.1 Pro Preview reviews them and guides regeneration when needed.
Drive repeated debugging cycles with the required diagnose skill: establish evidence for a cause, choose one focused fix, and rerun the original validation. Reassess after each change until no credible fix remains or further progress requires user input.
Maintain and patch existing Lark/Feishu documents while preserving comments, highlights, citations, and newer remote edits. Use for iterative document updates, local-mirror sync, or durable project ownership; LoopX integration is optional.
The English summary is being prepared. Showing the original description.
Improve existing code through up to two optimization rounds, measuring execution time and memory use against a baseline. Verify that results remain correct, save the optimized code, and document changes, measured gains, and trade-offs in a report.
工作流组合：当一个任务明显需要多件思想武器接力时，提供四种标准组合模式（新项目启动、复杂问题攻坚、方案迭代优化、阶段复盘），定义调用顺序、每步交接物和终止条件。触发信号包括从零启动、疑难攻坚、迭代优化、阶段复盘；单一 skill 就够用时不触发。 English: Workflow patterns. When a task clearly needs several skills in sequence, pick one of four standard patterns (project kickoff, hard-problem assault, iterative improvement, stage retrospective) that fix the order, the handoff artifact between steps, and the stop condition. Skip when a single skill suffices.
The English summary is being prepared. Showing the original description.
Self-improving browser automation via the auto-research loop. Iteratively runs a browsing task, reads the trace, and improves the navigation skill (strategy.md) until it reliably passes. Supports parallel runs across multiple tasks using sub-agents. Use when you want to build or improve browser automation skills for specific website tasks.
The English summary is being prepared. Showing the original description.
Create publication-quality scientific diagrams using Nano Banana Pro AI with smart iterative refinement. Uses Gemini 3 Pro for quality review. Only regenerates if quality is below threshold for your document type. Specialized in neural network architectures, system diagrams, flowcharts, biological pathways, and complex scientific visualizations.
The English summary is being prepared. Showing the original description.