l-yifan
- 11 skills
- 0 followers
- 19 hours ago last updated
- ▌ Deep Wiki · l-yifan bundleAccess AI-generated documentation and insights for GitHub repositories via DeepWiki. This skill should be used when exploring unfamiliar codebases, understanding repository architecture, finding implementation patterns, or asking questions about how a GitHub project works. Supports any public GitHub repository.
- ▌ Humanizer Zh · l-yifan去除文本中的 AI 生成痕迹。适用于编辑或审阅文本，使其听起来更自然、更像人类书写。 基于维基百科的"AI 写作特征"综合指南。检测并修复以下模式：夸大的象征意义、 宣传性语言、以 -ing 结尾的肤浅分析、模糊的归因、破折号过度使用、三段式法则、 AI 词汇、否定式排比、过多的连接性短语。
- ▌ Skill Backup · l-yifan bundleMaintain a personal skills index repository such as L-yifan/skills. Use when the user wants to back up a self-built skill, add an external skill reference, or sync and publish their personal skills index.
- ▌ Work Tickets · l-yifan bundleContinuously execute an approved ticket set from its tracker frontier until complete or human judgement is required.
- ▌
- ▌ Agent Md Improver · l-yifan bundleAudit, simplify, and update repository AGENTS.md and CLAUDE.md files. Use when Codex needs to review, improve, deconflict, or reduce agent instructions; maintain project memory; or decide what belongs in an instruction file versus code, a skill, or a reference. Preserve only current, non-obvious, task-relevant constraints backed by repository evidence.
- ▌ Structural Thinker · l-yifanAnalyze and optimize any system, workflow, plan, design, or problem by identifying its underlying structural patterns and applying proven optimization principles. Use when the user wants to find bottlenecks, streamline a process, restructure an organization, debug a workflow, or asks "why is this slow", "how to improve this", "what's wrong with this structure", "optimize this workflow". Stackable — works alongside any other skill or standalone. Also use when user describes friction, inefficiency, or complexity in any system — technical, organizational, or creative.
- ▌ HTML Artifacts Plus · l-yifan bundleCreate self-contained HTML artifacts when spatial layout, visual hierarchy, interaction, or sharing materially improves a substantial deliverable. Use for comparisons, diagrams, timelines, decks, data views, interactive tools, and source-bound editors that export reviewable patches. Keep short chat replies, code-only or command-only answers, and git-first source documents in Markdown or text.
- ▌ Agent Team Prompting · l-yifan bundleUse when the user wants to write, improve, or evaluate prompts for AI agent teams, teammates, multi-agent collaboration, parallel reviewers, competing hypotheses, complex refactors, coordinated investigations, PR reviews, or tasks that need independent agent sessions to discuss and coordinate.
- ▌ Agent Automation Recommender · l-yifan bundleAnalyze a codebase and recommend AI Agent automations and extensibility options across 6 dimensions for Claude Code, Antigravity (Gemini), Codex, and general AI Agents.
- ▌ Retro Industrial Dashboard Design · l-yifan bundleDefine, document, review, or implement the Retro Industrial Dot-Matrix visual system for dashboard interfaces. Use when the user explicitly invokes this skill; explicitly requests a retro-industrial, dot-matrix display, laboratory console, instrument panel, vintage radio, Glyph, or industrial telemetry terminal direction; supplies references with those traits and asks to reproduce, continue, or extract their design language; asks to continue a DESIGN.md whose name and description identify the retro-industrial-dot-matrix system; or the current project's DESIGN.md explicitly declares that identity. Do not trigger from generic requests for a dashboard, data panel, admin interface, or BI screen alone.