发现 Skills

<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT -->

Self-reflection + Self-criticism + learning from corrections. Agent evaluates its own work, catches mistakes, and improves permanently.

Assists with code refactoring by detecting code smells, suggesting improvements, and providing refactoring patterns. Activates when writing/editing code, explicitly requested refactoring, or when code quality issues are detected. Maintains awareness of core principles while providing detailed patterns and examples.

Technical fangirl AI coding companion that gives you flattering encouragement and emotional support while you code. Supports Fangirl Mode (everyday) and Romance Mode (private). Trigger words: "rainbow praise" (over-the-top praise), "praise me", "encourage me", "fangirl mode", "romance mode."

Step-by-step installer for the stitch-kit plugin and Stitch MCP server. Use this when setting up the plugin for the first time, diagnosing connection issues, or helping a new user get Stitch running in Claude Code or Codex CLI.

Use when the user asks how code works, wants to understand architecture, trace execution flows, or explore unfamiliar parts of the codebase. Examples: “How does X work?”, “What calls this function?”, “Show me the auth flow”

Use when creating ASCII art to guide your artistic approach

Guidelines for creating technical documentation, READMEs, API specifications, technical books, and articles. [Most important] Handling of measured data and verification results ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ Rules that must be followed: 1. Do not present data you did not actually measure or verify as "measured". 2. Do not record fictitious numbers as concrete values. 3. Do not use expressions that imply you validated something (e.g., "when we did ~", "as a result of verification"). 4. Do not include concrete numbers (memory usage, processing time, etc.) in Before/After comparisons. 5. Only cite official documentation, papers, or other reliable sources. Readers will assume the author actually verified the results. Expressions that make it seem like verification was performed when it was not betray readers' trust.

Design system reference for design md resend.

AI-powered scientific writing tool. Generate publication-ready papers, grant proposals, posters, and more with real-time research and verified citations.

Design a lesson that embeds PERMA wellbeing elements alongside academic learning objectives. Use when planning lessons that intentionally support both content mastery and student flourishing.

Trend and technical analysis. Use this skill ONLY when the user's query is exclusively about technical indicators or trend analysis for one coin with no other analysis dimensions. Trigger phrases: technical analysis, K-line, RSI, MACD, trend, support, resistance. If the query ALSO mentions fundamentals, risk, news, sentiment, or any other analysis dimension, use gate-info-research instead — it handles multi-dimension queries in a single unified report.

Automatically extract reusable patterns from Claude Code sessions and save them as learned skills for future use.

Installation step patterns for Gentleman.Dots TUI installer. Trigger: When editing installer.go, adding installation steps, or modifying the installation flow.

System detection and command execution patterns for Gentleman.Dots. Trigger: When editing files in installer/internal/system/, adding OS support, or modifying command execution.

React 19 patterns with React Compiler. Trigger: When writing React components - no useMemo/useCallback needed.

Process Telegram messages via GramJS MTProto client. Read messages, generate AI drafts, save drafts, and create intro groups. Use when handling Telegram conversations or facilitating introductions.

Create a git branch following Sentry naming conventions. Use when asked to "create a branch", "new branch", "start a branch", "make a branch", "switch to a new branch", or when starting new work on the default branch.

Implements progression from Vector RAG → GraphRAG → Temporal Knowledge Graphs. Use when designing persistent memory architectures for AI agent systems.

Triage and resolve Fedora issues with dnf, systemd, and SELinux-aware guidance.

Expert guidance for creating, configuring, and using Claude Code hooks. Use when working with hooks, setting up event listeners, validating commands, automating workflows, adding notifications, or understanding hook types (PreToolUse, PostToolUse, Stop, SessionStart, UserPromptSubmit, etc).

Create Model Context Protocol (MCP) servers that expose tools, resources, and prompts to Claude. Use when building custom integrations, APIs, data sources, or any server that Claude should interact with via the MCP protocol. Supports both TypeScript and Python implementations.

Create structured build plans from feature requests or Flow IDs. Use when planning features or designing implementation. Triggers on /flow-next:plan with text descriptions or Flow IDs (fn-1, fn-1.2).

Local install of flowctl CLI and CLAUDE.md/AGENTS.md instructions. Use when user runs /flow-next:setup.