LLM-based zero-shot and few-shot classification for flexible intent detection
Skills(SKILL.md)は、AIエージェント(Claude Code、Cursor、Codexなど)に特定の能力を追加するための設定ファイルです。
詳しく見る →LLM-based zero-shot and few-shot classification for flexible intent detection
Agents are autonomous subprocesses that handle complex, multi-step tasks independently. Understanding agent structure, triggering conditions, and system prompt design enables creating powerful autonom
The `dev-intelligence-orchestrator` skill provides intelligent development tool orchestration with **self-improving learning capabilities** through mcp-prompts integration.
Continuous learning — hooks observe failures and prompt reflection, sibling synergy deepens analysis with history and tool discovery
Show how many context window tokens each skill consumes. Use when the user asks about token cost, context budget, skill size, or wants to know which skills waste the most context space.
Plan, orchestrate, and validate deep research for nonfiction books. This skill
robius-widget-patterns
Produce a 1:1 Operating System Pack (agendas, coaching prompts, career conversation plan). See also: running-effective-meetings (group meetings).
Activate autonomous Ralph Wiggum loop mode for iterative task completion. Use when you have a well-defined task with clear completion criteria that benefits from persistent, autonomous execution.
- 因本 skill 设计缺陷导致的 bug,先用 `bensz-collect-bugs` 规范记录到 `~/.bensz-skills/bugs/`,不要直接修改用户本地已安装的 skill 源码;若有 workaround,先记 bug,再继续完成任务。
实现离散点Hough变换算法,输入包含浮点数的坐标点,输出检测到的直线斜率和截距,不使用MATLAB自带函数
Self-help mental wellness coach — daily journaling prompts + gratitude practice + emotional regulation tools + thought reframing สำหรับคนทั่วไป (ไม่ใช่ clinical therapy)
Launching Codex and Claude agents as bash commands with prompts via stdin
task = $ARGUMENTS
AI工程师角色。关键词:AI/LLM/智能体/Prompt/上下文工程/多智能体/工作流/RAG/Function Call/效果评测。激活后设计提示词、构建智能体调用链、评测输出质量。
Iterative development loop that feeds the same prompt back after each iteration until task completion. Use /bluera-base:milhouse-loop to start.
このスキルでは、Task toolを使用してgeneral-purpose subagentにプロンプトを渡す形式で処理を行う。
>-
A skill for automating AI CLI tool interactions by handling common prompts and managing continuous operation.
Gather phase context through adaptive questioning before planning. Use --auto to skip interactive questions (Claude picks recommended defaults). Use --chain for interactive disc...
Manage asynchronous jobs: submit, poll, check status, cancel, and batch operations.
Act as a **Senior AI Agent Developer** and **Prompt Engineer**.
Create a simple carry-over note with next prompt and files needed for session continuation
Visual content generation with Excalidraw hand-drawn aesthetic - technical diagrams, comics, editorial illustrations
../../prompt/instructions/ecc-common-agents.md
This is the highest-density area of unknown unknowns because AI agent systems are new enough that most developers have never encountered these failure modes.
Gather phase context through adaptive questioning before planning. Use --auto to skip interactive questions (Claude picks recommended defaults).
architect