用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/PracticalSwan/agent-skills --skill when-stuck命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
Official NVIDIA-authored guidance for NVIDIA cuDF GPU DataFrames, pandas acceleration, dask-cuDF, ETL, joins, groupby, CSV/Parquet I/O, nullable semantics, and multi-GPU DataFrame workloads.
Audit and improve web accessibility following WCAG 2.2 guidelines. Use when asked to "improve accessibility", "a11y audit", "WCAG compliance", "screen reader support", "keyboard navigation", or "make accessible".
Map tasks to specialist agents. Use when choosing which agent for a job, comparing agent capabilities, or routing to React/Next.js/Playwright/docs/code-quality experts. Keywords: which agent, best agent for this, delegate to expert, agent capability mapping.
基于 SOC 职业分类
正在显示 SKILL.md
| name | when-stuck |
| version | 2.0 |
| last_updated | 2026-08-29T00:00:00.000Z |
| tags | ["when","stuck"] |
| description | Dispatch to the right problem-solving technique based on how you're stuck |
Different stuck-types need different techniques. This skill helps you quickly identify which problem-solving skill to use.
Core principle: Match stuck-symptom to technique.
digraph stuck_dispatch {
rankdir=TB;
node [shape=box, style=rounded];
stuck [label="You're Stuck", shape=ellipse, style=filled, fillcolor=lightblue];
complexity [label="Same thing implemented 5+ ways?\nGrowing special cases?\nExcessive if/else?"];
innovation [label="Can't find fitting approach?\nConventional solutions inadequate?\nNeed breakthrough?"];
patterns [label="Same issue in different places?\nFeels familiar across domains?\nReinventing wheels?"];
assumptions [label="Solution feels forced?\n'This must be done this way'?\nStuck on assumptions?"];
scale [label="Will this work at production?\nEdge cases unclear?\nUnsure of limits?"];
bugs [label="Code behaving wrong?\nTest failing?\nUnexpected output?"];
stuck -> complexity;
stuck -> innovation;
stuck -> patterns;
stuck -> assumptions;
stuck -> scale;
stuck -> bugs;
complexity -> simp [label="yes"];
innovation -> collision [label="yes"];
patterns -> meta [label="yes"];
assumptions -> invert [label="yes"];
scale -> scale_skill [label="yes"];
bugs -> debug [label="yes"];
simp [label="skills/problem-solving/\nsimplification-cascades", shape=box, style="rounded,filled", fillcolor=lightgreen];
collision [label="skills/problem-solving/\ncollision-zone-thinking", shape=box, style="rounded,filled", fillcolor=lightgreen];
meta [label="skills/problem-solving/\nmeta-pattern-recognition", shape=box, style="rounded,filled", fillcolor=lightgreen];
invert [label="skills/problem-solving/\ninversion-exercise", shape=box, style="rounded,filled", fillcolor=lightgreen];
scale_skill [label="skills/problem-solving/\nscale-game", shape=box, style="rounded,filled", fillcolor=lightgreen];
debug [label="skills/debugging/\nsystematic-debugging", shape=box, style="rounded,filled", fillcolor=lightyellow];
}
| How You're Stuck | Use This Skill |
|---|---|
| Complexity spiraling - Same thing 5+ ways, growing special cases | simplification-cascades |
| Need innovation - Conventional solutions inadequate, can't find fitting approach | collision-zone-thinking |
| Recurring patterns - Same issue different places, reinventing wheels | meta-pattern-recognition |
| Forced by assumptions - "Must be done this way", can't question premise | inversion-exercise |
| Scale uncertainty - Will it work in production? Edge cases unclear? | scale-game |
| Code broken - Wrong behavior, test failing, unexpected output | systematic-debugging |
| Multiple independent problems - Can parallelize investigation | dispatching-parallel-agents |
| Root cause unknown - Symptom clear, cause hidden | root-cause-tracing |
Some problems need multiple techniques:
This skill is written to stay usable across GitHub Copilot, Claude Code, and Codex.
$CODEX_HOME/skills/when-stuck and restart Codex after major changes.Preferred MCP Server: None required
when-stuck outside its documented task boundary.Before claiming the when-stuck workflow succeeded: