跳到正文
cccskills
免费在 GitHub 公开

when-stuck

Dispatch to right technique when you hit a wall

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(1)

  • SKILL.md3.7 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

When Stuck

Recognition

You're stuck when:

  • Same approach tried multiple times
  • Context window filling with failed attempts
  • No clear next step
  • Feeling "lost" or "frustrated"

The Dispatch Table

Stuck TypeSymptomsTechnique
Don't understandRequirements unclear→ Ask user for clarification
Can't find codeNo idea where logic lives→ Semantic search, file patterns
Bug won't dieFix doesn't work→ Root cause tracing
Tests keep failingCan't get green→ Defense in depth, fresh look
Scope creepTask keeps growing→ Scope boundary check
Missing contextNeed info I don't have→ Read more files, ask user
Wrong approachThis path won't work→ Brainstorm alternatives
OverwhelmedToo complex→ Break into smaller pieces
Going in circlesSame ground repeatedly→ Fresh agent via subagent

Technique Details

Don't Understand → Clarify

STOP trying to guess
ASK: "I'm unclear on [specific thing]. Could you clarify [specific question]?"
WAIT for response before proceeding

Can't Find Code → Search Strategies

1. Semantic search with concept terms
2. Grep for unique strings
3. File pattern matching
4. Read likely files
5. List directories to discover structure

Bug Won't Die → Root Cause Trace

1. Document exact symptom
2. Trace backward: where does bad value come from?
3. Keep tracing until you find ORIGIN
4. Fix at origin, not symptoms

Tests Keep Failing → Fresh Eyes

1. Stop. Step back.
2. Re-read test expectation
3. Re-read actual behavior
4. Check: is test right or is code right?
5. Check: is environment consistent?

Scope Creep → Boundary Check

1. Re-read original request
2. List what you've done vs. what was asked
3. Identify scope drift
4. Either: refocus OR ask user if expansion wanted

Missing Context → Gather More

1. What specific info do you need?
2. Where might it be? (files, user knowledge, docs)
3. Ask/search for that specific info
4. Don't proceed without it

Wrong Approach → Brainstorm

1. What other approaches exist?
2. List 3-4 alternatives
3. Evaluate each briefly
4. Pick most promising, try it
5. If that fails, try next

Overwhelmed → Decompose

1. What's the smallest possible piece?
2. Do JUST that piece
3. Verify it works
4. What's next smallest piece?
5. Repeat until done

Going in Circles → Fresh Agent

Signal: Same ground covered 3+ times
Action: Use subagent for specific subtask
Pass: Clear scope, success criteria
Return: Just the result, not the journey

Anti-Patterns

❌ Brute Force

Trying same thing harder won't work
If it failed twice, it needs a different approach

❌ Hoping

"Maybe this time..." → No
Stop. Diagnose. Change approach.

❌ Hiding

Not admitting you're stuck wastes time
Say: "I'm stuck on X. Here's what I've tried..."

Success Metric

After applying technique:

  • Clear next step identified
  • Progress resuming
  • If still stuck → try next technique from table
  • If nothing works → ASK USER for help

Integration

Pairs well with:

  • assumption-checker → Often stuck because of wrong assumption
  • intent-clarifier → Often stuck because of unclear intent
  • brainstorming → For generating alternatives
  • root-cause-tracing → For debugging stuck

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Complete methodology for preventing AI hallucinations. Use when accuracy is critical and you need Claude to verify before claiming, cite before asserting, and admit uncertainty instead of guessing.

中文简介正在准备中。当前显示原文说明。

a-ariff/ariff-claude-plugins142026年3月29日 更新

Transform rough ideas into solid designs through structured questioning

中文简介正在准备中。当前显示原文说明。

a-ariff/ariff-claude-plugins142026年3月29日 更新

Canvas API Connection Skill

中文简介正在准备中。当前显示原文说明。

a-ariff/ariff-claude-plugins142026年3月29日 更新

Forces every code-related claim to include file:line citations. No citation means the claim must be verified or removed. Use when building documentation, writing code reviews, or any output that others will rely on.

中文简介正在准备中。当前显示原文说明。

a-ariff/ariff-claude-plugins142026年3月29日 更新

Assign confidence scores (0-100) to every claim in a response. Helps users understand which parts are verified facts and which are educated guesses. Use when the user needs to know how much to trust each part of the answer.

中文简介正在准备中。当前显示原文说明。

a-ariff/ariff-claude-plugins142026年3月29日 更新

Forces Claude to extract exact quotes from files before making claims about them. Prevents hallucinations by grounding every statement in actual text from the codebase. Use when working with large files or unfamiliar code.

中文简介正在准备中。当前显示原文说明。

a-ariff/ariff-claude-plugins142026年3月29日 更新

查看 a-ariff 的全部技能

报告此技能的问题