
when-stuck
by a-ariff
๐ Production-ready Claude Code plugin marketplace with 41 components: 21 autonomous agents, 15 power skills, 2 smart hooks, 2 custom commands. Transform Claude Code into an autonomous development powerhouse. One-line install, cross-device sync, comprehensive documentation.
SKILL.md
name: when-stuck description: Dispatch to right technique when you hit a wall version: 1.0.0 author: Ariff when_to_use: When progress stops - identify stuck type and apply matching technique
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 Type | Symptoms | Technique |
|---|---|---|
| Don't understand | Requirements unclear | โ Ask user for clarification |
| Can't find code | No idea where logic lives | โ Semantic search, file patterns |
| Bug won't die | Fix doesn't work | โ Root cause tracing |
| Tests keep failing | Can't get green | โ Defense in depth, fresh look |
| Scope creep | Task keeps growing | โ Scope boundary check |
| Missing context | Need info I don't have | โ Read more files, ask user |
| Wrong approach | This path won't work | โ Brainstorm alternatives |
| Overwhelmed | Too complex | โ Break into smaller pieces |
| Going in circles | Same ground repeatedly | โ Fresh agent via subagent |
Technique Details
Don't Understand โ 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 โ 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 โ 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 โ 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 โ 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 โ 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 โ 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 โ 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 โ 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
โ Brute Force
Trying same thing harder won't work
If it failed twice, it needs a different approach
โ Hoping
"Maybe this time..." โ No
Stop. Diagnose. Change approach.
โ 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 โ try next technique from table
- If nothing works โ ASK USER for help
Integration
Pairs well with:
assumption-checkerโ Often stuck because of wrong assumptionintent-clarifierโ Often stuck because of unclear intentbrainstormingโ For generating alternativesroot-cause-tracingโ For debugging stuck
Score
Total Score
Based on repository quality metrics
SKILL.mdใใกใคใซใๅซใพใใฆใใ
ใฉใคใปใณในใ่จญๅฎใใใฆใใ
100ๆๅญไปฅไธใฎ่ชฌๆใใใ
GitHub Stars 100ไปฅไธ
1ใถๆไปฅๅ ใซๆดๆฐ
10ๅไปฅไธใใฉใผใฏใใใฆใใ
ใชใผใใณIssueใ50ๆชๆบ
ใใญใฐใฉใใณใฐ่จ่ชใ่จญๅฎใใใฆใใ
1ใคไปฅไธใฎใฟใฐใ่จญๅฎใใใฆใใ
Reviews
Reviews coming soon

