- name
SKILL.md
The skill file stays in the publisher's repository.
Paste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add fy-agent/fyagent --skill trellis-break-loop -a cursor -yPaste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add fy-agent/fyagent --skill trellis-break-loop -a claude-code -yPaste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add fy-agent/fyagent --skill trellis-break-loop -a codex -yPaste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add fy-agent/fyagent --skill trellis-break-loop -a grok -ySend the copied message in a Grok Bot chat. The Bot fetches this SKILL.md from GitHub and adds it to the skills all your Bots share.
Install this skill: https://github.com/fy-agent/fyagent/tree/HEAD/.cursor/skills/trellis-break-loopFrom the publisher
When debug is complete, use this for deep analysis to break the "fix bug -> forget -> repeat" cycle.
Analyze the bug you just fixed from these 5 dimensions:
Which category does this bug belong to?
If you tried multiple fixes before succeeding, analyze each failure:
What mechanisms would prevent this from happening again?
What broader problems does this bug reveal?
Solidify insights into the system:
.trellis/spec/guides/ thinking guides.trellis/spec/ docsPlease output analysis in this format:
## Bug Analysis: [Short Description]
### 1. Root Cause Category
- **Category**: [A/B/C/D/E] - [Category Name]
- **Specific Cause**: [Detailed description]
### 2. Why Fixes Failed (if applicable)
1. [First attempt]: [Why it failed]
2. [Second attempt]: [Why it failed]
...
### 3. Prevention Mechanisms
| Priority | Mechanism | Specific Action | Status |
|----------|-----------|-----------------|--------|
| P0 | ... | ... | TODO/DONE |
### 4. Systematic Expansion
- **Similar Issues**: [List places with similar problems]
- **Design Improvement**: [Architecture-level suggestions]
- **Process Improvement**: [Development process suggestions]
### 5. Knowledge Capture
- [ ] [Documents to update / tickets to create]
The value of debugging is not in fixing the bug, but in making this class of bugs never happen again.
Three levels of insight:
30 minutes of analysis saves 30 hours of future debugging.
When multiple root causes are plausible and evidence is incomplete, update your beliefs proportionally to new evidence rather than clinging to initial assumptions.
Before investigating, state what you believe and why:
Priors must sum to 100%. If you can't assign probabilities, investigate first.
Document what you found — be specific about reliability:
For each hypothesis, ask: How likely is this evidence if this hypothesis were true?
Direction of update matters more than calculation:
Don't gather more of the same. Find evidence that differs strongly between top hypotheses.
If H1 and H3 are close: "What would I see if H1 is true but not if H3 is true?" Then check for that.
Never express binary certainty when evidence is incomplete. Use "most likely", "plausible but unlikely", "worth investigating".
IMPORTANT: After completing the analysis above, you MUST immediately:
Update spec/guides - Don't just list TODOs, actually update the relevant files:
cross-platform-thinking-guide.mdcross-layer-thinking-guide.mdcode-reuse-thinking-guide.mdbackend/*.md or frontend/*.mdSync templates - After updating .trellis/spec/, sync to src/templates/markdown/spec/
Commit the spec updates - This is the primary output, not just the analysis text
The analysis is worthless if it stays in chat. The value is in the updated specs.
Deep bug analysis to break the fix-forget-repeat cycle. Analyzes root cause category, why fixes failed, prevention mechanisms, and captures knowledge into specs. Use after fixing a bug to prevent the
---name: trellis-break-loopdescription: Deep bug analysis to break the fix-forget-repeat cycle. Analyzes root cause category, why fixes failed…---# .cursor/skills/trellis-break-loop/SKILL.mdOverview
Deep bug analysis to break the fix-forget-repeat cycle. Analyzes root cause category, why fixes failed, prevention mechanisms, and captures knowledge into specs. Use after fixing a bug to prevent the same class of bugs.
FAQ
Download .cursor/skills/trellis-break-loop/SKILL.md from the publisher, or copy the path and open the repository. PlugMCP lists the skill and does not host the file.
The publisher keeps it at https://github.com/fy-agent/fyagent.
Claude, Cursor, Codex, and Grok Build can read a SKILL.md you add from the publisher's repository. Grok Bot installs it when you send the skill's GitHub folder link in a chat.