trellis-break-loop

Analyzes fixed bugs across five dimensions to capture root causes and update prevention specs.

1|Updated Mar 19, 2026
One-click install
npx skills add https://github.com/hejiajiudeeyu/delegated-execution-workspace --skill trellis-break-loop-hejiajiudeeyu
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: trellis-break-loop
Source: https://github.com/hejiajiudeeyu/delegated-execution-workspace/tree/main/.agents/skills/trellis-break-loop
Command: npx skills add https://github.com/hejiajiudeeyu/delegated-execution-workspace --skill trellis-break-loop-hejiajiudeeyu

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Teams often fix a bug and move on, only to hit the same class of bug again later. This Skill breaks the fix-forget-repeat cycle by guiding a structured post-fix analysis that identifies the root cause category, explains why earlier fix attempts failed, and converts the lessons into updated specs and prevention mechanisms. ## Core Features & Use Cases - Five-Dimension Analysis Framework: Classifies the root cause (missing spec, cross-layer contract, change propagation failure, test coverage gap, implicit assumption), reviews failed fix attempts, defines prevention mechanisms, expands to systemic issues, and captures knowledge. - Structured Output Template: Produces a standardized Markdown bug analysis report with prioritized prevention actions (P0, TODO/DONE status). - Spec Knowledge Capture: Directs immediate updates to .trellis/spec/guides/ thinking guides, syncs templates to src/templates/markdown/spec/, and commits the spec changes as the primary deliverable. - Use Case: After fixing a bug where an API returned timestamps in seconds instead of milliseconds, run this analysis to classify it as an implicit assumption bug, add a compile-time type guard, and update the cross-layer thinking guide so the whole team avoids the same mistake. ## Quick Start Analyze the bug we just fixed using the break-loop framework and update the relevant thinking guides in the spec directory.

Frequently Asked Questions about trellis-break-loop

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I do a root cause analysis after fixing a bug?▼

Run a structured post-fix analysis that classifies the bug into a root cause category such as missing spec, cross-layer contract, change propagation failure, test coverage gap, or implicit assumption. Then document prevention mechanisms and update your team's thinking guides so the bug class does not recur.

How to prevent the same bug from happening again?▼

Prevention combines documentation updates, structural changes like type-safe wrappers, stricter compile-time checks, runtime monitoring, broader test coverage, and code review checklists. The analysis output prioritizes these mechanisms with P0 actions and TODO/DONE status tracking.

When should I run a post-fix bug analysis?▼

Run it immediately after debugging is complete, while the context of failed fix attempts and the root cause is still fresh. It is especially valuable when multiple fix attempts failed or when the bug reveals a cross-layer or systemic issue.

What are the common root cause categories for software bugs?▼

The framework defines five categories: missing spec, cross-layer contract mismatch, change propagation failure, test coverage gap, and implicit assumption. Classifying into these categories helps target the right prevention mechanism instead of only fixing the symptom.

Why did my first bug fix not work?▼

Failed fixes typically fall into four patterns: surface fixes that treat symptoms, incomplete scope that misses edge cases, tool limitations like grep missing occurrences, and mental model traps where you keep searching in the wrong layer. The analysis reviews each failed attempt explicitly.