Agent skill
dev-buddy-bug-fix
Bug fix pipeline — chains root cause analysis, requirements, planning, plan review, implementation, and code review. Uses single plan file and TaskManagement for progress tracking.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/dev-buddy-bug-fix
SKILL.md
Bug Fix Pipeline Orchestrator
Run the full bug fix pipeline end-to-end. Chains individual stage skills in the order defined by bugfix_pipeline in ~/.vcp/dev-buddy.json. All phases append to a single plan file.
Step 1: Initialize
- Load the pipeline config:
bun -e "
import { loadDevBuddyConfig, expandPipelineToEntries } from '${CLAUDE_PLUGIN_ROOT}/scripts/pipeline-config.ts';
const config = loadDevBuddyConfig();
const stages = expandPipelineToEntries(config, 'bugfix_pipeline');
console.log(JSON.stringify({
pipeline: config.bugfix_pipeline,
stages,
max_iterations: config.max_iterations
}));
"
- Display the pipeline stages to the user:
Bug Fix Pipeline: rca → requirements → planning → plan-review → implementation → code-review
Executors: {count} total across {stage_count} stages
- Initialize plan file — the plan file must exist before any stage appends to it. Create it now via the Write tool or by entering plan mode. Write the header:
# Plan: Bug Fix — {user's bug description (short title)}
**Status:** rca
**Pipeline:** bug-fix
**Created:** {date}
---
- Create pipeline phase tasks with TaskManagement:
T_rca = TaskCreate(subject='Phase: Root Cause Analysis', description='Diagnose the bug — find root cause with evidence', activeForm='Diagnosing...')
T_req = TaskCreate(subject='Phase: Requirements + TDD Test Plan', description='Define fix requirements, create TDD tests, identify risks', activeForm='Gathering requirements...')
TaskUpdate(T_req, addBlockedBy: [T_rca])
T_plan = TaskCreate(subject='Phase: Implementation Planning', description='Create granular fix steps mapped to ACs and tests', activeForm='Planning...')
TaskUpdate(T_plan, addBlockedBy: [T_req])
T_review_plan = TaskCreate(subject='Phase: Plan Review', description='Review fix plan for coverage and granularity', activeForm='Reviewing plan...')
TaskUpdate(T_review_plan, addBlockedBy: [T_plan])
T_impl = TaskCreate(subject='Phase: Implementation', description='Implement fix with TDD loop', activeForm='Implementing...')
TaskUpdate(T_impl, addBlockedBy: [T_review_plan])
T_review_code = TaskCreate(subject='Phase: Code Review', description='Review fix against ACs with evidence', activeForm='Reviewing code...')
TaskUpdate(T_review_code, addBlockedBy: [T_impl])
Step 2: Execute Stages in Order
For each stage type in bugfix_pipeline:
Stage-to-Skill Mapping
| Stage Type | Skill | Plan File Section Produced |
|---|---|---|
rca |
Skill(skill: "dev-buddy-rca") |
RCA Diagnosis |
requirements |
Skill(skill: "dev-buddy-requirements") |
Requirements + TDD Test Plan + Risk Registry |
planning |
Skill(skill: "dev-buddy-plan") |
Implementation Steps |
plan-review |
Skill(skill: "dev-buddy-review", args: "--plan") |
Plan Review Record |
implementation |
Skill(skill: "dev-buddy-implement") |
Step status updates |
code-review |
Skill(skill: "dev-buddy-review", args: "--code") |
Code Review Record + Sign-off |
Execution Flow
Same as feature pipeline:
TaskUpdate(phase_task_id, status: 'in_progress')- Announce each stage
- Invoke the corresponding skill
- Verify expected plan file section exists
TaskUpdate(phase_task_id, status: 'completed')- If review returns
rejected→ STOP, mark blocked, report
Step 3: Resume Support
Same as feature pipeline:
TaskList()to find completed vs pending phases- Read plan file to check which sections exist
- Skip completed phases, continue from next pending
Step 4: Report
After all stages complete:
- Present per-stage status summary
TaskList()for final task statuses- If all passed → "Bug fix pipeline complete!"
- If any rejected → report which stage and remaining findings
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?