name: 17th-pr-handler description: | Use this skill when user wants to analyze GitHub PR feedback or unresolved conversations. Analyzes validity of reviewer comments using GPT-5.3-Codex via GitHub MCP. Auto-triggers on: "PR 피드백", "unresolved", "리뷰 코멘트", "피드백 확인" Appropriate for: PR review handling, feedback validity check, reviewer response preparation. Not appropriate for: creating PRs, merging PRs, writing code directly.
PR Handler
Analyze GitHub PR unresolved feedback and judge validity using GPT-5.3-Codex.
Usage
/pr-feedback 183 → Codex high, PR #183
/pr-feedback 183 deep → Codex xhigh, PR #183
Argument Parsing
Required:
- PR number (numeric)
Keywords (reserved):
deep→ Use xhigh effort instead of high
Parsing Logic
args = split(input)
pr_number = null
effort = "high"
for arg in args:
if arg == "deep":
effort = "xhigh"
elif arg.isdigit():
pr_number = arg
if pr_number is null:
error("PR number required")
Result Mapping
| Input | PR | effort |
|---|---|---|
183 |
183 | high |
183 deep |
183 | xhigh |
deep 183 |
183 | xhigh |
Analysis Output
| Verdict | Meaning | Action |
|---|---|---|
| VALID | Feedback is correct | Should apply |
| INVALID | Feedback is wrong | Should not apply |
| NEEDS_DISCUSSION | Subjective/unclear | Discuss with reviewer |
Implementation
Invoke the 17th-pr-handler subagent:
Task(
description="Analyze PR #{pr_number} feedback ({effort})",
subagent_type="17th-pr-handler",
prompt="""
Analyze unresolved feedback for PR #{pr_number}.
Configuration:
- PR number: {pr_number}
- Effort: {effort} (high or xhigh)
- Project root: {project_root}
""",
run_in_background=true
)
Workflow After Analysis
- Subagent returns analysis report
- Main Agent presents to user:
- Valid feedbacks → "Apply these?"
- Invalid feedbacks → "Decline with reason?"
- Needs discussion → "How to respond?"
- User decides → Main Agent executes
Output
- Report:
.kkachi/{branch_name}/completed/pr-feedback-{pr_number}-{epoch_timestamp}.md - Summary: X valid, Y invalid, Z needs discussion
- Detailed reasoning for each judgment
Examples
| Input | pr_number | effort |
|---|---|---|
183 |
183 | high |
183 deep |
183 | xhigh |
456 deep |
456 | xhigh |
Notes
- Uses GPT-5.3-Codex with GitHub MCP
- Read-only analysis (no code modifications)
- Feedback can be wrong → careful judgment
- Main Agent handles actual code changes with user
- Ensure
.kkachi/is in.gitignore