research-merge
Processes research branches from Claude Code Web sessions - merges content, moves docs to docs/research/, and creates GitHub issues. Use when /popkit:next detects research branches or when manually processing research from mobile sessions. Do NOT use for regular feature branches - only for branches matching claude/research-* or containing research documentation.
What this skill does
# Research Branch Merge
## Overview
Handles the complete workflow for processing research branches created during Claude Code Web sessions:
1. Detect research branches
2. Preview content for user approval
3. Squash-merge to main branch
4. Move docs to standardized location
5. Create GitHub issue from findings
6. Clean up remote branch
**Trigger:** Called by `pop-next-action` skill when research branches detected, or directly via `/popkit:research merge`.
## User Interaction Pattern
**ALWAYS use AskUserQuestion** for merge decisions:
```
Use AskUserQuestion tool with:
- question: "Found research branch: [topic]. How should we process it?"
- header: "Research"
- options:
- label: "Merge and create issue"
description: "Squash-merge, move docs, create GitHub issue, delete branch"
- label: "Merge only"
description: "Squash-merge content without creating issue"
- label: "Skip for now"
description: "Leave branch for later processing"
- label: "Delete branch"
description: "Discard research (cannot be undone)"
- multiSelect: false
```
## Processing Workflow
### Step 1: Detect Research Branches
Use the `research_branch_detector.py` utility:
```python
import sys
# No longer needed - install popkit-shared instead
from research_branch_detector import (
fetch_remotes,
get_research_branches,
format_branch_table,
get_branch_content_preview,
parse_research_doc,
generate_issue_body
)
# Fetch and detect
fetch_remotes()
branches = get_research_branches()
if not branches:
print("No research branches detected.")
return
# Show table
print("## Research Branches Detected\n")
print(format_branch_table(branches))
```
### Step 2: Preview Content
For each branch, show a preview before prompting:
```python
for branch in branches:
print(f"\n### {branch.short_name}")
print(f"**Topic:** {branch.topic}")
print(f"**Created:** {branch.created_ago}")
print(f"**Commits:** {branch.commit_count} ahead of master")
if branch.doc_paths:
print(f"\n**Documentation:**")
for path in branch.doc_paths:
print(f"- `{path}`")
# Show summary preview
previews = get_branch_content_preview(branch, max_lines=20)
for path, content in previews.items():
parsed = parse_research_doc(content)
if parsed.get("summary"):
print(f"\n**Summary:** {parsed['summary'][:200]}...")
```
### Step 3: User Decision
Use AskUserQuestion for each branch:
```
Use AskUserQuestion tool with:
- question: f"Process '{branch.topic}' research? ({branch.commit_count} commits, {len(branch.doc_paths)} docs)"
- header: "Merge"
- options:
- label: "Merge + Issue"
description: "Full processing: merge, organize docs, create issue"
- label: "Merge Only"
description: "Just merge the content"
- label: "Skip"
description: "Process later"
- label: "Delete"
description: "Discard this research"
- multiSelect: false
```
### Step 4: Execute Merge
Based on user choice:
#### Option A: Merge + Issue (Full Processing)
```bash
# 1. Ensure clean working directory
git status --porcelain
# If dirty, prompt user to commit or stash first
# 2. Squash merge the research branch
git merge --squash origin/claude/research-[topic]-[session-id]
# 3. Organize docs (if not already in docs/research/)
mkdir -p docs/research
# Move any root-level research docs
git mv RESEARCH*.md docs/research/ 2>/dev/null || true
git mv *_RESEARCH.md docs/research/ 2>/dev/null || true
# 4. Commit with standard message
git commit -m "docs(research): merge [topic] research from web session
Merged from: [branch-name]
Created: [created-ago]
๐ค Generated with [Claude Code](https://claude.ai/claude-code)
Co-Authored-By: Claude Opus 4.5 <[email protected]>"
# 5. Create GitHub issue
gh issue create --title "[Research] [Topic Title]" --body "[generated-body]" --label "research,documentation"
# 6. Delete remote branch
git push origin --delete claude/research-[topic]-[session-id]
```
#### Option B: Merge Only
```bash
git merge --squash origin/claude/research-[topic]-[session-id]
git commit -m "docs(research): merge [topic] research
Merged from: [branch-name]
๐ค Generated with [Claude Code](https://claude.ai/claude-code)
Co-Authored-By: Claude Opus 4.5 <[email protected]>"
# Optionally delete branch
# Ask: "Delete the remote branch?"
```
#### Option C: Skip
No action - branch remains for future processing.
#### Option D: Delete
```bash
# Confirm deletion
# "Are you sure? This research will be permanently lost."
git push origin --delete claude/research-[topic]-[session-id]
```
### Step 5: Summary Report
After processing all branches:
```markdown
## Research Processing Complete
| Branch | Action | Result |
|--------|--------|--------|
| research-claude-code | Merged + Issue | Issue #182 created |
| research-audio-hooks | Skipped | - |
| research-old-test | Deleted | - |
**Next Steps:**
- Review created issues
- Run `/popkit:next` to see updated recommendations
```
## Issue Generation
### Title Format
```
[Research] {Topic Title}
```
Examples:
- `[Research] Claude Code v2.0.65 Features Integration`
- `[Research] Audio Feedback Hooks Architecture`
### Body Format
```markdown
## Summary
{Executive summary from research doc}
## Source
- **Branch:** `{full_branch_name}`
- **Created:** {created_ago}
- **Files:** {file_count} changed
## Documentation
- `docs/research/{doc_name}.md`
## Implementation Tasks
- [ ] {Task 1 from research}
- [ ] {Task 2 from research}
---
*Auto-generated from research branch by PopKit*
```
### Labels
Automatically apply:
- `research` - Marks as research output
- `documentation` - Contains documentation
Optionally detect from content:
- `enhancement` - If implementation tasks found
- `P1-high` / `P2-medium` / `P3-low` - From priority metadata
## Error Handling
| Situation | Response |
|-----------|----------|
| Dirty working directory | Prompt to commit/stash first |
| Merge conflicts | Show conflicts, offer manual resolution |
| gh CLI unavailable | Skip issue creation, note in output |
| No doc files | Merge anyway, create minimal issue |
| Branch already merged | Skip, note in output |
## Research Document Standard
For best results, research docs should follow this format:
```markdown
# Research: [Topic Name]
**Research Date:** YYYY-MM-DD
**Status:** Research Document
**Priority:** P1-high | P2-medium | P3-low
## Executive Summary
[Brief summary of findings - becomes issue body]
## Key Findings
[Main research content]
## Implementation Tasks
- [ ] Task 1 [becomes checklist in issue]
- [ ] Task 2
- [ ] Task 3
## References
[Links and sources]
```
## Integration Points
| Component | Role |
|-----------|------|
| `pop-next-action` | Calls this skill when branches detected |
| `research_branch_detector.py` | Core detection logic |
| `/popkit:next` | Entry point for auto-detection |
| `/popkit:routine morning` | Can include in morning routine |
| GitHub Issues | Output destination for findings |
## Related
- `/popkit:next` - Primary entry point
- `/popkit:routine morning` - Can detect in morning check
- `hooks/utils/research_branch_detector.py` - Detection utility
- `output-styles/research-summary.md` - Output formatting
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts โ single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score โฅ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.