agentsclimarketplace

Research merge

Skill aiskillstore/marketplace/skills/jrc1883/research-merge

Security-audited skills for Claude, Codex & Claude Code. One-click install, quality verified.

Install
npx -y skills add aiskillstore/marketplace --skill research-merge

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.

What its author says it does

Copied from the file, not written here

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.

SKILL.md

7.5 KB, ~1.8k tokens by cl100k_base, as published. Nobody here has run it

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:

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:

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)

# 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]

🤖 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

git merge --squash origin/claude/research-[topic]-[session-id]
git commit -m "docs(research): merge [topic] research

Merged from: [branch-name]

🤖 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

# 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:

## 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

## 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

SituationResponse
Dirty working directoryPrompt to commit/stash first
Merge conflictsShow conflicts, offer manual resolution
gh CLI unavailableSkip issue creation, note in output
No doc filesMerge anyway, create minimal issue
Branch already mergedSkip, note in output

Research Document Standard

For best results, research docs should follow this format:

# 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

ComponentRole
pop-next-actionCalls this skill when branches detected
research_branch_detector.pyCore detection logic
/popkit:nextEntry point for auto-detection
/popkit:routine morningCan include in morning routine
GitHub IssuesOutput 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

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.