Verifies tests, reviews for EC memory storage, and presents merge options. Use when implementation is complete and ready to finish a feature branch.
Verifies tests, stores learnings in memory, and presents merge options for completed feature branches.
npx claudepluginhub merewhiplash/engram-cogitatorThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Complete development work with verification, memory storage, and merge options.
Announce: "I'm using the finishing-branch skill to complete this work."
Verify Tests → EC Review → Present Options → Execute
Load project config:
ec_search:
query: project config
type: config
Run all verifications:
{test_command}
{lint_command}
{build_command}
If failures: Stop. Fix using @debugging before proceeding.
If passing: Continue.
Before finishing, review what's worth remembering.
Look at what changed:
git log --oneline main..HEAD
git diff --stat main..HEAD
Use AskUserQuestion:
{
"questions": [{
"question": "Any decisions, learnings, or patterns worth storing in EC?",
"header": "Memory",
"options": [
{ "label": "Yes", "description": "I'll describe what to store" },
{ "label": "No", "description": "Nothing notable this time" },
{ "label": "Let me suggest", "description": "Claude proposes, I approve" }
],
"multiSelect": false
}]
}
If "Let me suggest" - analyze the changes and propose:
For each approved memory:
ec_add:
type: decision|learning|pattern
area: [component]
content: [What to remember]
rationale: [Why it matters]
Load branch convention:
ec_search:
query: project config branch
type: config
{
"questions": [{
"question": "How do you want to finish this branch?",
"header": "Finish",
"options": [
{ "label": "Create PR", "description": "Push and open pull request" },
{ "label": "Merge locally", "description": "Merge to main locally" },
{ "label": "Keep as-is", "description": "I'll handle it later" },
{ "label": "Discard", "description": "Delete this branch and work" }
],
"multiSelect": false
}]
}
git push -u origin $(git branch --show-current)
gh pr create --title "<title>" --body "$(cat <<'EOF'
## Summary
- [What changed]
## Test Plan
- [ ] [Verification steps]
## EC Context
- [Relevant decisions/patterns consulted or created]
---
Design: docs/designs/YYYY-MM-DD-<topic>.md
Plan: docs/plans/YYYY-MM-DD-<topic>.md
EOF
)"
git checkout main
git pull
git merge <feature-branch>
{test_command} # Verify on merged result
git branch -d <feature-branch>
"Branch preserved. You can return to it later."
Confirm first:
"This will delete branch
<name>and all commits. Type 'discard' to confirm."
git checkout main
git branch -D <feature-branch>
After successful merge/PR:
"Branch complete. What's next?"
Suggest based on context:
Activates when the user asks about AI prompts, needs prompt templates, wants to search for prompts, or mentions prompts.chat. Use for discovering, retrieving, and improving prompts.
Search, retrieve, and install Agent Skills from the prompts.chat registry using MCP tools. Use when the user asks to find skills, browse skill catalogs, install a skill for Claude, or extend Claude's capabilities with reusable AI agent components.
This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.