KS
Killer-Skills

gogogo — Categories.community

v1.0.0
GitHub

About this Skill

Perfect for Development Agents needing automated implementation execution based on detailed plans. Agentic Ai by Paji

ContentsUS ContentsUS
[0]
[0]
Updated: 2/27/2026

Quality Score

Top 5%
46
Excellent
Based on code quality & docs
Installation
SYS Universal Install (Auto-Detect)
Cursor IDE Windsurf IDE VS Code IDE
> npx killer-skills add ContentsUS/Agentic-AI-Paji/gogogo

Agent Capability Analysis

The gogogo MCP Server by ContentsUS is an open-source Categories.community integration for Claude and other AI agents, enabling seamless task automation and capability expansion.

Ideal Agent Persona

Perfect for Development Agents needing automated implementation execution based on detailed plans.

Core Value

Empowers agents to execute planned implementations step-by-step, utilizing GitHub issues and JSON data for seamless execution, and automates the process of finding the most recent plan issue using gh issue list commands.

Capabilities Granted for gogogo MCP Server

Automating feature implementations
Executing planned fixes
Streamlining development workflows

! Prerequisites & Limits

  • Requires GitHub access
  • Needs gh issue list command functionality
  • Limited to executing plans labeled as 'plan' and in open state
Project
SKILL.md
4.4 KB
.cursorrules
1.2 KB
package.json
240 B
Ready
UTF-8

# Tags

[No tags]
SKILL.md
Readonly

GOGOGO - Execute Planned Implementation

Purpose

Execute the implementation plan step-by-step, following the detailed plan from the most recent "plan:" issue.

When to Use

  • User explicitly types gogogo
  • After creating a plan with nnn
  • Ready to implement a planned feature or fix

Steps

1. Find Implementation Issue

Find the most recent plan issue:

bash
1gh issue list --label "plan" --state open --limit 1 --json number,title

If no plan issue found:

  • Tell user: "No plan issue found. Create one with nnn first."
  • Stop execution

If plan issue found:

  • Display: "Found plan: #[number] - [title]"
  • Load the plan details:
bash
1gh issue view [number]

2. Prepare Branch

bash
1# Check current branch 2CURRENT_BRANCH=$(git branch --show-current) 3 4# If on main, create feature branch 5if [ "$CURRENT_BRANCH" = "main" ]; then 6 BRANCH_NAME="feat/issue-[number]-[description]" 7 git checkout -b $BRANCH_NAME 8fi 9 10# Ensure working directory is clean 11git status

3. Execute Implementation

Follow the plan step-by-step:

For each phase in the plan:

  1. Announce Phase: Tell user "Starting Phase X: [phase name]"
  2. Read Required Files: Use Read tool for files mentioned in the phase
  3. Make Changes: Use Edit or Write tools as needed
  4. Verify Changes: Check that changes compile/work
  5. Update Checklist: Comment on the issue to mark steps complete

Important:

  • Follow the plan exactly - don't add unplanned features
  • Keep changes focused and minimal
  • Test after each significant change
  • If you discover issues with the plan, ask user before deviating

4. Test & Verify

After implementation:

bash
1# Run build (if applicable) 2[build-command] 3 4# Run tests (if applicable) 5[test-command] 6 7# Manual verification 8# Test key scenarios mentioned in the plan

If tests fail:

  • Fix the issues
  • Re-run tests
  • Don't proceed until tests pass

5. Commit & Push

bash
1# Stage all changes 2git add -A 3 4# Create descriptive commit 5git commit -m "$(cat <<'EOF' 6feat: [Brief description from plan] 7 8- What: [Specific changes made] 9- Why: [Reason from plan] 10- Impact: [What this affects] 11 12Implements #[plan-issue-number] 13EOF 14)" 15 16# Push to remote 17git push -u origin $(git branch --show-current)

6. Create Pull Request

bash
1gh pr create --title "feat: [Same as commit title]" --body "$(cat <<'EOF' 2## Summary 3[Brief overview of what was implemented] 4 5## Implementation Details 6- [Key change 1] 7- [Key change 2] 8- [Key change 3] 9 10## Testing 11- [x] Build successful 12- [x] Tests passing 13- [x] Manual testing completed 14 15## Related Issues 16Implements #[plan-issue-number] 17 18--- 19🤖 Generated with [Claude Code](https://claude.com/claude-code) 20EOF 21)"

7. Update Plan Issue

Comment on the plan issue:

bash
1gh issue comment [plan-number] --body "✅ Implementation complete! 2 3**PR Created:** #[pr-number] 4 5**What was done:** 6- [Summary of implementation] 7 8**Test Results:** 9- Build: ✅ Passing 10- Tests: ✅ All passing 11- Manual: ✅ Verified 12 13Ready for review!"

8. Report to User

Provide a complete summary:

✅ Implementation Complete!

**Plan Issue:** #[plan-number]
**PR Created:** #[pr-number]
**Branch:** [branch-name]

**Changes:**
- [file1]: [what changed]
- [file2]: [what changed]

**Tests:** ✅ All passing
**Build:** ✅ Successful

**Next steps:**
1. Review the PR: [pr-url]
2. Request review from team
3. Merge when approved

⚠️ **IMPORTANT:** Don't merge until user explicitly approves!

Important Notes

  • Follow the Plan: Don't deviate without asking
  • Test Everything: Never skip testing
  • Commit Often: Make logical commits as you progress
  • Safety First: Follow all git safety rules (no --force)
  • Never Merge: Only create PR, wait for user approval
  • Ask Questions: If plan is unclear, ask user before proceeding
  • Update Issue: Keep the plan issue updated with progress

Error Handling

If build fails:

  1. Read error messages carefully
  2. Fix the issues
  3. Re-run build
  4. Continue only when passing

If plan is incomplete:

  1. Ask user for clarification
  2. Update plan issue with questions
  3. Wait for user response

If stuck:

  1. Document what you tried
  2. Comment on plan issue with blockers
  3. Ask user for guidance

Success Criteria

  • ✅ All plan phases completed
  • ✅ All tests passing
  • ✅ Build successful
  • ✅ PR created (not merged)
  • ✅ Plan issue updated
  • ✅ User provided with clear summary

Related Skills

Looking for an alternative to gogogo or building a Categories.community AI Agent? Explore these related open-source MCP Servers.

View All

widget-generator

Logo of f
f

widget-generator is an open-source AI agent skill for creating widget plugins that are injected into prompt feeds on prompts.chat. It supports two rendering modes: standard prompt widgets using default PromptCard styling and custom render widgets built as full React components.

149.6k
0
Design

chat-sdk

Logo of lobehub
lobehub

chat-sdk is a unified TypeScript SDK for building chat bots across multiple platforms, providing a single interface for deploying bot logic.

73.0k
0
Communication

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication