Install
Quick install
npx skills add https://github.com/speson/not-my-reforgenpx skills add speson/not-my-reforge --agent claude-codenpx skills add speson/not-my-reforge --agent cursornpx skills add speson/not-my-reforge --agent codexnpx skills add speson/not-my-reforge --agent opencodenpx skills add speson/not-my-reforge --agent github-copilotnpx skills add speson/not-my-reforge --agent windsurfMore install options
Shorthand — useful for multi-skill repos:
npx skills add speson/not-my-reforgeManual — clone the repo and drop the folder into your agent's skills directory:
git clone https://github.com/speson/not-my-reforge.gitcp -r not-my-reforge ~/.claude/skills/Team Pipeline
5-stage quality pipeline for Agent Teams — Plan, PRD, Execute, Verify, Fix
---
name: team-pipeline
description: 5-stage quality pipeline for Agent Teams — Plan, PRD, Execute, Verify, Fix
user_invocable: true
---
Team Pipeline
A structured 5-stage pipeline for executing complex tasks with Agent Teams.
Pipeline Stages
Stage 1: Plan
The planner agent creates an implementation plan:- Analyze the codebase and task requirements
- Identify change points and dependencies
- Produce a structured plan with phases and steps
- Enter plan mode for lead approval
Stage 2: PRD (Product Requirements Document)
The lead converts the approved plan into concrete tasks:- Create TaskCreate entries for each work unit
- Define clear acceptance criteria per task
- Set task dependencies (blockedBy/blocks)
- Assign tasks to workers
Stage 3: Execute
Workers implement in parallel:- Each worker operates in an isolated git worktree
- Workers follow their task's acceptance criteria
- Researcher gathers information as needed (background)
- Tester writes tests for implementations
Stage 4: Verify
Reviewer validates all changes:- Review each worker's diff against acceptance criteria
- Run full test suite
- Check for type errors and lint issues
- Verdict: APPROVE or REQUEST_CHANGES
Stage 5: Fix
If verification fails:- Failed items return to Execute stage
- Workers address reviewer feedback
- Re-verify until all checks pass
- Maximum 3 Fix cycles before escalating to user
Usage
omo team 3 <task description>The pipeline runs automatically when using the team command with the team-pipeline skill.
Quality Gates
Each stage transition requires:- Plan → PRD: Lead approval of plan
- PRD → Execute: All tasks created with acceptance criteria
- Execute → Verify: All tasks marked complete
- Verify → Fix/Done: Reviewer verdict
- Fix → Verify: Worker fixes applied
---
Source: https://github.com/speson/not-my-reforge
Author: speson
Discovered via: skillsdirectory.com
Genre: ai-agents
SKILL.md source
--- name: Team Pipeline description: 5-stage quality pipeline for Agent Teams — Plan, PRD, Execute, Verify, Fix --- # Team Pipeline 5-stage quality pipeline for Agent Teams — Plan, PRD, Execute, Verify, Fix --- name: team-pipeline description: 5-stage quality pipeline for Agent Teams — Plan, PRD, Execute, Verify, Fix user_invocable: true --- # Team Pipeline A structured 5-stage pipeline for executing complex tasks with Agent Teams. ## Pipeline Stages ### Stage 1: Plan The **planner** agent creates an implementation plan: - Analyze the codebase and task requirements - Identify change points and dependencies - Produce a structured plan with phases and steps - Enter plan mode for lead approval ### Stage 2: PRD (Product Requirements Document) The **lead** converts the approved plan into concrete tasks: - Create TaskCreate entries for each work unit - Define clear acceptance criteria per task - Set task dependencies (blockedBy/blocks) - Assign tasks to workers ### Stage 3: Execute **Workers** implement in parallel: - Each worker operates in an isolated git worktree - Workers follow their task's acceptance criteria - **Researcher** gathers information as needed (background) - **Tester** writes tests for implementations ### Stage 4: Verify **Reviewer** validates all changes: - Review each worker's diff against acceptance criteria - Run full test suite - Check for type errors and lint issues - Verdict: APPROVE or REQUEST_CHANGES ### Stage 5: Fix If verification fails: - Failed items return to Execute stage - Workers address reviewer feedback - Re-verify until all checks pass - Maximum 3 Fix cycles before escalating to user ## Usage ``` omo team 3 <task description> ``` The pipeline runs automatically when using the team command with the team-pipeline skill. ## Quality Gates Each stage transition requires: - Plan → PRD: Lead approval of plan - PRD → Execute: All tasks created with acceptance criteria - Execute → Verify: All tasks marked complete - Verify → Fix/Done: Reviewer verdict - Fix → Verify: Worker fixes applied --- **Source**: https://github.com/speson/not-my-reforge **Author**: speson **Discovered via**: skillsdirectory.com **Genre**: ai-agents
Related skills 6
running-claude-code-via-litellm-copilot
Use when routing Claude Code through a local LiteLLM proxy to GitHub Copilot, reducing direct Anthropic spend, configuring ANTHROPIC_BASE_URL or ANTHROPIC_MODEL overrides, or troubleshooting Copilot proxy setup failures such as model-not-found, no localhost traffic, or GitHub 401/403 auth errors.
skills-cli
Use when users ask to discover, install, list, check, update, remove, back up, restore, sync, or initialize Agent Skills, mention `bunx skills`, `npx skills`, `skills.sh`, or `skills-lock.json`, ask "find a skill for X", or want help extending agent capabilities with installable skills.
repo-intake-and-plan
Narrow RigorPilot helper for README-first deep learning repo reproduction. Use when the task is specifically to scan a repository, read the README and common project files, extract documented commands, classify inference, evaluation, and training candidates, and return the smallest trustworthy reproduction plan to the main orchestrator. Do not use for environment setup, asset download, command execution, final reporting, paper lookup, or end-to-end orchestration.
image-to-video
Animate any still image on RunComfy — this skill is a smart router that matches the user's intent to the right i2v model in the RunComfy catalog. Picks HappyHorse 1.0 I2V (Arena #1, native audio, identity preservation) for general animations, Wan 2.7 with `audio_url` for custom-voiceover lip-sync, or Seedance 2.0 Pro for multi-modal animation from image + reference video + reference audio. Bundles each model's documented prompting patterns so the caller gets sharper output without burning ite...
video-edit
Edit existing video on RunComfy — this skill is a smart router that matches the user's intent to the right edit model in the RunComfy catalog. Picks Wan 2.7 Edit-Video (general restyle / background swap / packaging swap, identity + motion preservation), Kling 2.6 Pro Motion Control (transfer precise motion from a reference video to a target character), or Lucy Edit Restyle (lightweight identity-stable restyle / outfit swap). Bundles each model's documented prompting patterns so the skill gets...
nano-banana-2
Generate images with Google Nano Banana 2 (Gemini-family flash-tier text-to-image) on RunComfy — bundled with the model's documented prompting patterns so the skill gets sharper output than naive prompting against the same model. Documents Nano Banana 2's strengths (rapid iteration, in-image typography rendering, predictable framing, optional web-grounded context), the resolution-tier pricing, the safety-tolerance dial, and when to route to Nano Banana Pro / GPT Image 2 / Flux 2 / Seedream in...