NEW Browse AI tools across categories — updated daily. See what's new →

Migrate

Evaluate whether to upgrade from Torque (GSD + Superpowers) to Meridian, and guide the migration if ready. Use when projects outgrow the routing model.

Version1.0.0
LicenseMIT
Token count~1,347
UpdatedJun 5, 2026

Install

Quick install

via npx skills · works with 57+ agents
npx skills add https://github.com/mattjaikaran/meridian
Or pick agent:
npx skills add mattjaikaran/meridian --agent claude-code
npx skills add mattjaikaran/meridian --agent cursor
npx skills add mattjaikaran/meridian --agent codex
npx skills add mattjaikaran/meridian --agent opencode
npx skills add mattjaikaran/meridian --agent github-copilot
npx skills add mattjaikaran/meridian --agent windsurf
More install options

Shorthand — useful for multi-skill repos:

npx skills add mattjaikaran/meridian

Manual — clone the repo and drop the folder into your agent's skills directory:

git clone https://github.com/mattjaikaran/meridian.git
cp -r meridian ~/.claude/skills/
How to use: Once installed, ask your agent to "use the Migrate skill" or describe what you want (e.g. "Evaluate whether to upgrade from Torque (GSD + Superpowers) to Meridian, and gui"). Requires Node.js 18+.

Migrate

Evaluate whether to upgrade from Torque (GSD + Superpowers) to Meridian, and guide the migration if ready. Use when projects outgrow the routing model.

---
name: torque:migrate
description: "Evaluate whether to upgrade from Torque (GSD + Superpowers) to Meridian, and guide the migration if ready. Use when projects outgrow the routing model."
---

Migrate to Meridian

Evaluate whether the current project would benefit from upgrading to Meridian and provide a migration path.

What is Meridian?

Meridian is the standalone successor to Torque. Instead of routing between GSD and Superpowers, Meridian IS the system — a SQLite-backed state machine with 39 commands, deterministic resume, quality gates, and remote agent dispatch.

When to Migrate

Signals you've outgrown Torque

Run through this checklist. If 3+ are true, Meridian is the right move.

  • [ ] Session continuity is painful — you lose context between sessions and /gsd:resume-work isn't enough
  • [ ] Multi-milestone project — you've completed 1+ milestones and are starting another
  • [ ] Team coordination — multiple people or AI agents need to work on the project
  • [ ] You want deterministic resume — same state should produce the exact same prompt every time
  • [ ] You need board sync — Linear, Jira, or similar needs to stay in sync with phases
  • [ ] Remote execution — you want to dispatch plans to other machines or agents
  • [ ] Execution learnings — you want the system to learn from failures and improve over time
  • [ ] You're fighting the routing — GSD and SP conflict resolution is becoming overhead

Stay with Torque if

  • Project is simple (< 3 milestones expected)
  • You like GSD and Superpowers separately and just need them coordinated
  • You don't need persistent state beyond .planning/ files
  • Lightweight is a feature, not a limitation

Migration Path

Step 1: Install Meridian

git clone https://github.com/mattjaikaran/meridian.git ~/.claude/skills/meridian

Step 2: Initialize in your project

# In your project directory
# Meridian will detect existing .planning/ and offer to import

Then run /meridian:init — it creates .meridian/state.db and imports existing state.

Step 3: Map your workflow

| Torque (GSD + SP) | Meridian equivalent |
|-------------------|-------------------|
| /gsd:new-project | /meridian:init |
| /gsd:discuss-phase | /meridian:discuss |
| /gsd:spec-phase | /meridian:discuss (spec built-in) |
| /gsd:plan-phase | /meridian:plan |
| /gsd:execute-phase | /meridian:execute |
| /gsd:verify-work | /meridian:verify-phase |
| /gsd:validate-phase | /meridian:verify-phase (Nyquist built-in) |
| /gsd:resume-work | /meridian:resume (deterministic) |
| /gsd:quick | /meridian:quick |
| /gsd:fast | /meridian:fast |
| /gsd:ship | /meridian:ship |
| /gsd:pr-branch | /meridian:pr-branch |
| /gsd:autonomous | /meridian:autonomous |
| /gsd:insert-phase | /meridian:insert-phase |
| /gsd:remove-phase | /meridian:remove-phase |
| /gsd:undo | /meridian:revert |
| requesting-code-review | /meridian:review (two-stage) |
| receiving-code-review | /meridian:review (handles both sides) |
| systematic-debugging | /meridian:debug (with KB) |
| /gsd:note | /meridian:note |
| /gsd:plant-seed | /meridian:seed |
| /gsd:session-report | /meridian:report |
| /torque:status | /meridian:status or /meridian:dashboard |
| /torque:next | /meridian:next |

Step 4: What you gain

  • Deterministic resume: SQLite-backed, not file-based. Same state = same prompt.
  • Quality gates: Regression gate, stub detection, coverage tracking — enforced, not suggested.
  • Two-stage review: Spec compliance first, then code quality. Built-in, not bolted on.
  • Execution learnings: System learns from failures and injects rules into future plans.
  • Debug knowledge base: Resolved bugs persist and inform future debugging.
  • Board sync: Connect Linear/Jira with a pluggable provider.
  • Remote dispatch: Send plans to other agents for autonomous execution.
  • 39 commands: Everything Torque routes to, Meridian provides natively.

Step 5: Clean up

After migrating, you can optionally remove Torque:

rm -rf ~/.claude/skills/torque

The .planning/ directory is still valid — Meridian uses .meridian/ alongside it.

Output format

After evaluating the checklist:

## Migration Assessment

**Score**: 5/8 signals detected — Meridian recommended

### Signals detected
✓ Multi-milestone project (2 milestones completed)
✓ Session continuity issues (3 HANDOFF.md files found)
✓ Complex routing (both .planning/ and docs/plans/ present)
✗ No board sync needed
✗ No remote execution needed

### Recommendation
→ Install Meridian and run `/meridian:init` in this project.
   Your existing .planning/ state will be imported automatically.

Rules

  • Never modify any files. This is assessment-only unless the user explicitly asks to migrate.
  • Be honest — if Torque is sufficient, say so.
  • Always show the command mapping table so the user knows what changes.

---

Source: https://github.com/mattjaikaran/meridian
Author: mattjaikaran
Discovered via: skillsdirectory.com
Genre: ai-agents

SKILL.md source

---
name: Migrate
description: Evaluate whether to upgrade from Torque (GSD + Superpowers) to Meridian, and guide the migration if ready. Use when projects outgrow the routing model.
---

# Migrate

Evaluate whether to upgrade from Torque (GSD + Superpowers) to Meridian, and guide the migration if ready. Use when projects outgrow the routing model.

---
name: torque:migrate
description: "Evaluate whether to upgrade from Torque (GSD + Superpowers) to Meridian, and guide the migration if ready. Use when projects outgrow the routing model."
---

# Migrate to Meridian

Evaluate whether the current project would benefit from upgrading to [Meridian](https://github.com/mattjaikaran/meridian) and provide a migration path.

## What is Meridian?

Meridian is the standalone successor to Torque. Instead of routing between GSD and Superpowers, Meridian IS the system — a SQLite-backed state machine with 39 commands, deterministic resume, quality gates, and remote agent dispatch.

## When to Migrate

### Signals you've outgrown Torque

Run through this checklist. If 3+ are true, Meridian is the right move.

- [ ] **Session continuity is painful** — you lose context between sessions and `/gsd:resume-work` isn't enough
- [ ] **Multi-milestone project** — you've completed 1+ milestones and are starting another
- [ ] **Team coordination** — multiple people or AI agents need to work on the project
- [ ] **You want deterministic resume** — same state should produce the exact same prompt every time
- [ ] **You need board sync** — Linear, Jira, or similar needs to stay in sync with phases
- [ ] **Remote execution** — you want to dispatch plans to other machines or agents
- [ ] **Execution learnings** — you want the system to learn from failures and improve over time
- [ ] **You're fighting the routing** — GSD and SP conflict resolution is becoming overhead

### Stay with Torque if

- Project is simple (< 3 milestones expected)
- You like GSD and Superpowers separately and just need them coordinated
- You don't need persistent state beyond `.planning/` files
- Lightweight is a feature, not a limitation

## Migration Path

### Step 1: Install Meridian

```bash
git clone https://github.com/mattjaikaran/meridian.git ~/.claude/skills/meridian
```

### Step 2: Initialize in your project

```bash
# In your project directory
# Meridian will detect existing .planning/ and offer to import
```

Then run `/meridian:init` — it creates `.meridian/state.db` and imports existing state.

### Step 3: Map your workflow

| Torque (GSD + SP) | Meridian equivalent |
|-------------------|-------------------|
| `/gsd:new-project` | `/meridian:init` |
| `/gsd:discuss-phase` | `/meridian:discuss` |
| `/gsd:spec-phase` | `/meridian:discuss` (spec built-in) |
| `/gsd:plan-phase` | `/meridian:plan` |
| `/gsd:execute-phase` | `/meridian:execute` |
| `/gsd:verify-work` | `/meridian:verify-phase` |
| `/gsd:validate-phase` | `/meridian:verify-phase` (Nyquist built-in) |
| `/gsd:resume-work` | `/meridian:resume` (deterministic) |
| `/gsd:quick` | `/meridian:quick` |
| `/gsd:fast` | `/meridian:fast` |
| `/gsd:ship` | `/meridian:ship` |
| `/gsd:pr-branch` | `/meridian:pr-branch` |
| `/gsd:autonomous` | `/meridian:autonomous` |
| `/gsd:insert-phase` | `/meridian:insert-phase` |
| `/gsd:remove-phase` | `/meridian:remove-phase` |
| `/gsd:undo` | `/meridian:revert` |
| `requesting-code-review` | `/meridian:review` (two-stage) |
| `receiving-code-review` | `/meridian:review` (handles both sides) |
| `systematic-debugging` | `/meridian:debug` (with KB) |
| `/gsd:note` | `/meridian:note` |
| `/gsd:plant-seed` | `/meridian:seed` |
| `/gsd:session-report` | `/meridian:report` |
| `/torque:status` | `/meridian:status` or `/meridian:dashboard` |
| `/torque:next` | `/meridian:next` |

### Step 4: What you gain

- **Deterministic resume**: SQLite-backed, not file-based. Same state = same prompt.
- **Quality gates**: Regression gate, stub detection, coverage tracking — enforced, not suggested.
- **Two-stage review**: Spec compliance first, then code quality. Built-in, not bolted on.
- **Execution learnings**: System learns from failures and injects rules into future plans.
- **Debug knowledge base**: Resolved bugs persist and inform future debugging.
- **Board sync**: Connect Linear/Jira with a pluggable provider.
- **Remote dispatch**: Send plans to other agents for autonomous execution.
- **39 commands**: Everything Torque routes to, Meridian provides natively.

### Step 5: Clean up

After migrating, you can optionally remove Torque:
```bash
rm -rf ~/.claude/skills/torque
```

The `.planning/` directory is still valid — Meridian uses `.meridian/` alongside it.

## Output format

After evaluating the checklist:

```
## Migration Assessment

**Score**: 5/8 signals detected — Meridian recommended

### Signals detected
✓ Multi-milestone project (2 milestones completed)
✓ Session continuity issues (3 HANDOFF.md files found)
✓ Complex routing (both .planning/ and docs/plans/ present)
✗ No board sync needed
✗ No remote execution needed

### Recommendation
→ Install Meridian and run `/meridian:init` in this project.
   Your existing .planning/ state will be imported automatically.
```

## Rules

- Never modify any files. This is assessment-only unless the user explicitly asks to migrate.
- Be honest — if Torque is sufficient, say so.
- Always show the command mapping table so the user knows what changes.


---

**Source**: https://github.com/mattjaikaran/meridian
**Author**: mattjaikaran
**Discovered via**: skillsdirectory.com
**Genre**: ai-agents

Related skills 6

running-claude-code-via-litellm-copilot

★ Featured

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.

xixu-me 155k
AI & ML

skills-cli

★ Featured

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.

xixu-me 155k
AI & ML

repo-intake-and-plan

★ Featured

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.

lllllllama 127k
AI & ML

image-to-video

★ Featured

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...

agentspace-so 121k
AI & ML

video-edit

★ Featured

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...

agentspace-so 121k
AI & ML

nano-banana-2

★ Featured

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...

agentspace-so 121k
AI & ML