orch-build-mvp

SkillDocs & knowledge

orch-build-mvp is a skill that turns a design or spec document into a working first version of a product. It reads the document, plans thin vertical slices, scaffolds the first end-to-end slice, and then runs a generator-evaluator loop with review and gated commits. Use it when a design or spec document must become a running MVP.

Use orch-build-mvp in Claude, ChatGPT or Ahel Desktop

Free. Sign in, add orch-build-mvp and connect your AI. About a minute.

Also: Claude Code · Cursor · Codex

Then ask your AI: use the orch-build-mvp skill

Details

Instructions available. Your AI can read the instructions. Execution depends on the setup they require.

Have a design or spec document ready in a format the agent can read.

orch-build-mvpStart free

What your AI can do with it

  • Ingest an SDD or PRD document and extract scope and features
  • Plan thin vertical slices that end in one complete path
  • Scaffold the first end-to-end slice
  • Drive a generator-evaluator build loop against a rubric
  • Pause at approval gates before committing changes

Getting started

  1. Have a design or spec document ready in a format the agent can read.
  2. Add the orch-build-mvp skill to your agent setup.
  3. Point the agent at the document and ask it to plan the MVP slices.
  4. Review the planned slices and approve the first one to scaffold.
  5. Let the build loop run and approve changes at each gate before they are committed.

What this skill tells your AI

The instructions your AI receives, as published by affaan-m/ecc in skills/orch-build-mvp/SKILL.md and read by ahel’s review.

Actor · action · target: orch · build · mvp. Thin wrapper over the shared engine in orch-pipeline.

When to Use

  • The user has a design / spec document (SDD, PRD, system_design) and wants a working vertical slice bootstrapped from it.
  • Takes a doc path as its argument, e.g. civicpulse/docs/SDD-v0.6.md.

Operation settings

  • Default size floor: large — this is the full pipeline including Scaffold.
  • Phase mask: 0 (read the spec) → 1 → 2 (heavy) → 3 (scaffold) → 4 → 5 → 6.
  • First move (phase 0 → 2): read the doc; extract scope, locked decisions, and the feature list; order it into thin vertical slices (one end-to-end path first, not all-models-then-all-views). Phase 3 stands up that first slice.

How It Works

  1. Run the orch-pipeline engine with the settings above.
  2. Reuse the existing GAN harness instead of hand-rolling an iterate loop:
    • Translate the SDD into gan-harness/spec.md + gan-harness/eval-rubric.md (this stands in for what gan-planner would generate — you already have the spec).
    • Drive the build with /gan-build "<one-line brief>" --skip-planner (defaults: --max-iterations 15, --pass-threshold 7.0, --eval-mode playwright; use --eval-mode code-only for non-UI slices).
    • That command runs the gan-generator → gan-evaluator loop and writes gan-harness/feedback/feedback-NNN.md until the score passes or plateaus.
  3. Stop at Gate 1 (slice plan) and Gate 2 (pre-commit). Commit the scaffold and each slice as separate feat: commits.
  4. Add security-reviewer for any slice touching a security trigger.

Example

orch-build-mvp: civicpulse/docs/SDD-v0.6.md
→ read SDD → slice list (vertical) → scaffold slice 1  [GATE 1: approve]
→ /gan-build --skip-planner (generator → evaluator loop) scores vs spec → review
→ commit feat:  [GATE 2: confirm] → next slice

Signals

GitHub stars
270k
Forks
40k
Last commit
Sep 2026

Questions

What kind of document does it need?
It works from a design or spec document such as an SDD or PRD. The document must describe the scope and features so the skill can extract them and plan slices.
Does it commit changes automatically?
No. Changes pause at approval gates before being committed, so a person reviews each step.
How does it decide what to build first?
It orders work into thin vertical slices that end in one complete path, then scaffolds the first slice before starting the build loop.
What happens if the generated code fails review?
The generator-evaluator loop continues: code is generated, evaluated against a rubric, and repeated until the result passes review.
Advanced
Item type
skill
Key
orch-build-mvp
Source
github.com/affaan-m/ecc