Turn a design or requirements document into a working MVP, a minimal product, through small end-to-end feature slices. It coordinates scaffolding, repeated generation and evaluation, reviews, and approval gates, with separate commits for the scaffold and each slice.
Orchestrate bootstrapping a working MVP from a design or spec document — ingest the SDD/PRD, plan thin vertical slices, scaffold the first end-to-end slice, then drive a generator-evaluator build loop with review and gated feat commits. Use when a design or spec document must become a running MVP through planned vertical slices.
This skill guides the work of turning a design or requirements document into an MVP, a minimal working product. It extracts scope, settled decisions, and the feature list, then divides the work into small feature slices that each support a complete path from start to finish. It scaffolds the first slice and coordinates repeated generation and evaluation, review, and approval. The scaffold and each feature slice receive separate feat: commits.
Use it when you have an SDD or PRD but have not decided where to begin building the product. It supports getting one user path working first, adding features afterward, and using evaluation results to guide implementation.
Supply the document path as an argument. The skill uses the shared orch-pipeline, an existing GAN harness, and /gan-build. UI evaluation defaults to playwright; non-UI work uses code-only. Approval is required for the feature plan and before committing. Security-related features also involve security-reviewer.
This overview was written by AI (OpenAI Codex) from the public SKILL.md. Check the original below for the exact behavior.
AI rated this skill on four points using only the contents of its SKILL.md. Stars and popularity are not taken into account.
The total counts each point as A = 25, B = 15, C = 5. Rated by AI (OpenAI Codex) as of Oct 19, 2026. Treat it as a guide and read the original before installing.
Review the instructions the agent will receive before you install.
Actor · action · target: orch · build · mvp. Thin wrapper over the shared
engine in orch-pipeline.
civicpulse/docs/SDD-v0.6.md.orch-pipeline engine with the settings above.gan-harness/spec.md + gan-harness/eval-rubric.md
(this stands in for what gan-planner would generate — you already have the spec)./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).gan-generator → gan-evaluator loop and writes
gan-harness/feedback/feedback-NNN.md until the score passes or plateaus.feat: commits.security-reviewer for any slice touching a security trigger.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
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Design and audit interfaces for Web, iOS, and Android using WCAG 2.2 accessibility guidance. Check screen-reader labels, keyboard navigation, contrast, and control sizes to identify barriers and guide implementation for people using assistive technology.
Investigate unreliable AI agents across 12 layers, including instructions, memory, tool execution, and display. Use code and logs to trace failures, rank findings by severity, and produce an ordered repair plan that prioritizes code changes.
Compare coding agents on tasks from your own codebase. Define success checks, run agents in separate Git working directories, and report pass rates, available API costs, completion time, and consistency across repeated trials.
Design and refine an AI agent’s available actions, tool inputs, and result formats. Define recovery steps for errors, manage the information kept in context, and evaluate changes through completion rates, retries, and cost per successful task.
Diagnose failed AI agent runs by capturing errors, checking likely causes, and choosing small, reversible recovery actions. The workflow produces a structured report of the failure, recovery steps, and evidence, helping explain repeated retries or stalled progress.
Diagnose AI agent runs that fail repeatedly, loop through tools, or lose track of the task. Capture errors and environment details, test a focused recovery action, and produce a report explaining the evidence and outcome.