$ loading_
Turn a design or spec into a running MVP starting point.
The material indicates a prompt-only/workflow wrapper with no declared secrets, remote endpoints, or standalone system privileges. Combined with an open-source GitHub source and strong community adoption, the overall risk appears low, with only mild caution around document ingestion and scaffold/commit-oriented workflow described in the prompt.
The material explicitly states that no keys or environment variables are required, and the README does not request API tokens, cloud credentials, or account authorization; no credential collection, storage, or forwarding is described.
The system flags it as prompt-only and lists no remote endpoint hosts; while the document mentions build/evaluation workflow, it does not declare sending user data to any external service or unknown endpoint.
The README describes scaffolding, TDD implementation, committing, and invoking a shared engine plus a `/gan-build` workflow, indicating intended use around generating/modifying project code and advancing development tasks. Based on the material alone, no standalone executable component or extra system privilege request is shown, so this is normal capability warranting caution rather than a high-risk red flag.
The skill is intended to read a design/spec document path and transform that content into plans, scaffolding, and feedback files, which implies access to user-provided local project documents and derived artifacts. The material does not show data access beyond its stated purpose or any sign of overbroad authorization.
The source is an open-source GitHub repository, and the system flags it as open-source with very strong community adoption (about 210.5k stars), all of which are strong risk-reducing signals. The missing license declaration and unknown maintenance status add some governance uncertainty, but not enough to make it high risk.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "orch-build-mvp" skill from askskill: 1. Download https://raw.githubusercontent.com/affaan-m/ECC/main/skills/orch-build-mvp/SKILL.md 2. Save it as ~/.claude/skills/orch-build-mvp/SKILL.md 3. Reload skills and tell me it's ready
Using this PRD, plan the thinnest vertical slice for a task management web app and scaffold the first runnable version. First break down the user flow, define the minimal data model, generate frontend and backend skeletons, then TDD-implement the 'create task and display list' feature, and finally review the code and provide gated commit notes.
An MVP starter containing the slice plan, project scaffold, tests, first end-to-end implementation, and commit notes.
Read this design spec and build a runnable MVP prototype for a post-login dashboard product. Identify core pages and key interactions, plan the smallest closed-loop slice, generate the base project structure, and prioritize implementing the 'user logs in and views overview cards' flow with tests first, then self-review and list open questions.
A runnable prototype around the core post-login flow, with tests, review findings, and follow-up questions.
Based on this SDD, start MVP engineering for an internal approval system. First extract system boundaries and dependencies, choose the approval submission flow as the first vertical slice, complete repository initialization, basic CI setup, app scaffolding, testing framework integration, and implement a demo-ready approval request submission feature, then output review conclusions and next-step recommendations.
An engineering-ready starting point with repo structure, CI, test setup, first approval flow, and review recommendations.
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
Prevent destructive actions in production systems and autonomous agent workflows.
Learn Pythonic patterns, type hints, and best practices for maintainable code.
Optimize energy procurement, tariffs, PPAs, and multi-site energy cost strategies.
Apply PyTorch best practices for robust, efficient, reproducible deep learning pipelines.
Investigate quality nonconformances, find root causes, and drive CAPA improvements.
Search icons and generate Xcode-ready PNG asset sets for iOS apps.
Orchestrate end-to-end new feature delivery with research, TDD, review, and gated commits.
Plan features and create structured software design documents stored locally.
Create step-by-step implementation plans for engineers new to a codebase.
Build quick throwaway prototypes to validate options and deliver a verdict.
Generate PRDs, tech designs, and MVP plans with AI IDE prompt templates.
Read architecture config to map layers, trace slices, and validate rules.