workflow-feature-shipper
Feature Shipper
Turn "I want to build a feature" into a fast execution chain.
Input (Pass Paths Only)
feature.md: Requirements description (acceptance criteria + non-goals)repo_rootrun_dir
Optional flags (recommended inside feature.md)
mode:plan-only|execute(default:execute)feature_slug: short slug for artifact naming (default: derived from title + timestamp)quality_bar:demo-ready|functional-only(default:demo-readyfor user-facing UI features)
Output (Persisted)
evidence/features/<feature_slug>-plan.md(checklist plan: tasks + verification)evidence/parallel/features/<feature_slug>/(if implementation is split)evidence/features/<feature_slug>-summary.md
Process
- Hooks doctor (required check; non-blocking): Run
tool-hooks-doctoronce at the start of the session to verifyskill-evolutionhooks are enabled. If missing, offer to install project-level hooks; continue either way. - Read
feature.md, normalize into: acceptance criteria, boundaries, risks, rollback. - Prototype UI rule (default): if this feature affects user-facing UI and
quality_barisn’tfunctional-only, propose 1 “demo moment” (animation/micro-interaction) and add it to acceptance criteria. Must respectprefers-reduced-motion. - Produce 2 options (A: minimal; B: cleaner but slower), default to A. If user cares about “demo feel”, offer A-demo-ready vs A-functional-only as explicit sub-options.
- Split into PR-sized small steps (each independently runnable + rollback-able).
- Write plan to
evidence/features/<feature_slug>-plan.md. - If
mode: plan-only, stop here and ask for confirmation before implementing. - Implement (batch execution + checkpoints):
- UI visual/layout/animation changes → First call
tool-design-style-selectorto load the project’sdesign-system.md, then strictly follow it. Iftool-ui-ux-pro-maxis installed, use it to ground motion/UX constraints (search “animation” + “accessibility”). For complex visual/animation/responsive design, delegate to/geminifrontend UI/UX senior design agent. - Business logic/data flow/integration → Implement directly.
- Default batch rhythm: 3 small tasks per batch → run verification → report and wait for feedback; stop immediately for help when blocked/verification fails.
- After each batch (or before merge), recommend using
review-qualityfor a conclusive review + verdict.review-qualityis the single entry point and will auto-triage: if React/Next.js performance risk is detected, it will also runreview-react-best-practices.- If the user explicitly wants only a React/Next.js perf audit, run
review-react-best-practicesdirectly.
- UI visual/layout/animation changes → First call
- Verification: can run, can build (and existing tests pass).
- If verification fails (tests/build/runtime error): run
tool-systematic-debuggingbefore attempting more fixes. - Persist debugging artifacts to:
evidence/features/<feature_slug>-debug.md(repro steps, hypotheses, root cause, fix + re-verify)
- If verification fails (tests/build/runtime error): run
- Write
evidence/features/<feature_slug>-summary.md: what was done, how verified, next steps. - Wrap up: Do a
skill-evolutionEvolution checkpoint (3 questions); if user chooses "want to optimize", runskill-improverbased on thisrun_dirto produce minimal patch suggestions
Delivery Requirements
- No "big bang" refactoring
- Don't introduce new complexity (unless it significantly reduces future cost, and user confirms)
More from heyvhuang/ship-faster
mcp-supabase
Execute database operations via Supabase MCP (query/write/migration/logs/type generation). Triggers: query/statistics/export/insert/update/delete/fix/backfill/migrate/logs/alerts/type generation. Does not trigger for: pure architecture discussion or code planning. Write operations require confirmation; UPDATE/DELETE without WHERE is refused.
76tool-ast-grep-rules
Write AST-based code search and rewrite rules using ast-grep YAML. Create linting rules, code modernizations, and API migrations with auto-fix. Use when the user mentions ast-grep, tree-sitter patterns, code search rules, lint rules with YAML, AST matching, or code refactoring patterns.
55skill-evolution
Global evolution system for ship-faster skills. Uses hooks to capture context, failures, and session summaries, then generates patch suggestions (no auto edits) via skill-improver. Use when you want the skills to self-improve safely and continuously.
53review-doc-consistency
Documentation consistency reviewer that checks alignment between code implementation and documentation. Use when user requests reviewing documentation vs code consistency, checking if README/docs are outdated, verifying API documentation accuracy. Applicable for (1) reviewing README vs implementation consistency (2) checking if docs/ directory content is outdated (3) verifying API/config documentation accuracy (4) generating documentation consistency reports. Trigger words include doc review, documentation consistency, check outdated docs, verify docs.
53stripe
Billing and payment operations for Stripe: customers, products, prices, invoices, payment links, subscriptions, refunds, disputes, balance. Triggers: create customer, create product, create invoice, generate payment link, query transactions, process refunds, manage subscriptions, view disputes, check balance. Money operations require confirmation. MCP is optional — works with Dashboard/CLI too.
53tool-design-style-selector
Use when you need to define or converge a project's visual direction. Scan project documentation to identify intent, then produce a design-system.md (either preserve existing style or pick from 30 presets). Triggers: design system, design spec, UI style, visual style, design tokens, color palette, typography, layout. Flow: scan → intent → (gate) preserve vs preset → deploy design-system.md after confirmation → (default) implement UI/UX per design-system.md (plan first, then execute).
52