pillip

pillip/claude-dev-kit

Plugin Claude Code

PRD-driven AI dev team control plane for Claude Code.

pillip/claude-dev-kit

Plugin Claude Code

PRD-driven AI dev team control plane for Claude Code — agents, skills, and a GitHub-first sprint workflow.

pillip/claude-dev-kit

Agent

WCAG 2.1 AA accessibility audit — check color contrast, keyboard nav, screen reader support, touch targets, motion safety, and semantic structure.

pillip/claude-dev-kit

Agent

Design pragmatic software architecture from PRD and requirements. Make explicit tradeoffs, not theoretical diagrams.

pillip/claude-dev-kit

Agent

Interactive brainstorming agent — guides users from vague ideas to concrete problem definitions and solution directions through Socratic dialogue. Existing Landscape research is delegated to runtime /deep-research (primary) or the kit's degraded capture+validate flow; this agent does NOT make free-form web claims.

pillip/claude-dev-kit

Agent

Interactive business analysis agent — validates business viability through market research, competitive analysis, and strategic critique before PRD creation. Per SPEC-018, Market/Competitive/Pricing/Risks dimensions are delegated to runtime /deep-research (primary) or the kit's degraded capture+validate flow; this…

pillip/claude-dev-kit

Agent

Analyze an existing codebase in 4 passes — identity, architecture, requirements inference, quality assessment. Produces structured scancontext for downstream scan agents.

pillip/claude-dev-kit

Agent

Write all user-facing copy — UI labels, empty states, error messages, onboarding, CTAs. Produce a copy guide that developers can reference during implementation.

pillip/claude-dev-kit

Agent

Design detailed data models — schemas, indexes, migrations, seed data, query patterns. Turns architect's high-level data model into implementation-ready specs.

pillip/claude-dev-kit

Agent

Audit the design SYSTEM (tokens, component definitions, cross-platform alignment, philosophy compliance) — system-level only. Implementation-level checks belong to ui-reviewer.

pillip/claude-dev-kit

Agent

Extract the design system a codebase already ships — tokens, type scale, spacing, motion, and a reverse-engineered Signature Move — from web, React Native, or Electron sources. Read-only, provenance-tagged, never invents values.

pillip/claude-dev-kit

Agent

Desktop UI/UX development expert who establishes design philosophy based on PRD and UX specs, and generates desktop design systems, wireframes, and Electron prototypes.

pillip/claude-dev-kit

Agent

Implement issues with tests and GitHub-first flow — create GH Issue (if missing) + PR with Closes.

pillip/claude-dev-kit

Agent

Set up and maintain CI/CD pipelines, Dockerfiles, and deployment infrastructure.

pillip/claude-dev-kit

Agent

Maintain project documentation — setup guide, runbook, troubleshooting. Write for the reader, not the writer.

pillip/claude-dev-kit

Agent

Convert Figma API design data (from figmafetch.py) into clean prototype HTML using project design system tokens. Reads node trees, maps values to tokens, outputs semantic HTML.

pillip/claude-dev-kit

Agent

Create a single well-formed issue from natural language and update relevant planning docs.

pillip/claude-dev-kit

Agent

Mobile UI/UX development expert who establishes design philosophy based on PRD and UX specs, and generates mobile design systems, wireframes, and React Native (Expo) prototypes.

pillip/claude-dev-kit

Agent

Break requirements into small, implementable issues with dependencies, ordering, and estimates. Maintain issues.md as SSOT.

pillip/claude-dev-kit

Agent

Design test strategy and test cases from requirements — risk-based prioritization, coverage matrix, not test code.

pillip/claude-dev-kit

Agent

Analyze PRD.md and produce crisp requirements, scope, assumptions, and success metrics.

pillip/claude-dev-kit

Agent

Separate-context auditor for the kit's degraded research path. Verifies that every claim in brainstormnotes.md / businessanalysis.md carries a verbatim quote that appears in the captured source snapshot AND that the surrounding context supports the claim. Refute-first prompt — defaults claims to fabricated until…

pillip/claude-dev-kit

Agent

Separate-context auditor for the kit's review synthesis layer. Verifies that runtime /code-review and /security-review findings survive into docs/reviewnotes.md without being dropped, distorted, severity-changed, or scope-shifted. Refute-first prompt — defaults findings to suspect until proven faithful.

pillip/claude-dev-kit

Agent

Degraded-path fallback for /review's correctness + security dimensions (per SPEC-019), plus the kit-distinctive over-engineering minimality axis which runs on BOTH paths. On the primary path, kit /review delegates correctness + security to runtime /code-review and /security-review; this agent then runs only the…