dlabs/claude-marketplace

ab-testing

Production A/B testing lifecycle for design variants. Covers hypothesis formation, feature flags, variant comparison, analytics tracking, statistical significance analysis, experiment setup, and cleanup.

原文の言語: 英語

agent-browser

Browser automation using Vercel's agent-browser CLI. Use when you need to interact with web pages, fill forms, take screenshots, or scrape data. Uses Bash commands with ref-based element selection. Triggers on "browse website", "fill form", "click button",…

原文の言語: 英語

architecture-review

Multi-agent architecture review combining core architecture design with parallel security, performance, and data integrity assessments. Produces ADRs in MADR format. Covers ADR, architecture decision, system design, scalability assessment. Not for code review…

原文の言語: 英語

batch-integration

Reference for how the built-in /batch command integrates with blueprint-dev workflows — parallel codebase-wide changes using worktrees with project context.

原文の言語: 英語

claude-md-learning

Analyzes detected stack profiles and suggests targeted CLAUDE.md improvements. Covers CLAUDE.md improvement, project configuration, AI instructions. Never auto-writes to CLAUDE.md — stages suggestions for user review.

原文の言語: 英語

compound-knowledge

Problem documentation methodology for compounding team knowledge. Captures solved problems with structured metadata for searchability, pattern detection, and prevention. Covers postmortem, lessons learned, debugging documentation, solved problem capture. Not…

原文の言語: 英語

eval-runner

Run evaluation suites against blueprint-dev skills. Benchmarks skill performance, tracks pass rates, and validates skill quality after changes.

原文の言語: 英語

git-worktree

Git worktree management for isolated parallel development. Handles creating, listing, switching, and cleaning up worktrees with interactive confirmations, automatic .env copying, and .gitignore management. Follows KISS principles.

原文の言語: 英語

lightweight-planning

Fast-lane planning for bug fixes, UI tweaks, and features under 600 LOC. Scope triage, adaptive process, right-sized ceremony. Use for small-to-medium changes that don't need full requirements decomposition.

原文の言語: 英語

planning-methodology

Full planning framework for complex features needing requirements decomposition, research, and scope analysis. For tasks with 15+ files, 5+ endpoints, architecture decisions, or security concerns. Templates for PRD, spec, and scope documents.

原文の言語: 英語

pr-workflow

End-to-end pull request lifecycle reference. Ties together branch creation, implementation, /simplify, code review, and merge following trunk-based-dev rules.

原文の言語: 英語

simplify-integration

Reference for how the built-in /simplify command integrates with blueprint-dev workflows — when it runs, what it checks, and how it complements review agents.

原文の言語: 英語

stack-detection

Detects project technology stacks by analyzing package manifests, config files, directory structures, and code patterns. Produces a structured stack profile for agent adaptation. Covers technology detection, framework identification, project type analysis.

原文の言語: 英語

swarm-orchestration

Orchestration patterns for multi-agent team workflows — team definitions, sequencing rules, result aggregation, conflict resolution. Covers multi-agent coordination, parallel agents, team workflow.

原文の言語: 英語

trunk-based-dev

Trunk-based development practices with short-lived branches, feature flags, small PRs, and continuous integration. Enforced via hooks and agents.

原文の言語: 英語

digital-twin-universe

Framework for building behavioral clones (digital twins) of third-party services. Covers API surface replication, state machines, chaos injection, and twin composition for validating at volumes and rates impossible against live services.

原文の言語: 英語

satisfaction-metrics

Framework for measuring, aggregating, and trending satisfaction scores across scenarios. Covers LLM-as-judge methodology, trajectory evaluation, threshold configuration, comparison analysis, and reporting.

原文の言語: 英語

scenario-methodology

Framework for authoring, structuring, and managing scenarios — end-to-end user stories validated probabilistically by LLM-as-judge. Covers the holdout principle, scenario anatomy, versioning, composition, and anti-reward-hacking patterns.

原文の言語: 英語

design-system

Code-first design exploration workflow. Product Planning → Section Design → Brand (optional) → Explore (HTML variants) → Refine → Decide (extract tokens) → Ship (Next.js components). Covers section screen design, brand discovery, variant generation, iterative…

原文の言語: 英語

product-planning

Guided product planning workflow. Define your product (overview + roadmap), model data entities, specify the app shell, and create feature sections — all through interactive conversation that produces viewer-compatible structured markdown.

原文の言語: 英語