By mayurpise
Practice Context-Driven Development: draft specs and plans from project context before coding, decompose into tracks, implement tasks via TDD with automated reviews, audit git diffs for risks, hunt bugs, generate docs/ADRs/checklists, manage incidents/Jira, and track progress in monorepos.
npx claudepluginhub mayurpise/draft --plugin draftCreate and manage Architecture Decision Records. Documents significant technical decisions with context, alternatives, and consequences. Also supports evaluate (assess proposals) and design (system design) modes.
Lower cognitive load for human reviewers by auditing specifically for architectural risks mapped to the original track specification.
Performs an exhaustive 14-dimension bug hunt across the codebase using Draft context (architecture, tech-stack, product) for false-positive elimination. Generates a severity-ranked report with code evidence, data flow traces, and suggested fixes. Optionally writes regression tests. Use when the user asks to find bugs, audit code for defects, scan for vulnerabilities, or says 'hunt bugs', 'find bugs', or 'code audit'.
Handle mid-track requirement changes. Analyzes impact on completed and pending tasks, proposes amendments to spec.md and plan.md before applying.
Compute code coverage for active track or module. Targets 95%+ coverage with report and justification for uncovered lines. Complements TDD workflow.
Runs a structured debugging session: reproduces the bug, isolates the failing code path, forms and tests hypotheses one at a time, fixes with developer approval, and generates a debug report. Use when the user reports an error, crash, broken feature, exception, stack trace, or says 'not working', 'debug this', or 'investigate bug'. Invoked by /draft:new-track for bug tracks or directly for ad-hoc debugging.
Decompose project or track into modules with dependency mapping. Updates architecture.md (source of truth) and derives .ai-context.md (token-optimized, derived from architecture.md) with module definitions, dependency diagram, and implementation order.
Perform an exhaustive end-to-end lifecycle review of a service, component, or module. Evaluates ACID compliance, architectural resilience, and production-grade enterprise quality.
Pre-deployment verification checklist. Generates customized checklists based on tech-stack with rollback triggers.
Technical documentation writing and maintenance. Modes — readme, runbook, api, onboarding. Uses writer agent principles for audience-appropriate, maintainable docs.
Lists all Draft CLI commands, explains the Context-Driven Development workflow (init, new-track, implement, review), and recommends the appropriate next step. Use when the user asks about available Draft commands, needs help choosing a workflow step, or says 'what can Draft do', 'help', or 'show commands'.
Telemetry and analytics suite generating project-wide insights by parsing execution timestamps, revert history, and phase tracking.
Executes tasks from the current track's plan using TDD workflow (red-green-refactor). Implements one task at a time, commits after each, runs three-stage review at phase boundaries, and tracks progress in plan.md. Use when the user asks to implement the next task, start coding, continue a plan, run test-driven development, or says 'start implementing'.
Incident management lifecycle — triage, communicate, mitigate, postmortem. Three modes — new (start incident), update (status update), postmortem (blameless RCA report).
Build federated index from all child draft/ directories. Aggregates service-level context into root-level knowledge without deep code analysis. Use at monorepo root after services have been initialized with /draft:init.
Create Jira issues from jira-export-latest.md via MCP. Auto-generates export if missing.
Generate Jira export file from track plan for review before creating issues.
Scan codebase to discover coding patterns and update draft/guardrails.md. Learns conventions (skip in future) and anti-patterns (always flag). Supports migration from workflow.md and pattern promotion.
Start a new feature or bug track. Collaborative intake process with structured questions, AI guidance, and progressive refinement before generating spec.md and plan.md.
Lightweight ad-hoc code review for a PR, diff, or file. Four dimensions — security, performance, correctness, maintainability. No track context required.
Git-aware revert that understands Draft tracks, phases, and tasks. Safely undo work at task, phase, or track level.
Orchestrates multi-file code reviews at track level (against spec.md acceptance criteria) or project level (uncommitted changes, file patterns, commit ranges). Runs three stages: automated validation, spec compliance, and code quality. Optionally integrates bughunt. Use when the user asks for a code review, PR review, wants to check code quality, or validate changes against requirements.
Generate standup summary from git history, track progress, and optional Jira/GitHub PR activity. Read-only — makes no changes to the codebase.
Display current progress of Draft tracks and active tasks. Shows phases, completion percentages, and blocked items.
Identify, categorize, and prioritize technical debt across six dimensions. Generates remediation plans with effort estimates. Offered by /draft:new-track for refactor tracks.
Design test strategies and test plans with coverage targets. Complements /draft:coverage which measures what this skill plans. Auto-loaded by /draft:implement before TDD.
Engaging, interactive onboarding tour of the repository to train new engineers on system architecture and patterns without passive reading.
Persona-driven AI development team: orchestrator, team agents, review agents, skills, slash commands, and advisory hooks for Claude Code
Share bugs, ideas, or general feedback.
GitHub Spec-Kit integration for Specification-Driven Development - define WHAT and HOW before coding
End-to-end development workflow: design → draft-plan → orchestrate → review → pr-create → pr-review → pr-merge
Correctness workflow for structured development. 26 skills with configurable intensity levels: spec-before-code, skeptical review, enforced TDD, formal modeling, adversarial review, verification, documentation, and metrics. Intensity gates let you choose standard, high, or critical rigor per project.
Skills-first specification-driven development framework with 7 agent skills for planning, implementation, review, and shipping. Natural language activation with intelligent agent orchestration. Includes /plan, /implement, /research commands plus managing-specifications, implementing-features, and reviewing-and-shipping skills.
Spec-Driven Development Workflow for Claude Code. A 6-step pipeline: Requirements → Code Analysis → Design → Implement → Verify → Self-Improve. Specifications are the source of truth, code is a verified artifact.