By evanklem
Invoke 'let's evanflow this' to run a complete TDD-driven development loop in Claude Code: brainstorm ideas into plans, execute tasks via parallel coder-overseer pairs, apply vertical-slice TDD, iterate with root-cause debugging and self-reviews, using checkpoints to maintain context and quality without auto-commits.
npx claudepluginhub evanklem/evanflow --plugin evanflowImplementation subagent for one decomposed unit of work in the evanflow-coder-overseer pattern. Uses vertical-slice TDD per evanflow-tdd. Tool-restricted to prevent any git ops or destructive actions — you cannot accidentally commit, push, or modify state outside your task scope.
Read-only review subagent for one coder's output (or for cross-coder integration review) in the evanflow-coder-overseer pattern. Reports findings; never fixes. Tool-restricted to prevent any modifications — Read/Grep/Glob only, no Edit/Write/Bash. The role separation is the QA signal.
Clarify intent, propose 2-3 approaches, embedded grill to stress-test the chosen path. Use before any creative work — new features, components, behavior changes, design questions. Mockup-only requests use mockup quick-mode (no spec/plan ceremony).
Orchestrate parallel implementation with coder/overseer pairs. Coders implement decomposed tasks using evanflow-tdd; overseers review each coder's output for bugs, gaps, errors, AND cohesion violations against a shared contract. A final integration overseer checks cross-coder cohesion. Use for plans with 3+ truly independent tasks that share an interface contract.
Manage long-session context to prevent drift and degradation. Strategies for proactive summarization, branch isolation, and /clear decisions. Invoke when context feels heavy, when accuracy starts slipping, or proactively after a major phase boundary. Addresses the
Root-cause discipline for bugs, test failures, and unexpected behavior. Embedded grill on the hypothesis before writing fix code. Use when encountering any bug, failing test, or behavior that doesn't match expectation.
Design a module's interface using parallel sub-agents producing radically different designs ("design it twice"). Compare on depth, simplicity, and efficiency. Embedded grill on the synthesized choice. Use when designing a new API, exploring interface options, or deciding the shape of a refactor before writing code.
Execute a written implementation plan task-by-task with inline verification. Stop and ask on blockers. No forced sub-skill chains. Use when a plan exists and you're ready to implement.
Extract canonical domain terms into CONTEXT.md. Flag ambiguities (same word, different meanings) and synonyms (different words, same meaning). Re-invoking updates the file in place. Use when authoring or updating CONTEXT.md, or when a new domain term emerges in conversation.
Single entry-point orchestrator for the entire EvanFlow loop. The user says "let's evanflow this", "use evanflow", "evanflow this idea", "run this through evanflow", "implement with evanflow", or any similar phrasing — and you walk the full loop (brainstorm → plan → execute → tdd → iterate → STOP) end-to-end, announcing each step, respecting checkpoints, and stopping where the user retains control. Trigger keywords: "evanflow", "let's evanflow", "use evanflow", "evanflow this".
Identify refactoring opportunities by surfacing architectural friction. Apply the deletion test, deep-modules vocabulary, and seams analysis. Each opportunity becomes its own evanflow-writing-plans cycle. Use when reviewing code for refactoring, when a file has grown too large, or when architecture concerns surface during feature work.
Iterative self-review loop after implementing a plan. Re-read changed code with fresh eyes, fix issues found, re-run quality checks, repeat until clean. For UI work, includes visual verification (view the rendered page). Use after evanflow-executing-plans completes; on success, report and stop — the user decides what's next.
Synthesize a PRD (Product Requirements Document) for a big new feature. Synthesis (not interview) — uses existing project context and explicit ADRs. Asks before gh issue create. Use when scoping a substantial new feature in PRD shape (e.g., before a sprint).
Conversational bug discovery → issue draft. Light listening, background exploration, scope assessment. Asks before gh issue create — never auto-files. Use when conducting a QA session, triaging user-reported issues, or filing bugs.
Code review — both giving and receiving feedback. Verifying observed behavior over performative agreement. Use when reviewing a PR, requesting review on completed work, or processing review feedback you received.
Vertical-slice TDD for any production code. One test → one impl → repeat. Tests verify behavior through public interfaces, not internals. Use when implementing any feature, bugfix, or behavior change.
Turn a spec or requirements into a bite-sized implementation plan. File-structure-first (deep modules), embedded grill to stress-test, no forced sub-skill chains. Use when you have a spec or clear requirements and are ready to plan execution.
Meta skill for the EvanFlow system. Loads the shared vocabulary (deep modules, deletion test, vertical slice, grill, mockup quick-mode, no-auto-commit) and describes when to invoke each evanflow-* skill. Use when starting a new task and unsure which evanflow skill applies, or when you need to ground reasoning in the shared vocabulary.
Executes bash commands
Hook triggers when Bash tool is used
Uses power tools
Uses Bash, Write, or Edit tools
Share bugs, ideas, or general feedback.
Persona-driven AI development team: orchestrator, team agents, review agents, skills, slash commands, and advisory hooks for Claude Code
Test-driven development skill that enforces red-green-refactor, one test at a time
AI-driven development toolkit for TDD and SDD workflows, providing comprehensive command templates and agents to enhance developer productivity with Claude Code
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Manus-style persistent markdown files for planning, progress tracking, and knowledge storage. Works with Claude Code, Kiro, Clawd CLI, Gemini CLI, Cursor, Continue, Hermes, and 17+ AI coding assistants. Now with Arabic, German, Spanish, and Chinese (Simplified & Traditional) support.