kumi

Plugin kumi from marketplace buildwithclaude in davepoon/buildwithclaude. Commands read from the repo's manifest — yesterday.

Skills (23)

• aki

  Reviews React and TypeScript code for correctness, performance, accessibility, and consistency before it ships. Read-only, never edits; reports findings ranked by severity. Send writing to noa, a bug to rui.

• anu

  Finds and fixes a specific Python bug: a traceback, a failing test, wrong output, an exception. Reproduces it first and changes only what is broken. Send new Python to eero, a review to ivo.

• eero

  Writes and edits Python code from a spec: features, modules, functionality. Send a specific bug to anu, a review to ivo.

• enn

  Starts, stops, and inspects running processes and dev servers: launching a Go binary or a dev server, killing a process by port or name, checking what holds a port. It manages processes and does not edit code.

• ivo

  Reviews Python code for quality, correctness, security, and style before it ships. Read-only, never edits. Send writing to eero, a bug to anu.

• jaan

  Writes and edits Go code from a spec: features, endpoints, new packages, functionality. Send a specific bug to siim, a review to mart, a design to kai.

• kadi

  Finds and fixes a specific Angular or TypeScript bug: a broken component, a wrong render, a failing API call, a compile error. Finds the root cause first and changes only what is broken. Send new features to liis, a review to tiiu.

• kai

  Designs and specs before any code is written, in any stack: a new system, interfaces and module boundaries, a technical spec. Reads the existing codebase and produces an architecture document, and never writes code. Hands the spec to the stack's implementer (jaan for Go, noa for React, eero for Pyth

• liis

  Writes and edits Angular and TypeScript features from a spec: components, routes, services, templates, signals. Send a specific bug to kadi, a review to tiiu.

• mart

  Reviews Go code for quality, security, and architecture before it merges. Read-only, never edits; reports findings ranked by severity. Good after jaan or siim, or on any Go about to ship. Send writing to jaan, a bug to siim.

• noa

  Writes and edits React and TypeScript from a spec: components, hooks, state, features. Send a specific bug to rui, a review to aki.

• remo

  Models document and key-value data and its access patterns, for stores like MongoDB, DynamoDB, and Redis. Send relational schema and SQL to saku.

• ren

  Writes and edits Swift and iOS features with SwiftUI from a spec: screens, views, data models, following Apple's Human Interface Guidelines. Send a specific bug to shu, a review to ryo.

• rui

  Finds and fixes a specific React bug: a render error, broken state, a stale closure, a bad effect, wrong UI behavior. Reproduces it first and changes only what is broken. Send new React to noa, a review to aki.

• ryo

  Reviews Swift and iOS code for quality, memory safety, and Human Interface Guidelines compliance before an App Store submission. Read-only, never edits. Good after ren or shu. Send writing to ren, a bug to shu.

• saku

  Handles relational database work: designing schema, writing and tuning SQL, and writing safe migrations, always from the current schema. Send document and key-value work to remo.

• shu

  Finds and fixes a specific Swift or iOS bug: a crash, wrong behavior, a rendering problem. Finds the root cause first and changes only what is broken. Send new features to ren, a review to ryo.

• siim

  Finds and fixes a specific Go bug: an error, a panic, a test failure, wrong behavior. Finds the root cause first and changes only the broken path. Send new features to jaan, a review to mart.

• sora

  Writes and maintains Dockerfiles, CI/CD pipelines (for example GitHub Actions), and infrastructure as code (Terraform, CloudFormation): builds, deploys, and environment config, across any stack. Always shows the plan and gets confirmation before applying, deploying, or destroying anything. Send a sy

• tiiu

  Reviews Angular and TypeScript code for correctness, performance, accessibility, and style before it ships. Read-only, never edits. Good after liis or kadi. Send writing to liis, a bug to kadi.

• trust

  Apply this project's kumi rules file after reviewing it. Type /kumi:trust alone to see the file and its code, then /kumi:trust followed by that code.

• untrust

  Stop applying this project's kumi rules file.

• yui

  Coordinates multi-step engineering work across the team. Routes a task to the right specialist, or runs a feature end to end when it spans design, build, debugging, and review. Use it when you are unsure who should handle something. Knows Go (jaan, siim, mart), Angular (liis, kadi, tiiu), iOS (ren,

Subagents (20)

• aki

  Reviews React and TypeScript code for correctness, performance, accessibility, and consistency before it ships. Read-only, never edits; reports findings ranked by severity. Send writing to noa, a bug to rui.

• anu

  Finds and fixes a specific Python bug: a traceback, a failing test, wrong output, an exception. Reproduces it first and changes only what is broken. Send new Python to eero, a review to ivo.

• eero

  Writes and edits Python code from a spec: features, modules, functionality. Send a specific bug to anu, a review to ivo.

• enn

  Starts, stops, and inspects running processes and dev servers: launching a Go binary or a dev server, killing a process by port or name, checking what holds a port. It manages processes and does not edit code.

• ivo

  Reviews Python code for quality, correctness, security, and style before it ships. Read-only, never edits. Send writing to eero, a bug to anu.

• jaan

  Writes and edits Go code from a spec: features, endpoints, new packages, functionality. Send a specific bug to siim, a review to mart, a design to kai.

• kadi

  Finds and fixes a specific Angular or TypeScript bug: a broken component, a wrong render, a failing API call, a compile error. Finds the root cause first and changes only what is broken. Send new features to liis, a review to tiiu.

• kai

  Designs and specs before any code is written, in any stack: a new system, interfaces and module boundaries, a technical spec. Reads the existing codebase and produces an architecture document, and never writes code. Hands the spec to the stack's implementer (jaan for Go, noa for React, eero for Pyth

• liis

  Writes and edits Angular and TypeScript features from a spec: components, routes, services, templates, signals. Send a specific bug to kadi, a review to tiiu.

• mart

  Reviews Go code for quality, security, and architecture before it merges. Read-only, never edits; reports findings ranked by severity. Good after jaan or siim, or on any Go about to ship. Send writing to jaan, a bug to siim.

• noa

  Writes and edits React and TypeScript from a spec: components, hooks, state, features. Send a specific bug to rui, a review to aki.

• remo

  Models document and key-value data and its access patterns, for stores like MongoDB, DynamoDB, and Redis. Send relational schema and SQL to saku.

• ren

  Writes and edits Swift and iOS features with SwiftUI from a spec: screens, views, data models, following Apple's Human Interface Guidelines. Send a specific bug to shu, a review to ryo.

• rui

  Finds and fixes a specific React bug: a render error, broken state, a stale closure, a bad effect, wrong UI behavior. Reproduces it first and changes only what is broken. Send new React to noa, a review to aki.

• ryo

  Reviews Swift and iOS code for quality, memory safety, and Human Interface Guidelines compliance before an App Store submission. Read-only, never edits. Good after ren or shu. Send writing to ren, a bug to shu.

• saku

  Handles relational database work: designing schema, writing and tuning SQL, and writing safe migrations, always from the current schema. Send document and key-value work to remo.

• shu

  Finds and fixes a specific Swift or iOS bug: a crash, wrong behavior, a rendering problem. Finds the root cause first and changes only what is broken. Send new features to ren, a review to ryo.

• siim

  Finds and fixes a specific Go bug: an error, a panic, a test failure, wrong behavior. Finds the root cause first and changes only the broken path. Send new features to jaan, a review to mart.

• sora

  Writes and maintains Dockerfiles, CI/CD pipelines (for example GitHub Actions), and infrastructure as code (Terraform, CloudFormation): builds, deploys, and environment config, across any stack. Always shows the plan and gets confirmation before applying, deploying, or destroying anything. Send a sy

• tiiu

  Reviews Angular and TypeScript code for correctness, performance, accessibility, and style before it ships. Read-only, never edits. Good after liis or kadi. Send writing to liis, a bug to kadi.

Hooks (12)

• SessionStart

  python3 -I -c "import os,runpy,sys;h=os.path.join(os.environ['CLAUDE_PLUGIN_ROOT'],'hooks');sys.path.insert(0,h);runpy.run_path(os.path.join(h,'restore_memory.py'),run_name='__main__')"

• SessionStart

  python3 -I -c "import os,runpy,sys;h=os.path.join(os.environ['CLAUDE_PLUGIN_ROOT'],'hooks');sys.path.insert(0,h);runpy.run_path(os.path.join(h,'apply_overrides.py'),run_name='__main__')"

• UserPromptSubmit

  python3 -I -c "import os,runpy,sys;h=os.path.join(os.environ['CLAUDE_PLUGIN_ROOT'],'hooks');sys.path.insert(0,h);runpy.run_path(os.path.join(h,'ensure_state.py'),run_name='__main__')"

• PreToolUse

  python3 -I -c "import os,runpy,sys;h=os.path.join(os.environ['CLAUDE_PLUGIN_ROOT'],'hooks');sys.path.insert(0,h);runpy.run_path(os.path.join(h,'ensure_state.py'),run_name='__main__')"

• PreToolUse

  python3 -I -c "import os,runpy,sys;h=os.path.join(os.environ['CLAUDE_PLUGIN_ROOT'],'hooks');sys.path.insert(0,h);runpy.run_path(os.path.join(h,'inject_specialist_context.py'),run_name='__main__')"

• UserPromptExpansion

  python3 -I -c "import os,runpy,sys;h=os.path.join(os.environ['CLAUDE_PLUGIN_ROOT'],'hooks');sys.path.insert(0,h);runpy.run_path(os.path.join(h,'ensure_state.py'),run_name='__main__')"

• UserPromptExpansion

  python3 -I -c "import os,runpy,sys;h=os.path.join(os.environ['CLAUDE_PLUGIN_ROOT'],'hooks');sys.path.insert(0,h);runpy.run_path(os.path.join(h,'confirm_overrides.py'),run_name='__main__')"

• PostToolUse

  python3 -I -c "import os,runpy,sys;h=os.path.join(os.environ['CLAUDE_PLUGIN_ROOT'],'hooks');sys.path.insert(0,h);runpy.run_path(os.path.join(h,'log_activity.py'),run_name='__main__')"

• Stop

  python3 -I -c "import os,runpy,sys;h=os.path.join(os.environ['CLAUDE_PLUGIN_ROOT'],'hooks');sys.path.insert(0,h);runpy.run_path(os.path.join(h,'capture_memory.py'),run_name='__main__')"

• Stop

  python3 -I -c "import os,runpy,sys;h=os.path.join(os.environ['CLAUDE_PLUGIN_ROOT'],'hooks');sys.path.insert(0,h);runpy.run_path(os.path.join(h,'record_metrics.py'),run_name='__main__')"

• SubagentStop

  python3 -I -c "import os,runpy,sys;h=os.path.join(os.environ['CLAUDE_PLUGIN_ROOT'],'hooks');sys.path.insert(0,h);runpy.run_path(os.path.join(h,'capture_memory.py'),run_name='__main__')"

• SubagentStop

  python3 -I -c "import os,runpy,sys;h=os.path.join(os.environ['CLAUDE_PLUGIN_ROOT'],'hooks');sys.path.insert(0,h);runpy.run_path(os.path.join(h,'record_metrics.py'),run_name='__main__')"

Similar plugins