luisabwk

luisabwk/kraken

Agent Claude Code

Confidence-based code review specialist. Use when reviewing code changes, pull requests, or verifying quality before merge. Applies scoring threshold of 80+ to avoid noise.

luisabwk/kraken

Agent Claude Code

Post-implementation code cleanup specialist. Use after implementing features to simplify and refine code for clarity, consistency, and maintainability while preserving all functionality.

luisabwk/kraken

Agent Claude Code

Systematic debugging specialist. Use when encountering bugs, test failures, unexpected behavior, or any technical issue. Follows a 4-phase root cause analysis process before proposing fixes.

luisabwk/kraken

Agent Claude Code

Product Requirement Prompt (PRP) creation and task decomposition specialist. Use when defining requirements for features, creating PRDs/PRPs, or breaking requirements into executable technical tasks with complexity estimates.

luisabwk/kraken

Agent Claude Code

Test-driven development specialist. Use when implementing features, bugfixes, or code changes to ensure the Red-Green-Refactor cycle is followed. Write tests first, watch them fail, then implement.

luisabwk/kraken

Command Claude Code

Initialize agent, verify setup, and load rules.

luisabwk/kraken

Command Claude Code

Repository hygiene — clean temp files, organize execution folders.

luisabwk/kraken

Command Claude Code

Confidence-based code review checklist.

luisabwk/kraken

Command Claude Code

Git commit with conventional commits format.

luisabwk/kraken

Command Claude Code

Dynamic context management — status, clean, log, save, read.

luisabwk/kraken

Command Claude Code

Run task execution workflow step-by-step.

luisabwk/kraken

Command Claude Code

Switch MCP mode to optimize context window.

luisabwk/kraken

Command Claude Code

Create new Product Requirement Prompt from scratch.

luisabwk/kraken

Command Claude Code

Review and validate an existing PRP.

luisabwk/kraken

Command Claude Code

Command "run" from luisabwk/kraken, covering run project locally and workflow.

luisabwk/kraken

Hook Claude Code

Runs after a tool call finishes for Write and Edit tool calls, running an inline shell check. From luisabwk/kraken.

luisabwk/kraken

Hook Claude Code

Runs before the agent uses a tool for Bash tool calls, running an inline shell check. From luisabwk/kraken.

luisabwk/kraken

Settings file Claude Code

Agent settings declaring 2 hook events (PostToolUse, PreToolUse) and 35 allowed tools.

luisabwk/kraken

Skill Claude CodeCodexCursor

Design, run, and analyze A/B tests (controlled experiments) using Ronny Kohavi's methodology and Gibson Biddle's DHM trade-off analysis. Use when the user needs to plan an experiment, choose metrics (OEC), evaluate statistical significance, assess sample size requirements, avoid common experimentation pitfalls, or…

luisabwk/kraken

Skill Claude CodeCodexCursor

Build AI evals using the Husain-Shankar framework (error analysis, open/axial coding, LLM-as-judge). Use when a user needs to create, improve, or debug evals for an AI product — including defining failure modes, building LLM judges, or setting up production monitoring for an LLM application.

luisabwk/kraken

Skill Claude CodeCodexCursor

Use after implementing features to simplify and refine code for clarity, consistency, and maintainability.

luisabwk/kraken

Skill Claude CodeCodexCursor

Guide teams through building sustainable customer interview habits and discovery practices. Use when setting up weekly customer interviews, preparing interview guides, coaching story-based interviewing technique, synthesizing user research findings, planning assumption tests, or helping teams that say they don't have…

luisabwk/kraken

Skill Claude CodeCodexCursor

Evaluate and strengthen product strategy using Gibson Biddle's DHM framework (Delight, Hard-to-copy, Margin-enhancing). Use when the user asks about product strategy, competitive advantage, feature prioritization trade-offs, or wants to stress-test whether a product idea is strategically sound.

luisabwk/kraken

Skill Claude CodeCodexCursor

Use when creating or editing structural files like commands, hooks, rules, AGENTS.md, or README files.