すべてのClaudeスキルを閲覧

Root Cause Tracing

Systematically traces software bugs back to their original trigger points through call stack analysis and strategic instrumentation.

Systematic Debugging Framework

Implements a rigorous four-phase methodology to identify root causes and ensure reliable software fixes before proposing code changes.

Technical Code Review Reception

Processes code review feedback with technical rigor and verification instead of performative agreement.

Systematic Plan Execution

Executes complex implementation plans in controlled batches with systematic review checkpoints and mandatory verification steps.

Defense-in-Depth Validation

Implements multi-layered validation patterns to prevent deep execution failures and make software bugs structurally impossible.

AI Code Review Dispatcher

Dispatches a specialized code-reviewer subagent to identify implementation issues and verify requirements before code is merged.

Verification Before Completion

Enforces a strict evidence-based workflow that requires running verification commands before claiming any task is finished.

Skill Sharing Workflow

Guides the contribution of locally developed Claude Code skills to upstream repositories through standardized Git and PR workflows.

Skill Authoring TDD

Applies Test-Driven Development principles to documentation to ensure Claude skills are bulletproof through subagent pressure testing.

Skill Contribution Workflow

Streamlines the process of contributing custom Claude skills to upstream repositories through standardized Git and GitHub CLI workflows.

Defense-in-Depth Validation

Implements a multi-layered validation strategy to make software bugs structurally impossible by verifying data at every system boundary.

Metabase Documentation Reviewer

Reviews documentation changes for compliance with the Metabase writing style guide and general readability standards.

Benchling R&D Integration

Connects Claude to the Benchling life sciences platform to automate R&D data management, registry updates, and laboratory workflows.

ClinicalTrials.gov Explorer

Accesses and queries the ClinicalTrials.gov API v2 to retrieve comprehensive data on global clinical studies.

Verification & Quality Assurance

Maintains codebase integrity through real-time truth scoring, automated security checks, and intelligent rollback mechanisms.

Technical Code Review Response

Ensures technical rigor and objective verification when processing code review feedback by prioritizing correctness over social agreement.

APL - Autonomous Phased Looper

Automates the entire digital product lifecycle from design and coding to deployment and performance monitoring.

Project Workflow Automator

Automates the entire project lifecycle from initial idea validation and planning to session management and secure GitHub releases.

Google Workspace Integration

Streamlines the development of robust integrations with Google Workspace APIs using standardized authentication patterns and rate-limit handling.

Testing Anti-Patterns

Identifies and prevents common software testing pitfalls to ensure test suites verify real behavior rather than mock implementation.

AI Code Review Orchestrator

Automates the dispatching of specialized AI subagents to perform deep code reviews against requirements and git history.

Strict Test-Driven Development (TDD)

Enforces a rigorous Red-Green-Refactor workflow by requiring failing tests before any production code is written.

Design Thinking Pipeline

Transforms rough product ideas into production-ready UI specifications using a structured 9-pass UX analysis and design thinking framework.

Dispatching Parallel Agents

Parallelizes debugging and bug fixes by dispatching multiple Claude agents to investigate independent system failures concurrently.

Condition-Based Waiting

Eliminates flaky tests and race conditions by replacing arbitrary timeouts with smart, asynchronous condition polling.

Subagent-Driven Development

Orchestrates complex coding plans by dispatching fresh subagents for individual tasks with automated code review gates.

Skill Testing with Subagents

Applies Test-Driven Development (TDD) principles to AI process documentation to ensure skills resist rationalization under pressure.

Condition-Based Waiting

Eliminates flaky tests and race conditions by replacing arbitrary timeouts with intelligent state polling.

Subagent-Driven Development

Executes complex implementation plans by dispatching fresh subagents for individual tasks with integrated code review cycles.

Skill Testing with Subagents

Applies Test-Driven Development (TDD) principles to AI skills to ensure they remain effective under pressure and resist rationalization.