New engineering work often starts without clear scope or acceptance criteria. This skill gathers inputs and produces Conductor specs, plans, metadata, and track links.

Conductor repositories can accumulate stale tracks, archived work, and inconsistent metadata. This skill guides Claude, Codex, and Claude Code through track lifecycle operations.

Conductor tracks can drift when tasks, tests, and metadata are updated by hand. This skill guides Claude, Codex, or Claude Code through TDD implementation, checkpoints, commits, and progress updates.

Planning coding work can become vague and hard to execute. This skill turns requests into scoped, ordered checklists with validation steps.

Modern vision projects require choices across detection, segmentation, VLMs, depth, and deployment. This skill guides architecture, model selection, optimization, and edge deployment for practical computer vision systems.

Computer use agents need safe designs before they control screens, keyboards, and files. This skill provides implementation patterns, sandbox guidance, and Claude tool examples for safer GUI automation.

Pull requests often lack context, test evidence, and reviewer guidance. This skill creates structured PR material that helps reviewers act faster.

Large code changes can hide quality, security, performance, and testing risks. This skill coordinates a phased review workflow that turns those risks into prioritized action.

Competitive analysis often becomes scattered across competitor notes, pricing tables, and positioning ideas. This skill guides Claude, Codex, and Claude Code through structured frameworks that turn market evidence into clear strategy.

Code reviews can miss regressions, risky refactors, and release notes. This skill guides Codex, Claude, and Claude Code through review and CHANGELOG workflows.

Code reviews can miss important risks or become hard to act on. This skill gives Claude, Codex, and Claude Code a structured review method with clear severity, rationale, and follow-up questions.

Code reviews can miss bugs, security issues, and test gaps when reviewers work from memory. This skill provides a structured checklist and comment templates for consistent reviews.

Code reviews can miss security, performance, and maintainability issues when changes move quickly. This skill provides structured AI review workflows, scanner guidance, and comment formats for pull requests.

Technical debt slows delivery, raises defect rates, and makes planning difficult. This skill turns debt signals into measured remediation plans with ROI.

Complex code becomes hard to change and risky to extend. This skill guides Claude, Codex, and Claude Code through focused refactoring with tests and reviewable steps.

Long refactors lose important decisions when work moves across sessions or agents. This skill guides semantic context retrieval, ranking, rehydration, and validation.

Codebases often lack current API, architecture, and user documentation. This skill guides Claude, Codex, and Claude Code to extract facts from source files and produce maintainable docs.

Complex code is hard to teach, review, and onboard. This skill turns code into clear walkthroughs, diagrams, examples, and learning paths.

Technical debt slows delivery, raises defect rates, and makes modernization harder. This skill guides Claude, Codex, and Claude Code through measurable cleanup planning.

Legacy code slows feature work and raises maintenance risk. This skill guides structured refactoring, clean code analysis, tests, and reviewable cleanup steps.