selcukyucel

Run AI-specific inversion analysis on a requirement before implementation. Dispatches the `ai-invert-analyst` agent on a separate thread. Use before complex or high-stakes AI tasks that touch prompts, models, RAG, or AI-powered outputs.

Autonomously improve any skill or agent prompt via measure-change-test hill-climbing. Dispatches the `auto-improver` agent on a separate thread. Use when a skill gives inconsistent results, when asked to "improve/optimize/autoresearch" a skill, or when output quality needs iterative tightening.

Capture a reproducible AI performance baseline before changes. Dispatches the `baseline-capturer` agent on a separate thread. Use before any change to a client-facing AI output. Triggered automatically by the Q3 gate in CLAUDE.md.

Generate AI tool configuration for an existing project. Explores the codebase and produces context files, path-scoped pattern rules, landmine rules, and agents for Claude Code and VS Code Copilot. Run once per project.

Inject managed sections into existing CLAUDE.md and AGENTS.md after a North Starr GenAI plugin update without re-bootstrapping. Preserves all project-specific content.

Generate executable pytest test files for AI outputs. Produces assertion-based tests for deterministic AI components (classification, extraction, routing, structured output) that run in CI/CD. Complements /eval-suite which produces statistical evaluation datasets for non-deterministic outputs.

Pre-deployment verification checklist for AI automations. Verifies evals pass, baselines show no regressions, guardrails are tested, costs are reviewed, monitoring is configured, and rollback plan is documented.

Deep structured inversion analysis on a requirement before implementation. Identifies risks, edge cases, failure modes, and convention violations. Use before complex or high-stakes tasks.

Decompose a PRD into prioritized, dependency-mapped epics and user stories. Accepts pasted text, file path, or PDF.

Inject managed sections into existing CLAUDE.md and AGENTS.md after a plugin update without re-bootstrapping. Preserves all project-specific content.

Generate AI tool configuration for an existing project. Explores the codebase and produces context files, path-scoped pattern rules, landmine rules, and agents for Claude Code and VS Code Copilot. Run once per project.

Autonomously improve any skill prompt using a measure-change-test loop inspired by Karpathy's autoresearch. Runs the skill repeatedly, scores output against a yes/no checklist, makes one small change per round, keeps improvements, reverts regressions. Use when the user asks to "improve a skill", "optimize a skill", "autoimprove", "run autoresearch on a skill", or similar requests about iteratively improving skill quality.

Analyze code modules and files for refactoring opportunities, code smells, and architectural pattern violations in any language or framework. Use this skill when the user asks to "analyze code smells", "find refactoring opportunities", "check for code quality issues", or "review architecture" for a specific module or file.

Generate clear, descriptive git commit messages by analyzing staged changes. Use this skill when the user asks to "generate a commit message", "write a commit message", "create a commit message", or similar requests related to git commits.

Generate a pull request description by analyzing git changes against the target branch and filling in the project's PR template. Use this skill when the user asks to "generate PR description", "write PR description", "create PR body", "fill PR template", "prepare pull request", or similar requests related to pull request documentation.

Deep structured inversion analysis on a requirement before implementation. Identifies risks, edge cases, failure modes, and convention violations. Use before complex or high-stakes tasks.