LLM & Agents

Information about running tests, test coverage, and known testing issues in the Rails application. Use when the user asks about testing procedures, encounters test failures, wants to know about coverage, or needs to troubleshoot intermittent system test issues.

TEST PHASE: Testing strategies, patterns, and quality assurance workflows.Provides test strategy frameworks, coverage guidelines, unit/integration/e2e patterns,performance testing approaches, and security testing checklists.Use when: designing test strategies, writing tests, evaluating coverage,planning QA workflows, implementing test automation.

How to approach tests, types, lints, and coverage

Implement code quality ratchets to prevent proliferation of deprecated patterns. Use when (1) migrating away from legacy code patterns, (2) enforcing gradual codebase improvements, (3) preventing copy-paste proliferation of deprecated practices, or (4) setting up pre-commit hooks to count and limit specific code patterns. A ratchet fails if pattern count exceeds OR falls below expected—ensuring patterns never increase and prompting updates when they decrease.

Collect and synthesize opinions from multiple AI agents. Use when users say "summon the council", "ask other AIs", or want multiple AI perspectives on a question.

This skill should be used when running CI checks iteratively and fixing failures. Use when executing make targets (fast-ci, all-ci, ci), iterating on lint/format/type/test errors, or needing the devrun agent pattern for pytest/ty/ruff/prettier/make/gt commands.

Transform clarified user requests into structured delegation prompts optimized for specialist agents (cto-architect, strategic-cto-mentor, cv-ml-architect). Use after clarification is complete, before routing to specialist agents. Ensures agents receive complete context for effective work.

This skill should be used when inspecting, analyzing, or querying Claude Code session logs. Use when users ask about session history, want to find sessions, analyze context usage, extract tool call patterns, debug agent execution, or understand what happened in previous sessions. Essential for understanding Claude Code's ~/.claude/projects/ structure, JSONL session format, and the erk extraction pipeline.

Use this skill when you need to deploy HyperShift clusters on bare metal, edge environments, or disconnected infrastructures using pre-provisioned agents

Analyzes LVMS must-gather data to diagnose storage issues

This skill should be used when creating a Claude Code slash command. Use when users ask to "create a command", "make a slash command", "add a command", or want to document a workflow as a reusable command. Essential for creating optimized, agent-executable slash commands with proper structure and best practices.

Analyze recent conversation to identify improvements for CLAUDE.md memory files. Trigger when user says "reflect on this session", "reflect on this conversation", "reflect on this code", or "improve CLAUDE.md by reflecting on this session". The verb "reflect" combined with a session/conversation/code subject is the key trigger.

Enable AI agents to introspect and control Castella UIs via MCP. Create MCP servers, expose UI resources, handle MCP tools, and use semantic IDs.

Deduplicate and consolidate CLAUDE.md memory files. Trigger when user says "condense my CLAUDE.md files", "deduplicate CLAUDE.md", "clean up my memory files", or "consolidate my instructions". Removes redundancy within files and across the file hierarchy.

Dashboard pattern for tracking doc coverage across product versions, locales, and channels.

Get Gemini's code review of git changes after Claude makes edits. Trigger when user wants a second opinion on code changes ("have Gemini review my changes", "get code review from Gemini", "review this diff"), or as a final check before committing.

Add or update automated tests for a change (bugfix, feature, refactor) using the repository’s testing rules in `AGENTS.md`. Use TDD where applicable; derive scenarios from docs/Features/* and ADR invariants; prefer stable integration/API/UI tests, run build before tests, and verify meaningful assertions for happy/negative/edge cases.

Use to inspect qualification coverage across Metrics, Economic buyer, Decision criteria, Decision process, Implications, Champion.

Get Codex's code review of git changes after Claude makes edits. Trigger when user wants a second opinion on code changes ("have Codex review my changes", "get code review from Codex", "review this diff with Codex"), or as a final check before committing.

Use when defining ABM tiers, scoring logic, and coverage rules.