Outlook LLM Tests — Testing skill for Claude Code
Run make crud-test from the repository root via the Bash tool.
How to install Outlook LLM Tests
Installs to ~/.claude/commands/desek-outlook-local-mcp-outlook-llm-tests.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/desek/outlook-local-mcp/HEAD/.claude/commands/outlook-llm-tests.md -o ~/.claude/commands/desek-outlook-local-mcp-outlook-llm-tests.md Restart Claude Code, or start a new session, for it to be picked up.
What Outlook LLM Tests does
Run `make crud-test` from the repository root via the Bash tool. This is the **primary, canonical** way to execute the MCP CRUD lifecycle test — do not reinterpret the prompt at `docs/prompts/mcp-tool-crud-test.md` directly. The target wraps `scripts/crud-test.sh`.
The script:
- Spawns a headless
claude -psubprocess against the locally configured outlook-local-mcp server. - Captures
stream-jsonevents todocs/bench/runs/{timestamp}/stream.jsonland wall-clock totime.txt. - Appends one
Alternatives in Testing
- Test Repl — Run a REPL test scenario against the claude-in-mobile REPL plugin (python/node/bash/...) 356 ★
- Test Docs Creator — Generate test documentation 210 ★
- Production Grade — Production Grade — route any build, feature, review, test, harden, ship, or docs request through the 14-agent 175 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Prompt Test
Test LLM prompts against sample inputs. Shows outputs, checks for regressions when prompts change, and compare
Grimoire
Prompt engineering toolkit: version-controlled prompts, AI agent skills manager, sandboxed Claude sessions in
Phishing Triage Skill
A reusable SKILL.md that teaches an open-source LLM agent to triage a user-reported email the way a careful SO
Electron Stagewright
Drive Electron apps the way Playwright drives browsers — MCP server for AI agents.
Ihudak Claude Plugins
Claude Code plugins for the full feature lifecycle: idea → Value Increment → ARD → spec → design → Epics → imp
AI Engineering Framework
Spec-first AI-engineering framework for Claude Code: lifecycle skills, reviewer subagents, and CI-enforced qua
Related Agents
Claude Code System Prompts
by Piebald AI - All parts of Claude Code's system prompt, including builtin tool descriptions, sub agent promp
AI Prompt Architect
Designs and versions LLM system prompts for ai-system / agent-product archetypes. Outputs docs/decisions/ADR-{
LLM Specialist
Prompt engineering specialist and LLM expert. Use when crafting prompts, optimizing AI responses, or implement