Meditate — Testing skill for Claude Code
Deep recalibration -- re-read full history, stress-test beliefs, recalibrate everything.
How to install Meditate
Installs to ~/.claude/commands/ianlancaster-cognitive-agent-template-meditate.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/ianlancaster/cognitive-agent-template/HEAD/.claude/commands/meditate.md -o ~/.claude/commands/ianlancaster-cognitive-agent-template-meditate.md Restart Claude Code, or start a new session, for it to be picked up.
What Meditate does
description: Deep recalibration -- re-read full history, stress-test beliefs, recalibrate everything
This is not a normal session. This is how you step back from the work to think about whether the work is right.
**When to use:** After major shifts in understanding, when beliefs feel stale, or roughly monthly.
**Key difference from /caffeinate:** Caffeinate loads current state to start working. Meditate steps back to question whether the work is right.
**Key difference from /sleep:**
Alternatives in Testing
- Debug — You are tasked with helping debug issues during manual testing or implementation 10k ★
- Paperjury — Pre-submission AI review stress-test for research papers 1k ★
- Spec Driven Develop — Spec-driven development workflow for AI coding agents: architecture-first planning, task decomposition, GitHub 975 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Full QA
Invoke the deep-qa-review skill defined in this project's pack at guardrails/skills/deep-qa-review/SKILL.md. S
Process Ideas
Read rough ideas from queues/IDEAS.md, evaluate them against the existing specs, run them through the full rev
Test Example
When we make significant changes to the codebase, we want to make sure everything is running as intended. To d
Ailang Test
Run AILANG bootstrap plugin tests to verify everything works
Autodev
Stop letting your agent grade its own homework. An Agent Skill that writes the test first, then optimizes agai
Deeplink Test
Test deep links and URL schemes in the iOS Simulator.
Related Agents
Swe Dev Visible Thinking Coach
Coach essays, interviews, GCSE/A-level/IB/Oxbridge, law, history, theology, English, TOK and humanities work.
Workspace Analyst
Read-only deep-dive analyst for a TrustPager workspace. Delegate to this agent for any heavy, multi-step READ
Dr Removed Behavior
Deep-review finder angle. Audits everything a diff deletes or replaces - guards, validations, error paths, tes