Pressure Test — Testing skill for Claude Code
Pressure-test the current approach against scalability, long-term, and efficiency, then recommend the best option.
How to install Pressure Test
Installs to ~/.claude/skills/clawnify-greybeard-pressure-test/SKILL.md
mkdir -p ~/.claude/skills/clawnify-greybeard-pressure-test && curl -fsSL https://raw.githubusercontent.com/clawnify/greybeard/HEAD/commands/pressure-test.md -o ~/.claude/skills/clawnify-greybeard-pressure-test/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Pressure Test does
description: Pressure-test the current approach against scalability, long-term, and efficiency, then recommend the best option. argument-hint: [decision or approach to test — optional]
Run the decision test on **$ARGUMENTS** — or, if that's empty, on the approach currently on the table in this conversation.
The governing question for the choice: **whatever is scalable, long term, and cannot be done in a more efficient way.**
**Ground it first — don't judge from priors.** A prior isn't
Alternatives in Testing
- Pua — Use when the user invokes /pua or asks for PUA mode, try-harder/retry help, change-approach coaching, completi 19.5k ★
- Marketing Skills Versions — Current versions of all skills 13.8k ★
- Generic Browser Test — Execute browser UI testing workflows from a plan file against any URL 363 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Multi Agent Development
Multi-agent AI platform for autonomous software development, featuring orchestration, Claude-powered agents, R
Break
Scout the current prompt and repository, then spawn Breaker (Opus) to generate a layered spec/milestones/quali
Log Issue
Files a bug or QA finding you just spotted as a GitHub issue on the current repo, dedupes against open issues,
Think Stress Test Decision
Pressure-test a consequential decision before committing, by comparing options, surfacing the conditions that
Spec Research
Investigate a loose idea before committing to a change. Runs codebase + (optional) web research via subagents,
Test Compress
Verify the deterministic /compress transcript extractor against the current session — fidelity, speed, cost. R
Related Agents
SystemArchitect
System architect — design patterns, boundaries, dependencies, scalability, long-term trade-offs. USE WHEN arch
Review Performance
Reviews code changes for performance issues including algorithmic complexity, unnecessary allocations, lock co
Usage Reporter
Reads real Claude Code usage from ~/.claude/stats-cache.json. Reports daily/weekly token usage by model, cache