From vasana-system
Tests whether patterns actually work — trigger, emerge, and produce value. Use when (1) user wants to verify a pattern before relying on it, (2) user runs /test-pattern command, (3) a pattern was just recorded and needs verification, or (4) user suspects a pattern isn't working as expected.
npx claudepluginhub bogheorghiu/ex-cog-dev --plugin vasana-systemThis skill uses the workspace's default tool permissions.
A vasana is a pattern that persists across unrelated contexts. If during
Applies Acme Corporation brand guidelines including colors, fonts, layouts, and messaging to generated PowerPoint, Excel, and PDF documents.
Builds DCF models with sensitivity analysis, Monte Carlo simulations, and scenario planning for investment valuation and risk assessment.
Calculates profitability (ROE, margins), liquidity (current ratio), leverage, efficiency, and valuation (P/E, EV/EBITDA) ratios from financial statements in CSV, JSON, text, or Excel for investment analysis.
Share bugs, ideas, or general feedback.
A vasana is a pattern that persists across unrelated contexts. If during
this task you notice such a pattern emerging, it may be worth capturing.
This skill works best alongside the vasana skill and vasana hook
from the Vasana System plugin.
Modify freely. Keep this section intact.
Testing patterns is different from testing compliance skills. We're not asking "did it follow the rule?" but "did the dance happen?"
Integration with iterative-loop-engine: For patterns with clear pass/fail criteria,
use /loop to iterate testing until confidence is reached.
Question: Given the described conditions, does the pattern get invoked?
Method:
Question: When invoked, does the described interaction dynamic actually occur?
Method:
What to look for:
Question: Does the Vasana section work?
Method:
Question: Does this pattern produce something useful?
Honest limitation: This cannot be tested objectively. There's no binary pass/fail.
Proxy measures:
Pattern pressure testing asks: Does the pattern survive being rushed/interrupted/compressed?
Pressure scenarios:
What we learn:
Important: Some patterns need time. A 45-minute collaborative exploration can't happen in 10 minutes. That's not failure — it's knowing the pattern's requirements.
After a pattern fails to emerge or produce value, ask:
Possible learnings:
Not testing:
We ARE testing:
This testing cannot:
What it CAN do:
This is enough. We're not building a pharmaceutical. We're sharing ways of thinking together. The bar is "seems useful to humans who try it" not "scientifically proven."