← Browse
ai-criteria
phantomMillie ★ 0
This Claude Code plugin logs repeated AI mistakes as 3-field cases (gave / actual / why), rolls them up weekly to identify recurring root causes, and promotes only verified patterns into falsifiable input/judgment criteria for future sessions. It operates locally with zero external dependencies, using Python 3.8+ and shell execution to manage a persistent criteria database that retires rules when counter-examples prove them wrong.
Install
> /plugin marketplace add phantomMillie/ai-criteria
> /plugin install ai-criteria
What it's made of
5 skills · 2 hooks
- Commands
- 0
- Agents
- 0
- Skills
- 5
- MCP servers
- 0
- Hooks
- 2 · SessionStart, UserPromptSubmit
What it needs & plugs into
- API keys
- none
- Paid services
- none detected
- External tools
python3- Talks to
- nothing external detected
Analyzed . Facts extracted from the plugin's files. Prose generated by claude-haiku-4-5-20251001.
Is this your plugin?
Claim it to keep the card accurate and enter the weekly contest. Requires signing in as the GitHub owner (phantomMillie).