Stats
Actions
Tags
Help us improve
Share bugs, ideas, or general feedback.
From claude-gladiator
Continuous learning — INVOKE after sessions with many errors or corrections to record patterns and improve rules, hooks, and skills
npx claudepluginhub vvkmnn/claude-emporium-beta --plugin claude-gladiatorHow this skill is triggered — by the user, by Claude, or both
Slash command
/claude-gladiator:claude-gladiatorThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Continuous learning. Observes tool failures and prompts reflection to evolve rules, hooks, and skills.
Observes tool failures via hooks, collects observations, and prompts reflection to evolve rules, hooks, and skills. Batch review command; integrates historian/oracle for context.
Learns from user corrections, tool failures, and repeated instructions to generate improvement proposals that require explicit approval before modifying CLAUDE.md.
Logs user corrections like 'wrong' or 'no' as mistakes, updates CLAUDE.md rules, and auto-generates skills from repeated patterns after 3+ occurrences. Triggers on feedback or repetitions.
Share bugs, ideas, or general feedback.
Continuous learning. Observes tool failures and prompts reflection to evolve rules, hooks, and skills.
| Hook | When | Action |
|---|---|---|
| PostToolUseFailure(Bash/Edit) | After tool failure | Nudges you to call gladiator_observe() — you must call it, not automatic |
| Stop | Session ending | Prompts gladiator_reflect() if >= 10 unprocessed observations |
| Command | Description |
|---|---|
/review-gladiator [topic] | Batch learn from accumulated observations and session history |
After a tool failure, the hook nudges you. YOU must call gladiator_observe() — it is NOT automatic. After fixing an error, record what worked:
gladiator_observe(
summary: "<what failed and how it was fixed>",
context: {error, tool, before, after},
tags: ["error", "<tool_name>"]
)
gladiator_reflect() — cluster observations into recommendationsgladiator_reflect() to cluster all observations| Situation | Call |
|---|---|
| Tool failure (auto) | gladiator_observe(summary, context={error, tool, before, after}, tags=["error", tool]) |
| User correction | gladiator_observe(summary, context={before, after}, tags=["correction"]) |
| Convention found | gladiator_observe(summary, tags=["convention", "domain"]) |
| Decision made | gladiator_observe(summary, tags=["architecture", "decision"]) |
claude mcp add gladiator -- npx claude-gladiator-mcp