From claude-gladiator
Observes tool failures via hooks, collects observations, and prompts reflection to evolve rules, hooks, and skills. Batch review command; integrates historian/oracle for context.
How 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 at session end to evolve rules, hooks, and skills.
Continuous learning. Observes tool failures and prompts reflection at session end to evolve rules, hooks, and skills.
| Hook | When | Action |
|---|---|---|
| PostToolUse(Bash|Edit|Write) | After tool failure | Observes the error pattern (silent on success) |
| Stop | Session ending | Prompts reflection if unprocessed observations exist |
| Command | Description |
|---|---|
/review-gladiator [topic] | Batch learn from accumulated observations and session history |
Tool failures trigger observation automatically:
gladiator_observe(
summary: "<what failed and how it was fixed>",
context: {error, tool, before, after},
tags: ["error", "<tool_name>"]
)
gladiator_reflect() — cluster observations into recommendationssearch_conversations("project or topic") — related past workget_error_solutions("specific error") — for error clustersfind_tool_patterns("tool name") — for tool workflow clustersgladiator_reflect() — cluster observationssearch("cluster tag") — check if best-in-class solution already existslist_recent_sessions() to get session refsgladiator_observe(source: "conversation", session_ref: <ref>) for relevant sessionsgladiator_reflect() to cluster all observations| Sibling | Value | How |
|---|---|---|
| Historian | Past solutions enrich reflection | get_error_solutions(), search_conversations(), find_tool_patterns() |
| Oracle | Existing tools found before creating new | Search oracle for best-in-class solutions during reflection |
| Praetorian | n/a | Gladiator has its own persistence |
| Vigil | n/a | Different concerns (files vs patterns) |
| 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
npx claudepluginhub vvkmnn/claude-emporium --plugin claude-gladiatorDetects learning opportunities from user corrections, repeated instructions, tool failures, and tone escalation. Extracts improvement candidates and applies them to Claude's configuration after user approval via `/coach` commands.
Extracts reusable patterns from Claude Code sessions and saves them as learned skills. Useful for curating personal knowledge from past sessions.
Analyzes session history via ccrecall.db or in-context to extract learnings from corrections, discoveries, and failures, then proposes persistent skill updates. Invoke /reflect post-session.