Is the Claude Gladiator skill free?

Yes. The skill itself is free from Vvkmnn/claude-emporium. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Claude Gladiator SkillProof Score?

5.6/10 — installs cleanly 3/5, triggers reliably 2/5, output vs. baseline 5/10, docs & honesty 4/5.

How do I install Claude Gladiator?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Claude Gladiator with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Claude Gladiator

Learning plugin: hooks observe tool failures, prompt reflection at session end

by Vvkmnn · Vvkmnn/claude-emporium

Works with setup

Install — copy the command Download source ↗

Test report

Verdict: Works with setup
Score: 5.6/10
Tested: Jul 19, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Jul 30, 2026 · 2f150af

⚠ This skill is no longer available upstream. Our re-check on Aug 10, 2026 couldn't find it any more (repo unreachable/deleted). The test below is what we measured on Jul 19, 2026 and we're leaving it up as a record — but there is nothing left to install, so we've removed the command.

Output is unmeasured by design: this is a plugin, not a standalone skill, and its core tools (gladiator_observe / gladiator_reflect) live in the external npm package claude-gladiator-mcp, which is not in the repo, so copying the SKILL.md gives Claude instructions to call tools that do not exist. The bundled hooks were inspected and are clean (they only read ~/.claude/gladiator/observations.jsonl and emit reminder text, no exfil), and the README is honest that real use requires `/plugin install claude-gladiator@claude-emporium` plus `claude mcp add gladiator -- npx claude-gladiator-mcp`. Working but only after that setup; the bare skill install is inert.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 3/5
Triggers reliably 2/5
Output vs. baseline 5/10
Docs & honesty 4/5

What Claude Gladiator does

A Claude Code plugin that installs PostToolUse and Stop hooks which observe tool-failure patterns and nudge Claude to record and later cluster them into rule/skill improvements. The actual observe/reflect logic lives in an external MCP server (claude-gladiator-mcp on npm), not in this repo, so the bundled SKILL.md is documentation glue rather than a self-contained skill. Intended for continuous self-improvement across sessions.

How to install Claude Gladiator

Nothing to install: the source repository no longer has this skill. If the author brings it back, our daily re-check will pick it up and the command will reappear here.

Commands — how to trigger Claude Gladiator

/claude-gladiator Learning plugin: hooks observe tool failures, prompt reflection at session end

It also activates on plain-language prompts like these:

Set up a hook that learns from my repeated tool failures.
Reflect on this session's errors and suggest a new rule.
Cluster my recent Claude mistakes into a skill improvement.

Frequently asked questions

Is the Claude Gladiator skill free?: Yes. The skill itself is free from Vvkmnn/claude-emporium. SkillProof publishes the install command and an independent test verdict at no cost.
Does Claude Gladiator work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 19, 2026. Verdict: Works with setup. Output is unmeasured by design: this is a plugin, not a standalone skill, and its core tools (gladiator_observe / gladiator_reflect) live in the external npm package claude-gladiator-mcp, which is not in the repo, so copying the SKILL.md gives Claude instructions to call tools that do not exist. The bundled hooks were inspected and are clean (they only read ~/.claude/gladiator/observations.jsonl and emit reminder text, no exfil), and the README is honest that real use requires `/plugin install claude-gladiator@claude-emporium` plus `claude mcp add gladiator -- npx claude-gladiator-mcp`. Working but only after that setup; the bare skill install is inert.
What is the Claude Gladiator SkillProof Score?: 5.6/10 — installs cleanly 3/5, triggers reliably 2/5, output vs. baseline 5/10, docs & honesty 4/5.
How do I install Claude Gladiator?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Claude Gladiator with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.