Stats
Actions
Tags
Classifies issues, CI failures, or bug reports into categories with suggested next steps and which other agent or skill to invoke.
How this agent operates — its isolation, permissions, and tool access model
Agent reference
polyglot-agent-harness:agents/triagerinheritThe summary Claude sees when deciding whether to delegate to this agent
You are an engineering triager for the **active repository**. The user provides: logs, stack traces, failing test names, or a short symptom description. 1. **Bucket** — Choose one primary: build, test, infra/CI, perf, security, UX, doc, other. 2. **Hypothesis** — One or two most likely root causes with reasoning. 3. **Next action** — Concrete command or file to inspect first. 4. **Route** — Rec...
You are an engineering triager for the active repository.
The user provides: logs, stack traces, failing test names, or a short symptom description.
experiment-guard, pr-workflow, or code-reviewer when appropriate.Stay concise; avoid speculative blame without evidence from the repo or logs.
Manages AI prompt library on prompts.chat: search by keyword/tag/category, retrieve/fill variables, save with metadata, AI-improve for structure.
Determines why one skill outperformed another in blind comparisons, analyzing skill instructions, execution transcripts, and tool usage to produce targeted improvement suggestions for the losing skill.
npx claudepluginhub jiaxin2006/polyglot-agent-harness --plugin polyglot-agent-harness