Menü
Print available rounds skills, project directory layout, and a brief overview of what rounds does
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Basierend auf der SOC-Berufsklassifikation
| name | rounds-help |
| description | Print available rounds skills, project directory layout, and a brief overview of what rounds does |
| user_invocable | true |
| args | [] |
Print a quick-reference guide for working with rounds inside the container.
Output the following text exactly, with no additional commentary:
ROUNDS — Autonomous Error Diagnosis Agent
==========================================
Rounds is a lightweight daemon that watches your OpenTelemetry data, fingerprints
failure patterns, and uses LLM-powered analysis to diagnose root causes in your
codebase. It makes periodic passes over your telemetry — polling for errors,
tracing them through your system, recognizing recurring patterns, and building up
a persistent knowledge base of failure signatures and diagnoses. Think of it as a
nurse making rounds on your running software.
SKILLS AVAILABLE IN THE ROUNDS CONTEXT
---------------------------------------
/rounds-help — show this message
/rounds-investigate TRACE_ID — investigate a distributed trace
/rounds-list [STATUS] — list error signatures
/rounds-details SIGNATURE_ID — full signature details
/rounds-reinvestigate SIG_ID — re-run LLM diagnosis
/rounds-mute SIG_ID [REASON] — mute a signature
/rounds-resolve SIG_ID — mark a signature resolved
/rounds-daemon — start the polling daemon
/rounds-test — run pytest
/rounds-check — mypy + ruff
/rounds-explore [QUERY] — query telemetry: search logs, spans, traces
/rounds-assess [QUERY] — assess transaction types: instrumentation, code quality, usage, skill gaps
DIRECTORIES (inside container)
-------------------------------
/workspace/rounds — rounds source code (this project)
/workspace/target — target codebase being monitored and diagnosed
Assess telemetry data — identifies distinct transaction types from an explore query and launches sub-agents to analyze each for instrumentation quality, code efficiency, usage correctness, and skill improvement opportunities
Exploratory querying of telemetry data — search logs by keyword/metadata, search spans by metadata, and build full transaction trees from trace IDs using the rounds adapter interfaces
Get full details for a single rounds error signature including diagnosis, recent events, and related signatures
Investigate a distributed trace by ID — fetches the full trace, reads source files, and explains the end-to-end code flow
List error signatures in the rounds database, optionally filtered by status
Mute a rounds error signature to suppress further notifications