원클릭으로
opentraces
Search and use local OpenTraces agent traces, inspect capture status, and build datasets from captured Pi/Claude/Codex sessions.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Search and use local OpenTraces agent traces, inspect capture status, and build datasets from captured Pi/Claude/Codex sessions.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Share agent traces to open datasets on HuggingFace Hub. Use this skill when the user mentions OpenTraces, trace capture, Trace Trails, workflow-built datasets, dataset review, or publishing reviewed dataset rows.
Share agent traces to open datasets on HuggingFace Hub. Use this skill when the user mentions OpenTraces, trace capture, Trace Trails, workflow-built datasets, dataset review, or publishing reviewed dataset rows.
Project already-captured traces into scored-rollout rows for the SkillOpt optimizer.
Per-commit trace lineage rows for a branch context, deterministic.
Derive compact eval rows from command-attributed trace trajectories.
Land every site-related fix on main, deploy opentraces.ai to Vercel production, and verify it works across all pages (desktop + mobile) and the email-capture flow, fixing and re-deploying until green. Runs as a goal: land -> deploy -> verify -> triage -> repeat until safe. Use when the user says "deploy site", "deploy to vercel", "push site", "ship the site", "deploy-site", or "land and verify the site". For a full coordinated release that also bumps the version and publishes the Python packages, use /release-pack instead.
| name | opentraces |
| description | Search and use local OpenTraces agent traces, inspect capture status, and build datasets from captured Pi/Claude/Codex sessions. |
Use OpenTraces when the user asks about prior agent work, captured traces, bucket search, Trace Trails, Context Tree evidence, capsules, standups, or workflow-built datasets.
ot_capture_status — check package/CLI/project setup. Use this before
assuming capture is working.ot_search — search local bucket traces for relevant prior work.ot_trace — resolve a trace id or ot:// reference into compact evidence.ot_standup — query recent traces as standup input (a bounded recent-work query you then summarize).ot_capsule — capsule helper for previewing or explicitly exporting trace packets.ot_dataset — list/status/dry-run workflow-built datasets; creation requires an explicit user request.OpenTraces tool calls are retrieval-first and recursion tagged with
OPENTRACES_PI_EXTENSION_INTERNAL=1. Treat mutating actions such as dataset
creation or capsule export as user-approved follow-ups, not background work.
Run /ot-setup for minimal local capture readiness. Under global tracking (the
default) capture is automatic once the opentraces CLI is present, so the main
thing /ot-setup checks is that the CLI is installed; opentraces init --agent pi can still enroll a repo explicitly. Terminal/auth-heavy follow-ups are
reported as needs_terminal, for example:
opentraces setup git
opentraces setup auth
opentraces setup bucket
Raw provider bodies are default-off and local/security-gated when explicitly enabled. Normal Pi work must continue even if OpenTraces capture fails.