agentleFS
Sign inStart free
thebharathkumarthebharathkumar/agent-flight-recorder/skills/trace-triage/SKILL.md

trace-triage

Skill0 starsChanged 4 months agoMITView on GitHub

Cluster and rank agent failures from OpenTelemetry trace exports

  • Installs packages

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. magickkdd/MiniClaudeCode★ 1same name
    2. telerik/observability-skills★ 1same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository3 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Before and after: triage compare before.ndjson after.ndjson to verify a fix actually moved the numbers.

    line 40

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Trace Triage

Pipes OTLP span exports into agent-triage (PyPI) and surfaces the top failure clusters, ranked by frequency and severity, with recovery rates and suggested next actions.

Procedure

  1. Install the scorer in the target environment: pip install agent-triage.
  2. Locate the span source, in order of preference:
    • captures/otlp.json written by the otel-agent-tracing skill (either its docker collector or its OTLP JSON file exporter),
    • any OTLP JSON export the user points at,
    • native triage NDJSON, which skips step 3.
  3. Convert OTLP to triage events: python scripts/otlp_to_triage.py <otlp.json> -o events.ndjson. The DEFAULT mapping understands everything the otel-agent-tracing skill emits, including MCP semconv (mcp.method.name, span names shaped {method} {target}), so no --map is needed for pack-emitted spans. For foreign span layouts pass --map mapping.toml; the format and the full default mapping live in references/attribute-mapping.md. The converter prints mapped and skipped counts to stderr. If it warns that most failures are unclassified, relay that to the user: triage scoring degrades without failure labels.
  4. Score and report: triage report events.ndjson --top 5.
  5. Present the clusters to the user: rank, agent, tool, classification, final score, recovery rate, and the suggested action line. Offer to drill into the spans behind the top cluster.
  6. Optional follow-ups:
    • Before and after: triage compare before.ndjson after.ndjson to verify a fix actually moved the numbers.
    • Live dashboard: pip install "agent-triage[server]", run triage-serve, point agents or a collector at POST /otlp/v1/traces.

Files

  • scripts/otlp_to_triage.py: stdlib-only OTLP JSON to NDJSON converter with attribute mapping, turn synthesis, and classification derivation.
  • references/attribute-mapping.md: default mapping and --map format.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free