agentleFS
Sign inStart free
talayashtalayash/spring-fleet/skills/debug/SKILL.md

debug

Skill2 starsChanged 44 days agoMITView on GitHub

Debug a runtime failure across the fleet by correlating logs on an OTel trace_id / sessionId / requestId, or by reading a pasted Grafana / stack-trace screenshot, and mapping the failure back to source.

192 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use add-discord, add-slack and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • MicrosoftSkill

    add-discord

    Add Discord bot channel integration via Chat SDK.

    Also in 11 projects that use this

  • MicrosoftSkill

    add-slack

    Add Slack channel integration via Chat SDK.

    Also in 11 projects that use this

  • +10 more from microsoft

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 1 is distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 175 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use the debugging-runtime-logs skill.

    line 22
  2. Very specific:

    If the input is an image: read it first. Look for a trace_id / traceparent value, a sessionId, a service name + timestamp window, or an …

    line 23
  3. Very specific:

    If the cause is cross-service, dispatch fleet-explorer to confirm the call path and map the failing hop to file:line.

    line 30
  4. Very specific:

    No plugin subagents (Codex): read agents/log-correlator.md and agents/fleet-explorer.md under the plugin root (two directories above this …

    line 40

“Common” is measured: kept by at least 6 in 10 of the 175 edited versions of this file we could read. “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

Debug a cross-service runtime issue in the Spring Boot fleet.

Input: $ARGUMENTS: one of:

  • an OTel trace_id (32 lowercase hex chars): preferred, modern path.
  • a legacy sessionId / requestId: fallback for older fleets.
  • a pasted error or stack trace: agent extracts a trace key from nearby log lines.
  • a pasted screenshot of a Grafana / Tempo / Jaeger / Kibana panel or an IDE / terminal stack; the model reads it directly (Claude is multimodal); extract the trace_id or service + timestamp from the image and use that as the correlation handle.

Steps:

  1. Locate spring-fleet.config.json (cwd, else ask the user / suggest /fleet-init).
  2. Use the debugging-runtime-logs skill.
  3. If the input is an image: read it first. Look for a trace_id / traceparent value, a sessionId, a service name + timestamp window, or an exception class + message. Use whichever you find as the correlation handle (prefer trace_id). Quote what you extracted so the user can sanity-check it.
  4. Dispatch the log-correlator agent with the config path and the resolved handle to build the cross-service timeline and isolate the failure origin. Prefer the correlate_by_trace MCP tool when available.
  5. If the cause is cross-service, dispatch fleet-explorer to confirm the call path and map the failing hop to file:line.
  6. Report: what happened, the timeline, failure origin (service + file:line), how it surfaced upstream, the ROOT-CAUSE HYPOTHESIS block from the log-correlator (WHAT / WHERE / WHY / CONFIDENCE / SUGGESTED FIX), and any service missing a log file.

Outside Claude Code

  • $ARGUMENTS is the text the user supplied with the request.
  • No plugin subagents (Codex): read agents/log-correlator.md and agents/fleet-explorer.md under the plugin root (two directories above this SKILL.md) and do that work yourself instead of dispatching.
  • spring-fleet MCP tools: pass config_path (absolute path of the project's spring-fleet.config.json). Codex starts the server outside the project, so it cannot find the config on its own.

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