Skip to content
Back to skills

Debug

ASecurity

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.

  • 2 stars
  • 0 votes
  • 0 copies
  • 4 views
  • Added September 29, 2026
developmentbashspringdebugging

Works with

  • claude code
  • terminal
  • mcp

Security analysis

A100/100

Scanned September 29, 2026

npx -y skills add talayash/spring-fleet --skill debug --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Debug?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Debug
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/talayash-debug/badge)](https://www.skillsdirectory.com/skills/talayash-debug)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: debug
description: 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.
argument-hint: <trace_id | sessionId | "error snippet" | (or paste a screenshot)>
allowed-tools: Bash, Read, Grep, Glob, Task
---

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.

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.