← ClaudeAtlas

nexus-debugginglisted

Use when something is failing, regressing, or behaving unexpectedly and the goal is root-cause analysis, narrowest fix, and verification. Covers CI/CD, tests, runtime, deployment, and tooling failures. Output should be RCA + fix + prevention, not design options. When in doubt, use this skill.
aayushostwal/nexus · ★ 10 · AI & Automation · score 76
Install: claude install-skill aayushostwal/nexus
# Nexus Debugging Route to the correct sub-guide and follow it end-to-end. --- ## Compatibility - Sub-guides: `skills/debugging/ci-cd.md`, `skills/debugging/codebase.md`, `skills/debugging/frameworks.md` - Shared rules and output formats: `skills/debugging/common.md` --- ## Workflow ### Step 1 — Classify the Failure Pick exactly one track: | Track | Failure origin | Sub-guide | |-------|---------------|-----------| | CI/CD | GitHub Actions, Jenkins, CircleCI, or deployment pipeline log | `ci-cd.md` | | Codebase | Failing test, runtime exception, or regression in application code | `codebase.md` | | Framework | Django, FastAPI, Bazel, or other tooling misbehavior | `frameworks.md` | If unsure: ask "Is the failure in pipeline logs, app code, or a framework?" ### Step 2 — Gather Error Context Before reading the sub-guide, collect: 1. Full error message or stack trace — copy exact text, do not paraphrase 2. What changed recently: last commit, dependency update, config change, environment change 3. Environment details: local vs CI, OS, Python/Node/runtime version 4. Steps to reproduce (minimum reproducible case if possible) ### Step 3 — Read Sub-Guide & Execute Read the appropriate sub-guide. Follow its steps in order. Do not skip steps. Read `common.md` for shared output format and checklists. ### Step 4 — Search for Tool-Specific Errors If the error is framework-specific or tool-specific: 1. Search: `"<exact error message>" <tool-name> <version>` — use exact error tex