← ClaudeAtlas

ss-troubleshooting-workflowlisted

End-to-end defect fix — takes an issue link, alert ID, or problem description and orchestrates tier-adaptive root-cause investigation, human confirmation, branching, a fix plan, multi-agent coding with built-in review, and PR/commit delivery. Use only when the user explicitly asks for the full diagnose-to-delivery pipeline, not for diagnosis alone.
lbk-open/super-spec · ★ 1 · AI & Automation · score 65
Install: claude install-skill lbk-open/super-spec
# Troubleshooting Workflow Chains the existing `ss-*` skills into a single diagnose-fix-deliver flow: ``` ss-inspect → [Gate: root-cause confirmation] → ss-create-branch → ss-plan → ss-coding (built-in review) → review-acceptance loop → ss-create-pr ``` **Core principle: thin orchestration.** This skill never writes code or drafts a plan itself. It calls the other skills in order, pauses at the gates below, passes each step's output to the next, and reports progress. > **Review is not run twice.** `ss-coding` already enforces a post-coding review > internally and returns a verdict. This workflow never invokes `ss-code-review` separately — > the review-acceptance loop below is driven entirely by that verdict. Unlike `ss-feature-workflow`, the root-cause report from `ss-inspect` replaces the proposal, and **root cause is confirmed before any branch is created** — worth fixing is established before code is touched. ## When to Run This is heavy, end-to-end orchestration: it runs a root-cause investigation, creates a branch, spawns coding agents, runs reviews, and delivers the fix. Only run it when the user explicitly asks for this skill or clearly wants the full diagnose-to-delivery pipeline. For a plain question or a diagnosis-only request, do the work directly (or point to `ss-inspect` for diagnosis alone). ## Inputs - **Problem source** — an issue link, alert ID, or plain-text problem description. If missing, ask for one. - **Delivery mode** — `full` (default) or `l