parallel-diagnosis
Parallel Diagnosis
Two independent agents investigate a bug in parallel, then converge on a single unified diagnosis. Produces structured output that downstream skills (two-pass-review, fix-loop) can act on.
When to use
- YES: Multi-layer bugs (schema + router + model), framework quirks, uncertain library behavior, high-risk deploys, intermittent failures
- NO: Trivial bugs, typos, issues where root cause is already known, zero blast radius
Instructions
1 — Parallel diagnosis
If the problem statement is ambiguous (unclear which subsystem, multiple possible symptoms, or no file paths identified), use the AskUserQuestion tool to narrow scope before spinning up agents. Present what you understand and ask the user to confirm or clarify.
- Spin up 2 independent subagents in parallel. Default: Sonnet. Use Opus for complex async/architectural bugs.
- Give them ONLY the problem statement and relevant file paths.
- Instruct each agent to:
- Read the code independently — no communication between agents.
More from preetamnath/agent-skills
shopify-dev-mcp
Routes Shopify Dev MCP calls for surfaces NOT covered by the bundled Shopify skills: `storefront-graphql`, `customer`, `partner`, `payments-apps`, `functions`, `hydrogen`, `liquid`, `custom-data`. SKIP for Admin GraphQL or App Home markup — the bundled `shopify-admin` and `shopify-polaris-app-home` skills cover those. SKIP entirely for `@shopify/post-purchase-ui-extensions-react` — the MCP doesn't index that legacy SDK; use `post-purchase-ui-extension` instead.
15plan-runner
Executes wave-grouped markdown plans via parallel subagents. Orchestrates implementation, per-wave review, fix cycles, and final two-pass-review. Resumable across conversations.
13interview-me
Move from ambiguity to clarity before building. Use when user says 'interview me', asks to be interviewed, or the task has ambiguous scope.
13sentry-analysis
Analyze Sentry error logs, breadcrumbs, and codebase context to diagnose and explain the root cause of issues.
13code-review
Structured code review with P0-P3 findings, confidence scores, and criteria-based analysis. Use for reviewing code changes, PRs, or specific files.
12plan-builder
Creates dependency-ordered, wave-grouped executable plans from a goal + context. Produces markdown plans with parallel execution waves compatible with plan-runner. Use when you need to break a goal into sequenced, atomic work items before execution.
10