Results for “backlog-prioritization”

Prioritize product work with explicit criteria, scoring, tradeoffs, and decision rationale.

Create a delivery plan with goals, capacity, scope, risks, and commitments.

Turns a pile of bugs, issues, and error reports into a ranked, actionable plan with reproduction evidence. Ingests GitHub issues via gh, TODO/FIXME scans, error logs, or a pasted list; attempts to reproduce or classify every item; scores by impact, frequency, fix cost, and regression risk; clusters duplicates; and.

Plan backend domains, services, jobs, integrations, and failure handling for a product or major feature. Use when UX and product scope are defined and the team needs a production-minded backend design without defaulting to premature microservices.

Plan a sprint by estimating team capacity, selecting and sequencing stories, and identifying risks.

研究优先于编码的工作流程。在编写自定义代码之前，搜索现有的工具、库和模式。调用研究员代理。

PR Fleet

Package a customer escalation for engineering, product, or leadership as a decision-ready handoff — impact, timeline, facts vs. hypotheses, and a specific ask with an owner.

当需要进入并维持高度专注的深度工作状态时

当需要在多个领域积累独特竞争优势，避免单一技能风险时

Use this when the system needs queue-backed processing design, message handling rules, delivery semantics, dead-letter strategy, or throughput planning. Trigger on requests about queues, brokers, message processing, and consumer coordination.

当面临信息过载或想法过多，需要筛选出值得投入资源（时间、精力）去执行的高价值想法时

Decide the highest-value safe thing to do right now in the active repo or workspace.

Issue Fleet

Triage Linear or Jira backlogs and run bug sweeps via the Composio CLI. Bulk-fetch issues, deduplicate, relabel, reassign, and post summaries all from the shell.

Test Fleet

Use this when background workers or job processors need design or review. Trigger on requests about asynchronous processing, job payloads, retries, scheduling, worker ownership, or long-running tasks outside the request path.

Almost every downstream bug traces back to an index that was assumed regular and

Strategic patterns for solving intractable problems through cascading approximation, self-improvement, and heterogeneous evaluation from DeepMind's AlphaGo system

Build serverless background jobs, event-driven workflows, and durable execution with Inngest, without managing queues or workers.

Graceful degradation when primary approach fails. Try alternates in priority order; record which path succeeded for future routing.