Results for “revision-roadmap”

通用多轮迭代改进：对任意研究制品反复调用 /review → 解析反馈 → 修复 → 更新 wiki，直到达标

Reviews local branch changes for bugs, security vulnerabilities, and code quality issues using a structured checklist and attack surface mapping.

Review git diffs or file scopes for code reuse, quality, efficiency, and clarity issues, then optionally apply safe, behavior-preserving fixes.

When reviewing code, generate the complete corrected version — not just the issues, but the exact fixed code ready to copy-paste.

Builds or modifies a RAG pipeline with intent-based routing, vector store search, citation rendering, and book fidelity enforcement.

Build a compact, validation-gated implementation plan for multi-step, risky, or ambiguous work — typically when phases need explicit checkpoints, the change touches multiple files/services, or the user wants alignment before execution. Output goes to `.claude/plans/<topic>.md` (or `.agents/plans/`) with goal, in/out-of-scope, phased steps, validation per phase, and replanning triggers. Skip for trivial single-file fixes, bug investigations (use `tracer`), or open-ended exploration (use `explore`). Pair with `ship` once the plan ends and merge work begins.

Turn a new rep's start date into a ramp that ends in quota, not confusion. Builds a 30/60/90 onboarding plan with milestones at each gate, a certification bar they have to clear before they carry full load, and the manager touchpoints that catch a slow ramp early. Built for B2B sales managers and enablement, customizable to your role and motion. Trigger on "build an onboarding plan", "30/60/90 for a new AE", "how do I ramp this rep", "certification checklist", "onboarding milestones", or any new-hire ramp.

Iterates through pending development plans in .cursor/plans, implementing tasks, running self-tests, reviewing code, committing locally, and moving completed plans to docs/plans/done.

Plan before implementing - understand scope and approach with detailed guidance

Reviews code changes with a second AI reviewer, validates reported issues against the actual code, and reports only confirmed findings.

Analyzes evaluation patterns across completed plans and evolves the superpowers checklists accordingly.