75 个（Basinfy 的仓库） · 按人气排序
Turn your AI session into an autonomous SaaS and software engineering studio with 49 specialized agents, 74 workflow skills (/saas-*), 28 director gates, and complete architecture across Next.js, FastAPI, Supabase, Tailwind, and Stripe.
中文简介正在准备中。当前显示原文说明。
High-concurrency load, stress, and endurance soak test protocol for SaaS endpoints — simulates virtual users, monitors p95/p99 latency, RPS, connection pool limits, and memory leaks.
中文简介正在准备中。当前显示原文说明。
Localization pipeline — find hardcoded strings, extract string tables, cultural review, transactional email & messaging, RTL, enforce string freeze.
中文简介正在准备中。当前显示原文说明。
Decompose a concept into individual systems, map dependencies, prioritize design order, create the systems index.
中文简介正在准备中。当前显示原文说明。
Milestone progress review — completeness, quality metrics, risk, go/no-go recommendation. At checkpoints or before a deadline.
中文简介正在准备中。当前显示原文说明。
Onboarding doc for a new contributor or agent — project state, conventions, priorities relevant to the specified role.
中文简介正在准备中。当前显示原文说明。
User-facing patch notes from git history and changelogs. Translates developer language into user communication.
中文简介正在准备中。当前显示原文说明。
Performance profiling — find bottlenecks, measure against budgets, produce ranked optimization recommendations.
中文简介正在准备中。当前显示原文说明。
Day-one launch patch — focused fix for known issues found after GA production release. Mini-sprint with QA gate and rollback.
中文简介正在准备中。当前显示原文说明。
Find pricing outliers, tier cannibalization, negative gross margin risks, and usage quota imbalances in pricing models and unit economics. 'Check SaaS pricing & unit economics'.
中文简介正在准备中。当前显示原文说明。
Analyze project state, detect stage, identify gaps, recommend next steps. 'Where are we in development?'
中文简介正在准备中。当前显示原文说明。
Finds architecture decisions (ADRs) made stale by a changed PRD and walks through resolving each. Use when the user changed a number or rule in a PRD and asks which ADRs or architecture decisions are now out of date.
中文简介正在准备中。当前显示原文说明。
Concept prototype before PRDs — throwaway HTML, Engine or Paper build, PROCEED/PIVOT/KILL/NOT ASSESSED. After /saas-brainstorm and /saas-setup-stack.
中文简介正在准备中。当前显示原文说明。
QA test plan for a sprint — classifies stories by Logic/Integration/Visual/UI, covers automated tests, manual cases, smoke scope.
中文简介正在准备中。当前显示原文说明。
Lightweight spec for small changes — tuning adjustments, minor workflow tweaks. Embeds directly into stories; skips full PRD.
中文简介正在准备中。当前显示原文说明。
Map test coverage to PRD critical paths, find fixed bugs lacking regression tests, flag drift from new features.
中文简介正在准备中。当前显示原文说明。
Pre-release checklist — build verification, certification requirements, store metadata, launch readiness.
中文简介正在准备中。当前显示原文说明。
Sprint or milestone retrospective from completed work, velocity, blockers. Actionable insights for the next iteration.
中文简介正在准备中。当前显示原文说明。
Generate missing design or architecture docs from existing implementation — works backwards from code and prototypes.
中文简介正在准备中。当前显示原文说明。
Holistic cross-PRD review — contradictions between systems, conflicting business rules, pricing tier cannibalization, cognitive overload, pillar drift.
中文简介正在准备中。当前显示原文说明。
Scope creep check — current scope versus the original plan. Flags additions, quantifies bloat, recommends cuts. 'Any scope creep?'
中文简介正在准备中。当前显示原文说明。
Application security (AppSec) audit — tenant isolation, auth & RBAC, OWASP Top 10, webhook signatures, rate limiting, dependency CVEs. Before release.
中文简介正在准备中。当前显示原文说明。
Brownfield audit — do existing artifacts actually work? Numbered migration plan. Unlike /saas-project-stage-detect, checks compliance not existence.
中文简介正在准备中。当前显示原文说明。
Configure engine and version. Pins it in CLAUDE.md; WebSearch fills reference docs when the version is beyond LLM training data.
中文简介正在准备中。当前显示原文说明。