superpowers
claudecodexCore skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Ten battle-tested SDLC skills: sdlc-intent (PRD digest + seven-layer audit + A/B/C risk tiering), sdlc-design (technical design: alternatives, tiered interface contracts, shared assets, C/H decisions, slicing constraints), sdlc-test (cases/dev/static/exec/spec/report with human checkpoints), sdlc-gate (risk-tiered adversarial review gate: 4/2 fresh-context subagents or self-check, plus guard_dev), sdlc-doubt (adversarial re-check of non-trivial decisions), sdlc-ui-visual (design-to-code visual restoration via screenshots: DOM geometry + pixel heatmap + tiered fix rounds), sdlc-release-check (pre-release audit: config keys, job/MQ registrations, DDL/DML grading, runbook), sdlc-guardrails (write-time red-line engine: PostToolUse hook + pre-commit + baseline scan), sdlc-sync (artifact sync bridge between local markdown and the team-facing platform), sdlc-handoff (cross-agent session handoff: self-contained card, drift check, direct takeover).
Plugin sdlc-skills from marketplace claude-sdlc-skills in TsCarpe/claude-sdlc-skills. Commands read from the repo's manifest — today.
sdlc-designProduces the technical design document (design.md) from the confirmed requirement digest: solution alternatives, data model, tiered interface contracts, shared-asset inventory with delivery ownership, decision table (C-constraint/H-assumption), and implementation slicing constraints handed to task f
sdlc-doubtAdversarially re-checks a non-trivial technical decision in a fresh context by stripping the conclusion and asking an independent reviewer to find problems. 对刚做出的非平凡技术决策发起对抗式独立复查——把决策剥离结论后交给全新上下文的审查者"找问题"。Use when 影响ER或公共组件的决策回写前、复杂SQL/状态机流转定稿前、技术方案选型二选一定稿前、提交前对"已全范围检查"断言存疑时、用户说"这个判断我不放心""帮我质疑一下这个方案
sdlc-gateRuns the mandatory risk-tiered review gate after technical design and test cases are finalized: adversarial review by fresh-context subagents (4 for tier A / 2 for tier B / main-session self-check for tier C), producing an issue list and divergence list for human adjudication before development or t
sdlc-guardrailsDeterministic guardrail engine that enforces \"write-it-and-it's-wrong\" red-lines at write time - a PostToolUse hook runs engine/check.py on every Write/Edit and blocks violations per project-defined guardrails.yaml rules (forbid / require / require_if / count_ge), with pre-commit fallback and --ch
sdlc-handoffSession handoff and takeover that works with any coding agent. 会话交接与会话接手:旧会话上下文将满、或任务要换会话/换机器/换 agent 继续时,把当前任务压缩成一张自足的交接卡(write);新会话读取交接卡并直接继续(resume),覆盖开发、排查、梳理、调研、文档等任意任务。Use when 交接、接手、继续上次的工作、上下文满了、换个会话做、上次做到哪了、pick up where I left off, handoff, resume previous work, context is full. 用法:/sdlc-h
sdlc-intentDigests and health-checks product requirement documents (PRD). Stage 1 produces a structured digest (roles, concepts, feature map, flow diagrams, state machines) to build shared understanding; stage 2 audits the requirement against a seven-layer defect taxonomy (six in-document consistency layers pl
sdlc-release-checkScans the Java + SQL diff between current and baseline branches (master/main), extracting release-time manual actions outside code: config-center keys (Apollo/Nacos), platform registrations (xxl-job, MQ listeners), DDL/DML changes, and behavior notices, producing config-key, platform-operation, data
sdlc-syncSyncs SDLC artifacts between local markdown workspace and the authoritative web platform: pulls platform digest/audit/answers plus the published standard doc back into local intake files (pull-artifacts), aligns the local dev workspace with finalized platform artifacts - standard doc, design, cases,
sdlc-testOrchestrates AI testing: dev-complete verification (health probe + smoke against an externally supplied service), case generation, static consistency checks, browser functional testing, and reports. Subcommands (cases/dev/static/exec/spec/report) are re-runnable with two human checkpoints; passing c
sdlc-ui-visualDesign-to-code visual restoration loop: diffs the running page against a Figma link or baseline image via real screenshots (DOM geometry + pixel diff/heatmap + zoomed inspection), drives tiered fix rounds and verifies functional regression. 设计稿到代码的视觉还原闭环:以 Figma 链接或基准图为唯一视觉基准,对运行中的前端页面做浏览器截图比对(DOM 几
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.
1 MCP server
Build powerful, stateful CLI interfaces for any GUI application using the cli-anything harness methodology.
5 commands
Automates browser interactions for web testing, form filling, screenshots, and data extraction
12 skills
Use Alibaba Open Code Review from local Codex.
2 skills
Claude Code skill for creating and presenting Slidev slidedecks
1 skill
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.