Claude Skills by TsCarpe

github.com/TsCarpe

8 skillsA× 80 installs10 views

Sdlc Config ReviewA扫描当前分支相对基线分支（master/main）的 Java 代码 diff，提取发版前需在代码之外人工处理的事项——①配置中心（Apollo/Nacos）Key：@Value 单值、@ConfigurationProperties 前缀、任意注解属性中的 ${...} 占位符；②外部平台注册操作：@XxlJob 任务（新增/改名/孤儿检测）、RocketMQ/Kafka/Rabbit listener 订阅关系；③行为知会项（@Scheduled 集群重复执行等）。产出配置 Key 清单 + 平台操作清单 + 知会项。Use when 用户要梳理上线配置清单、检查新增配置 Key、准备 Apollo/Nacos 发版配置、检查新增定时任务/xxl-job 任务/MQ 订阅，或说 config-sentinel、config review、Apollo/Nacos key audit、release config checklist、xxl-job audit、上线检查。ai-agentsjavashellVotes: 0GitHub stars: 62
Sdlc DoubtA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""这个方案稳不稳""doubt-review"。ai-agentssqlcode-reviewVotes: 0GitHub stars: 62
Sdlc GateA评审关口：技术设计与测试用例定稿后的强制评审关口——按风险分级分档对抗评审（A 级 4 个全新上下文子代理 / B 级 2 个 / C 级主会话自查）产出 issue 清单与分歧清单，人工逐条裁决后放行开发/测试执行。Use when 技术设计或测试用例已产出待评审、用户说评审关口、设计评审、用例预审、交叉审查、review gate、adversarial review、design review，或需求梳理确认后设计与用例并行产出完毕。用法：/sdlc-gate <需求名>ai-agentspythonsqlVotes: 0GitHub stars: 62
Sdlc GuardrailsADeterministic 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 --check baseline scanning for legacy code. Engine is mechanism (one global copy), rules are content (per project). Use when 接入或配置红线拦截、给项目编写 guardrails 规则、排查 hook 拦截了或没拦、扫描存量违规基线，或用户说 guardrails、红线引擎、红线...ai-agentspythonjavaVotes: 0GitHub stars: 62
Sdlc IntentADigests 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 plus an external-reference layer for missing-content defects) and produces a graded issue report plus a PM clarification checklist. Use when the user shares a requirement/PRD document (Feishu/wiki li...ai-agentspythonVotes: 0GitHub stars: 62
Sdlc SyncASyncs local SDLC artifacts (requirement digest/audit/checklist, test cases) to a team-facing web platform and pulls PM clarification answers back into local markdown files. Bridges the single-developer local workflow with multi-role collaboration: submit creates the requirement card for daily use; push-artifacts / pull-answers / publish / push-cases are local fallback channels for when the platform's online flow (task queue + runner, platform v2.0) is unavailable. Use when the user wants to 推...ai-agentsgoshellVotes: 0GitHub stars: 62
Skills DirectorySkills Directory Look up any of 103,619 scanned skills — grade, score, and every finding. Free.Check a skill
Sdlc TestAAI 测试智能体编排：开发完成验证（compile/boot/冒烟/回归）→ 用例生成 → 静态代码一致性检测 → test 环境浏览器功能测试 → 报告生成。子命令（cases/dev/static/exec/spec/report）独立可重跑，两道人工关卡（用例审核、报告复验）；通过用例可资产化为 Playwright spec，回归轮跑 runner 零 agent token。Use when 用户要求 AI 测试、生成测试用例、开发完成验证、冒烟自测、执行测试、提测验证、回归测试、生成回归脚本、spec 资产化，或说 AI testing、test generation、browser E2E、playwright spec。用法：/sdlc-test cases|dev|static|exec|spec|report <需求名>ai-agentspythonjavaVotes: 0GitHub stars: 62
Sdlc DesignAProduces 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 frameworks like Trellis. Use when the requirement digest is confirmed and design is due, or the user says 技术设计、详细设计、概要设计、出设计、设计文档、接口契约、D 表、方案骨架、切分约束、sdlc-design. 用法：/sdlc-design <需求名>ai-agentssqlVotes: 0GitHub stars: 62