ZBS Index What actually exists in applied AI, with the source next to it

Skills for Claude Code

These skills are associated with Claude Code because their author either published them under the harness's install path or tagged the repository for it on GitHub. Both are statements of intent by the author.

Neither is a test result. We have not run any of these with and without the skill enabled, so nothing here tells you whether a skill improves output, what it adds in tokens, or whether it duplicates behaviour the harness already has. When we run that comparison, the numbers will appear here with the task, the versions and the budget.

Worked on in the last 90 days (60)

Someone pushed a commit recently. This is the shortlist worth trying first.

  • zebbern-claude-code-guide-code-vuln-audit — last commit 2026-08-05
    Scan code for security issues: dependency vulnerabilities (npm/pip audit), secret leaks (regex and entropy analysis), and OWASP anti-patter…
  • zebbern-claude-code-guide-cross-examine — last commit 2026-08-05
    Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use…
  • zebbern-claude-code-guide-cv-tailor — last commit 2026-08-05
    Optimize resumes by matching keywords to the job description, rewriting experience with the quantified STAR method, and checking ATS compat…
  • zebbern-claude-code-guide-data-viz-renderer — last commit 2026-08-05
    Generate self-contained HTML/SVG infographics from JSON data, including stat cards, bar charts, flow diagrams, and mixed dashboards. Offers…
  • zebbern-claude-code-guide-database-optimizer — last commit 2026-08-05
    Use when investigating slow queries, analyzing execution plans, or optimizing database performance. Invoke for index design, query rewrites…
  • zebbern-claude-code-guide-database-scout — last commit 2026-08-05
    Explore SQLite and PostgreSQL databases: list tables, inspect schemas (columns/types/constraints), preview data, generate Mermaid ER diagra…
  • zebbern-claude-code-guide-dataset-quality-audit — last commit 2026-08-05
    Run comprehensive quality checks on tabular data (CSV/Excel/TSV/JSON), detecting missing values, duplicates, outliers, format issues, and t…
  • zebbern-claude-code-guide-deep-module-refactor — last commit 2026-08-05
    Explore a codebase to find opportunities for architectural improvement, focusing on making the codebase more testable by deepening shallow…
  • zebbern-claude-code-guide-design-system-builder — last commit 2026-08-05
    Extract design systems from reference UI images and generate implementation-ready UI design prompts. Use when users provide UI screenshots/…
  • zebbern-claude-code-guide-dev-guide-generator — last commit 2026-08-05
    Generates complete technical tutorials from prerequisites and environment setup to core steps, troubleshooting, and a final cheatsheet. Tri…
  • zebbern-claude-code-guide-ethical-hacking-methodology — last commit 2026-08-05
    This skill should be used when the user asks to "learn ethical hacking", "understand penetration testing lifecycle", "perform reconnaissanc…
  • zebbern-claude-code-guide-file-path-traversal — last commit 2026-08-05
    This skill should be used when the user asks to "test for directory traversal", "exploit path traversal vulnerabilities", "read arbitrary f…
  • zebbern-claude-code-guide-html-injection-testing — last commit 2026-08-05
    This skill should be used when the user asks to "test for HTML injection", "inject HTML into web pages", "perform HTML injection attacks",…
  • zebbern-claude-code-guide-http-load-profiler — last commit 2026-08-05
    Run stepped HTTP load tests with ab/wrk, ramping concurrency levels to collect p50/p90/p99 latency, detect performance inflection points, a…
  • zebbern-claude-code-guide-idor-testing — last commit 2026-08-05
    This skill should be used when the user asks to "test for insecure direct object references," "find IDOR vulnerabilities," "exploit broken…
  • zebbern-claude-code-guide-vercel-composition-patterns — last commit 2026-08-05
    React composition patterns that scale. Use when refactoring components with
  • juneyaooo-nihaisha-nishi-tcm-nihaisha — last commit 2026-08-04
    Use this skill when the user asks about Ni Haisha / 倪海厦 TCM course material, especially Shang Han Lun / 伤寒论, Jingui / 金匮要略, Zhongjing Xinfa…
  • lukasniessen-terrashark-terrashark — last commit 2026-08-04
    Prevent Terraform/OpenTofu hallucinations by diagnosing and fixing failure modes: identity churn, secret exposure, blast-radius mistakes, C…
  • y49-tlive-tlive — last commit 2026-08-04
    tlive — remote approvals (Telegram/Feishu/web), live web terminal, and
  • y49-tlive-tlive-fa4e10 — last commit 2026-08-04
    tlive — remote approvals (Telegram/Feishu/web), live web terminal, and
  • laolaoshiren-claude-code-skills-zh-api-tester — last commit 2026-08-04
    依据真实 OpenAPI、路由实现和现有测试生成并验证 API 测试。用于用户要求测试接口、补集成测试、验证 API 契约、生成回归用例或排查接口兼容性时;区分“生成测试”和“执行请求”的授权,不猜测状态码、响应结构或 SLA,不在未确认环境中发送写请求。
  • laolaoshiren-claude-code-skills-zh-changelog-gen — last commit 2026-08-04
    Changelog 生成器 - 从 Git 历史自动生成 CHANGELOG
  • laolaoshiren-claude-code-skills-zh-db-migrator — last commit 2026-08-04
    数据库迁移助手 - Schema 对比、迁移脚本生成
  • laolaoshiren-claude-code-skills-zh-dep-auditor — last commit 2026-08-04
    审计 Node.js、Python、Go、Rust、JVM、Ruby 项目的依赖漏洞、版本健康度与许可证事实;当用户要求检查 package.json、lockfile、requirements、go.mod、Cargo.toml、pom.xml、Gemfile.lock,或生…
  • laolaoshiren-claude-code-skills-zh-ds-mapper — last commit 2026-08-04
    项目目录结构地图 - 生成带说明的可视化目录树,快速理解任意代码库
  • laolaoshiren-claude-code-skills-zh-env-manager — last commit 2026-08-04
    环境变量管理器:扫描、校验、同步 .env 文件,生成安全配置模板
  • laolaoshiren-claude-code-skills-zh-error-translator — last commit 2026-08-04
    编程错误消息翻译专家 — 将英文错误消息翻译成中文,解释原因并提供修复方案
  • laolaoshiren-claude-code-skills-zh-eslint-fix — last commit 2026-08-04
    安全诊断并修复 ESLint error、warning 和配置兼容问题。用于用户要求运行 lint、解释 ESLint 报错、限定范围自动修复或迁移 ESLint 配置时;优先使用项目锁定的包管理器与版本,先预检再修改,不自动下载最新版或批量改写无关源码。
  • laolaoshiren-claude-code-skills-zh-git-workflow — last commit 2026-08-04
    安全处理 Git 状态检查、提交信息、commit、分支、push、PR 和 rebase。用于用户要求检查改动、生成或创建提交、管理分支、推送、发起 PR 或整理历史时;严格区分每个动作的授权,并保护工作树中已有和无关的修改。
  • laolaoshiren-claude-code-skills-zh-github-actions-gen — last commit 2026-08-04
    分析真实项目并生成或修订安全、可验证的 GitHub Actions workflow;当用户要求创建 CI、测试矩阵、构建、Release、部署、缓存、Secrets、OIDC、PR 自动化或排查 workflow 配置时使用
  • laolaoshiren-claude-code-skills-zh-i18n-helper — last commit 2026-08-04
    国际化/本地化助手 — 扫描代码中的硬编码文本、生成 i18n 配置、批量翻译
  • laolaoshiren-claude-code-skills-zh-log-analyzer — last commit 2026-08-04
    日志分析助手 — 智能解析日志文件,识别异常模式,定位问题根因
  • laolaoshiren-claude-code-skills-zh-perf-profiler — last commit 2026-08-04
    基于可复现基线和 profiler 证据分析性能问题。用于用户要求定位慢接口、慢任务、慢查询、内存或网络瓶颈,制定优化方案,或验证优化收益时;区分实测结论与静态推断,不虚构耗时和提升比例,生产环境操作需明确授权。
  • laolaoshiren-claude-code-skills-zh-refactor-advisor — last commit 2026-08-04
    重构顾问 - 识别代码坏味道并提供重构方案
  • laolaoshiren-claude-code-skills-zh-security-audit — last commit 2026-08-04
    代码安全审计 - 漏洞扫描、依赖检查、安全最佳实践
  • laolaoshiren-claude-code-skills-zh-skill-curator — last commit 2026-08-04
    中文 Skill 收录评估器。用于核验 GitHub 上的 Claude Code、Codex、Agent Skills、Plugin、MCP、CLI 或 Agent 工作流是否值得加入精选列表;检查真实资产、安装方式、活跃度、重复项和安全边界,并生成分类、中文描述与可追溯证据。
  • laolaoshiren-claude-code-skills-zh-test-generator — last commit 2026-08-04
    依据真实代码契约生成并验证单元测试或集成测试。用于用户要求为函数、类、接口或缺陷补测试、提高覆盖率、生成回归用例或完善测试策略时;先读取现有测试与调用方,不猜测空值、异常或超时行为,不自动安装框架或访问生产依赖。
  • laolaoshiren-claude-code-skills-zh-zh-code-reviewer — last commit 2026-08-04
    中文代码审查专家 - 生成详细的中文代码审查报告
  • laolaoshiren-claude-code-skills-zh-zh-docgen — last commit 2026-08-04
    中文文档生成器 - 从代码库自动生成中文技术文档
  • laolaoshiren-claude-code-skills-zh-zh-readme — last commit 2026-08-04
    中文 README 生成器 - 先分析项目,再生成面向中文开发者的高质量 README
  • rohitg00-pro-workflow-agent-teams — last commit 2026-08-03
    Coordinate multiple Claude Code sessions as a team — lead + teammates with shared task lists, mailbox messaging, and file-lock claiming. Pa…
  • rohitg00-pro-workflow-auto-setup — last commit 2026-08-03
    Auto-configure quality gates, hooks, and settings for a new project. Detects project type and sets up appropriate tooling. Use when onboard…
  • rohitg00-pro-workflow-batch-orchestration — last commit 2026-08-03
    Decompose large-scale changes into independent units and spawn parallel agents in isolated worktrees. Use for migrations, refactors, codemo…
  • rohitg00-pro-workflow-bug-capture — last commit 2026-08-03
    Capture a user-reported defect as a durable GitHub issue written in the project's own domain language. Explores the codebase in parallel fo…
  • rohitg00-pro-workflow-compact-guard — last commit 2026-08-03
    Smart context compaction with state preservation. Saves critical files, task progress, and working state before compaction, restores after.…
  • rohitg00-pro-workflow-context-engineering — last commit 2026-08-03
    Master the four operations of context engineering — Write, Select, Compress, Isolate. Manage token budgets, compaction strategies, and cont…
  • rohitg00-pro-workflow-context-optimizer — last commit 2026-08-03
    Optimize token usage and context management. Use when sessions feel slow, context is degraded, or you're running out of budget.
  • rohitg00-pro-workflow-cost-tracker — last commit 2026-08-03
    Track session costs, set budget alerts, and optimize token spend. Use to check costs mid-session or set spending limits.
  • rohitg00-pro-workflow-design-engineering — last commit 2026-08-03
    Apply interface craft when building or reviewing UI - motion, easing, timing, springs, component feel, and visual foundations. Use when bui…
  • rohitg00-pro-workflow-deslop — last commit 2026-08-03
    Remove AI-generated code slop, unnecessary comments, and over-engineering from the current branch diff. Cleans up boilerplate, simplifies a…
  • rohitg00-pro-workflow-domain-modeling — last commit 2026-08-03
    Build the project's shared language and bounded contexts before writing code, so names stay consistent and the agent stops paraphrasing dom…
  • rohitg00-pro-workflow-file-watcher — last commit 2026-08-03
    Configure file watching hooks to auto-react to config changes, env file updates, and dependency modifications. Use to set up reactive workf…
  • rohitg00-pro-workflow-improve-architecture — last commit 2026-08-03
    Audit an area of the codebase and propose the smallest structural moves that improve it - untangle boundaries, kill duplication, fix seams,…
  • rohitg00-pro-workflow-insights — last commit 2026-08-03
    Show session analytics, learning patterns, correction trends, heatmaps, and productivity metrics. Computes stats from project memory and se…
  • rohitg00-pro-workflow-learn-rule — last commit 2026-08-03
    Capture a correction or lesson as a persistent learning rule with category, mistake, and correction. Stores, categorises, and retrieves rul…
  • rohitg00-pro-workflow-llm-council — last commit 2026-08-03
    Provider-agnostic multi-LLM deliberation. Three phases — independent responses, cross-model anonymized ranking, chairman synthesis. Provide…
  • rohitg00-pro-workflow-llm-gate — last commit 2026-08-03
    LLM-powered quality verification using prompt hooks. Validates commit messages, code patterns, and conventions using AI before allowing ope…
  • rohitg00-pro-workflow-mcp-audit — last commit 2026-08-03
    Audit connected MCP servers for token overhead, redundancy, and security. Use when sessions feel slow or before adding new MCPs.
  • rohitg00-pro-workflow-module-map — last commit 2026-08-03
    Produce a one-screen map of an unfamiliar area of the codebase: entry points, modules, data flow, callers. Designed to be read in fifteen s…
  • rohitg00-pro-workflow-orchestrate — last commit 2026-08-03
    Wire Commands, Agents, and Skills together for complex features. Use when building features that need research, planning, and implementatio…

Page 11 of 24

How this page is ordered

Entries are grouped by whether anyone is still working on them, using the date of the most recent push to the repository. They are not ordered by stars, because a star is a bookmark somebody left once and never took back.

Where we have not checked an entry yet, it says so rather than being mixed in with the verified ones.