majiayu000

Query foreign LLM for chat. Use this skill if a foreign LLM like OpenAI ChatGPT, Google Gemini, DeepSeek or xAI Grok should be queried with a single chat message.

Query Multiple AIs for Quorum Answer.

Use when turning a memory-corruption bug into a working PoC — stack/ROP, glibc heap & FSOP, format strings, browser/JIT type confusion & UAF, Linux/Windows kernel LPE against ASLR/DEP/CFG/CET/V8-Sandbox

Tinder for your Claude Code skills. Reviews a sorted deck of every installed skill and lets you swipe keep / delete / skip on each one. Use when the user wants to bulk-clean their skill collection, triage unused skills, or do interactive skill cleanup.

Use when the user wants to report a bug, file an issue, submit a bug report, or report any problem with the mobile-app plugin.

Resolve PR review feedback. Use when addressing review comments, resolving review threads, or fixing code-review feedback.

扫描本机 Claude Code 和 Codex 的会话日志，统计哪些 skill 有本地调用证据、哪些在本机无证据（已安装但日志无痕迹，不等于从未使用）、调用排行、月度趋势、项目分布，输出终端表格和 Markdown 报告，可导出 CSV/JSON。Use when the user asks to 统计 skill 使用, 看 skill usage, find zombie skills, 僵尸 skill, which skills are installed but never used, skill 调用排行, skill usage report, skill 使用健康度, audit personal skill arsenal, or manage which skills to keep or remove.

Detects when user requests warrant critical analysis via /advise command

Flexible data science analytics for any dataset. Auto-discovers schema, recommends charts, exports to create-figure. Works with JSONL, JSON, CSV from any source.

Use when you have CSV/Excel data files and need PM insights (retention, funnel, segmentation) via Python analysis.

Strategische Markenportfolio-Planung für Luxus-Modehaeuser: Mandant will Marken in DE/EU/international schützen oder Portfolio optimieren. Normen: §§ 32 ff. MarkenG, Art. 32 ff. UMV (EU) 2017/1001, Madrid-Protokoll (WIPO). Prüfraster: Nizza-Klassen (3/14/18/25/35), Multi-Class-Strategie, Prioritaets-Kaskade, Kostenoptimierung, Anmeldezeitpunkt. Output Marken-Portfolio-Plan, Anmelde-Empfehlung je Territorium, Kostenprojektion. Abgrenzung: Einzelne Anmeldung DPMA siehe wortmarke-anmeldung-dpma; Madrid-Protokoll Details siehe madrid-protokoll-und-internationale-registrierung.

Generate comprehensive anomaly detection report with Excel deliverables. Discovers data quality issues without requiring configuration.

Detect data anomalies in Datarails Finance OS tables. Finds outliers, missing values, duplicates, and data quality issues.

PostHog event tracking, user identification, group analytics for B2B, GDPR consent patterns. Use when implementing product analytics, tracking user behavior, setting up funnels, or configuring privacy-compliant tracking.

PostHog analytics and feature flags setup

Drizzle ORM, queries, migrations

跨工具（Claude Code + Codex）的只读 agent 健康体检与 skill 用量统计；只报告本地可验证证据，缺失检查面标为 unsupported。Use when the user asks 体检/doctor/health check/config audit、Claude 或 Codex 配置诊断、被拒命令分析、MCP/插件/skill 冲突、skill usage 排行或僵尸 skill。清理、权限、更新和配置写入必须基于证据单独确认。

能力蒸馏工作流——从用户批准的强模型访谈或真实任务轨迹中提取非显然的判断规则，形成可审计的 judgment packet，再交给 skill-audit 和 skill-creator 决定是否落成可加载 skill。当用户说“蒸馏这个模型的判断力”“把这次任务的关键决策固化下来”“模型窗口要关了，保留它在某类场景的判断”时使用。普通流程文档、直接写 SKILL.md、泛化最佳实践或未授权的会话日志扫描不使用本 skill。

检测一个 IP 或住宅/机房代理节点的质量——注册库、地理库一致性、ASN/org、风控信誉、黑名单、住宅真实性、BGP 宣告、目标服务(Grok/Claude/ChatGPT)解锁与延迟三角测量。判定该 IP 能否安全用于 AI 服务(避免被地理库误判到别国导致区域锁)。当用户说"查这个 IP"、"这个节点在哪"、"这个代理能用吗"、"IP 质量检测"、"验收住宅 IP"、"为什么被判定在 X 国"、"check ip"、给出 socks5 代理凭证问归属或解锁时使用。

Guard long, ambiguous, or stateful AI-agent work from drift. Use when the user asks to run or continue a multi-step task, autonomous loop, bug fix, repo change, PR readiness check, compaction handoff, resume from previous context, cost-control checkpoint, or any task likely to span many tool calls, files, sessions, agents, or verification gates.

Use before an agent-produced diff is committed, pushed, opened as a PR, merged, landed, or applied to user files when explicit implementation approval is missing. Trigger for review gate, review pack, approve before landing, diff first then land, human approval, merge gate, commit gate, push gate, or PR readiness. Produces a concise review pack, records risks and verification, and blocks landing until a human explicitly approves or approves with required fixes.

Audit, design, categorize, distribute, and measure agent skills using lessons from Anthropic's Lessons from building Claude Code: How we use skills. Use when reviewing an existing skill, deciding whether a workflow deserves a skill, planning a skill library, turning team knowledge into skills, choosing skill categories, writing trigger descriptions, designing progressive disclosure, or planning skill marketplace and usage measurement.

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Use when a skill is brittle, drifting, repeatedly failing, or needs a Reliable Skill Contract. Trigger for phrases like skill lifeguard, reliable skill, self-maintaining skill, negative examples, verification checkpoints, drift signals, replay hooks, or failure log to skill patch. Audits or patches skills so high-value workflows include explicit forbidden behaviors, checkpoints, machine-checkable done conditions, replay or smoke hooks, and drift detection.

跨语言代码库健康治理与自动优化系统。基于学术研究和实战经验，系统性检测 LLM 生成代码的结构性缺陷。完整流程：SCAN → DIAGNOSE → FIX → HARDEN。适用于任何语言的项目。

Sage 到 Tink UI 框架的完全重构指南，包含迁移步骤、文件清单、架构设计

Sage 版本管理规范，包含语义化版本、CHANGELOG、发布流程

Sage CLI UI 设计规范，参考 Claude Code 的终端显示模式，包含对齐、颜色、图标等设计标准

Sage Agent 执行引擎开发指南，涵盖 UnifiedExecutor、Subagent、Lifecycle 管理

Sage 项目整体架构设计指南，基于 Claude Code、Crush 最佳实践的融合方案

Sage 独有的检查点系统设计，包含状态快照、文件追踪、回滚恢复机制

Sage 配置系统开发指南，涵盖多源加载、凭证管理、验证、持久化

Use this skill whenever VibeGuard hook latency, benchmark-action output, GitHub Actions bench-output artifacts, or a suspected performance regression needs investigation. It preserves the PR-to-CI-artifact workflow for comparing recent PRs, older anchors such as PR

Use when the user asks for a VibeGuard dashboard, hook health, stats, doctor output, metrics export, or local observability status from the Codex App plugin.

Use when the user asks to install, verify, inspect, or remove VibeGuard Codex hooks through the Codex App plugin.

Use when the user asks Codex to apply VibeGuard anti-hallucination rules, inspect VibeGuard observability, or route a task through VibeGuard preflight/review/check workflows.

AI-assisted development of anti-hallucination specifications. Check out the seven-layer defense architecture, quantitative indicators, execution templates and practical cases. Used for code review, task startup inspection, and weekly review.

Automate analysis, evaluation, design and optimization of target projects. Integrate VibeGuard as a baseline scan, the remediation process adheres to VibeGuard specifications, and a compliance check is run at the end. Support auto-run-agent autonomous execution.

Discover and deliver repository optimization work end to end: identify performance/reliability/maintainability/security/dx/cost optimization points, prioritize by impact-effort-risk, then execute fixes step by step with continuous testing and explicit commit policy (`final_only`, `per_step`, `milestone`). Default to `per_step` for implementation work so each feature is tested then committed before the next feature. Supports optional BDD (Given/When/Then).

Audit AGENTS.md / CLAUDE.md against the five high-leverage patterns (progressive disclosure, procedural workflows, decision tables, production code examples, domain rules with concrete alternatives). Reports per-pattern coverage, anti-patterns, and a prioritized fix list.

Use when turning an approved SpecRail product and technical spec into the numbered `tasks.md` plan. Creates stable task IDs, owners, done-when conditions, verification commands, dependencies, and handoff notes without implementing the tasks.

Use when writing or updating a SpecRail product spec for a linked issue. Produces the numbered `product.md` spec from the locale-appropriate template, focusing on user-facing behavior, goals, non-goals, and acceptance criteria without implementation detail.

Use when writing or updating a SpecRail technical spec for a linked issue. Produces the numbered `tech.md` spec from the locale-appropriate template, translating accepted product behavior into design, affected files, risks, verification, and rollback without starting implementation.

Use when the user says "implx", "use implx", "用 implx", or asks for the one-line SpecRail queue shortcut. Plain implx means drain the full actionable issue/PR queue in auto mode: run SpecRail preflight, create missing spec/task PR work before implementation, use threads for reviewer/merge-reviewer lanes when available, create per-issue implementation PRs, require CI/reviewThreads/pr_gate evidence, auto-merge on complete evidence, and perform closure audit. Say "implx review" / "implx 人工" for the review mode that keeps per-PR human merge authorization.

Use when implementing or draining a GitHub issue/PR queue in a SpecRail-governed repository where approved specs already exist, such as multiple numbered specs/GH packets that need one or more implementation PRs per issue. Maps issues to specs and existing PRs, supports full-queue drain requests from implx, selects single-agent or optional threads orchestration, preserves partial versus final closing semantics, and requires SpecRail verification plus PR gates before merge-readiness claims.

Use before reporting a SpecRail PR as merge-ready. Collects read-only PR evidence, runs the offline PR gate, checks linked work, current head SHA, CI, review decision, review threads, merge state, and human merge authorization without merging.

Use when performing an advisory SpecRail PR review. Checks linked issue/spec evidence, route gates, verification evidence, review-thread state, human-gate preservation, and implementation quality without granting final approval or merging.

Use as the router/startup skill when working in a repository that adopts SpecRail for issue-first, spec-first, AI-assisted development. Routes triage, spec writing, task planning, implementation, PR review, CI diagnosis, PR gates, release notes, and spec-vs-implementation checks to focused SpecRail skills while preserving locale and human-gate boundaries.

LiteLLM-RS Routing Architecture. Covers 7 routing strategies, lock-free design with DashMap, health-aware selection, fallback chains, and load balancing.

LiteLLM-RS A2A Protocol Architecture. Covers Agent-to-Agent communication, JSON-RPC 2.0 messaging, multi-provider orchestration, agent registry, and task state management.

LiteLLM-RS Authentication Architecture. Covers JWT + API Key + RBAC multi-method auth, rate limiting with DashMap, middleware pipeline, and secure credential management.

LiteLLM-RS Caching Architecture. Covers Redis caching, vector database semantic caching, multi-tier cache strategy, TTL management, and cache invalidation patterns.

LiteLLM-RS Configuration Architecture. Covers YAML loading, environment variable override, validation patterns, type-safe config models, and hot reloading.

LiteLLM-RS Error Handling Architecture. Covers two-tier error hierarchy, ProviderError factory methods, HTTP status mapping, retry logic, and error context preservation.

LiteLLM-RS MCP Gateway Architecture. Covers Model Context Protocol, JSON-RPC 2.0 implementation, multi-transport support (HTTP, SSE, WebSocket, Stdio), and permission system.

LiteLLM-RS Observability Architecture. Covers Prometheus metrics, OpenTelemetry tracing, structured logging, health checks, and alerting integration.

Use when the user asks Codex to recall prior project context, save durable decisions or bug fixes, inspect remem memory health, or activate remem automatic memory hooks from the Codex plugin.

Use when turning an approved SpecRail product and technical spec into the numbered `tasks.md` plan. Creates stable task IDs, owners, done-when conditions, verification commands, dependencies, and handoff notes without implementing the tasks.

Use before reporting a SpecRail PR as merge-ready. Collects read-only PR evidence, runs the offline PR gate, checks linked work, current head SHA, CI, review decision, review threads, merge state, and human merge authorization without merging.

Use when performing an advisory SpecRail PR review. Checks linked issue/spec evidence, route gates, verification evidence, review-thread state, human-gate preservation, and implementation quality without granting final approval or merging.

Use as the router/startup skill when working in a repository that adopts SpecRail for issue-first, spec-first, AI-assisted development. Routes triage, spec writing, task planning, implementation, PR review, CI diagnosis, PR gates, release notes, and spec-vs-implementation checks to focused SpecRail skills while preserving locale and human-gate boundaries.

Use when writing or updating a SpecRail product spec for a linked issue. Produces the numbered `product.md` spec from the locale-appropriate template, focusing on user-facing behavior, goals, non-goals, and acceptance criteria without implementation detail.

Use when writing or updating a SpecRail technical spec for a linked issue. Produces the numbered `tech.md` spec from the locale-appropriate template, translating accepted product behavior into design, affected files, risks, verification, and rollback without starting implementation.

Validate remem first-run behavior from an isolated HOME and REMEM_DATA_DIR. Use when changing install, doctor, status, encrypt, hook activation, Codex/Claude setup, plugin activation, or user-facing onboarding documentation.

reads and summarizes files in the current workspace

Scaffolds a modern Python project using uv.

Fetches the current weather for a city via a public weather API.

Formats and beautifies Markdown files in your project.

Prints commit and contributor statistics for the current repo.

A general helper skill for everyday coding tasks.

Inserts emoji into your text by name.

Install the closed test loop into a fresh project. Copies the pre-commit hook, the CI workflow, the render script, the drift check script, the failure classifier, and the knowledge-base templates, then prepares the drill handoff that verifies the loop reacts.

Flag public symbols in the project's source tree that are not documented in the project's knowledge base. Use this before committing, in CI, or whenever a public API surface changes and you want to know whether the knowledge base has gone stale.

Verify the closed test loop actually reacts by injecting one intentionally failing test, running each of the five loop tools, and recording the result. Use after init-loop and after any change to a loop tool.

Group failing tests by naming convention so a real assertion failure is not hidden among tests that exist to verify a system rejects something. Use after running the test suite and before reading the report.

Turn a test runner's raw log into a Markdown report plus a structured JSON summary. Embeds the failure classification so a reader can see the failing tests, the run summary, and the failure-class counts on one page.

Meta-skill: choose which of the other five test-loop skills to invoke first, based on the user's description of the current state of their project. Use when a user says something like "I want to add tests to this project" or "this project has no CI" and the right entry point is not obvious.

Create, convert, audit, and package executable AI agent workflow patterns as Codex/Claude-style skills. Use when the user wants an agent workflow library, reusable workflow schema, pattern-to-skill conversion, skill pack design, exporter/validator behavior, curated coding-agent patterns, or wants to avoid prompt-library or hardcoded-script designs.

Diagnose failing CI by collecting fresh check evidence, reproducing the smallest failing command locally when possible, identifying one defensible root cause, and proposing a minimal fix plan. Use when CI is red, tests differ between local and remote, or the user asks for root cause before code changes. Do not use to bypass, delete, or weaken tests.

Create compact, evidence-backed handoff packs for long-running agent tasks. Use before context compaction, model/session handoff, task resumption, or when the user asks for exact current status across files, constraints, tests, decisions, blockers, and next action. Do not use for trivial one-command tasks with no durable state.

Review pull requests by collecting diff context, ranking behavioral risks, identifying missing tests, and producing verification commands. Use for non-trivial PR review, merge-readiness checks, review comment preparation, or turning review findings into a focused fix plan. Do not use for pure formatting review or to approve/merge without a human gate.

Improve GitHub and open-source repository SEO/discoverability across GitHub metadata, README/docs, package registries, GitHub Pages or docs sites, Google Search Console, and release verification. Use when the user asks why a repo/package cannot be found on Google, npm, crates.io, PyPI, etc.; asks to do SEO for a GitHub repo; needs README/package metadata optimization; wants Search Console submission; needs branded package scope planning for public repos; or wants evidence-backed repo/package/site discoverability audits.

Plan and review SEO content, keyword maps, content briefs, GEO/AEO readiness, AI-search citation potential, FAQ/schema opportunities, and comparison/disambiguation pages. Use when Codex needs content strategy, long-tail page ideas, AI answer optimization, E-E-A-T/entity clarity, or launch/discoverability copy that should align with Shipwise positioning.

Choose and document SEO data sources and MCP/provider boundaries for audits. Use when Codex needs to decide between local scripts, Firecrawl, Google Search Console, PageSpeed Insights, CrUX, DataForSEO, SE Ranking, Ahrefs, browser checks, or paid/live integrations; or when SEO findings require explicit source, cost, account, API-key, and confidence boundaries.

Run evidence-backed technical SEO audits for websites, docs sites, landing pages, and GitHub Pages properties. Use when Codex needs to inspect crawlability, title/meta/canonical tags, robots.txt, sitemap.xml, Open Graph/Twitter metadata, JSON-LD/schema, status codes, redirect/canonical issues, internal links, JavaScript rendering risk, Core Web Vitals boundaries, or technical SEO issues for a site.