majiayu000

Conduct deep web research using the openbrowser-ai agent: decompose a query, investigate sub-questions across multiple sources, and produce a cited markdown report plus structured JSON under local_docs/research/. Trigger when the user asks to: research a…

LLM token logprobs and calibration. Per-decision confidence, ECE, Brier, reliability diagrams, low-confidence triage.

Analyze LLM token logprobs and calibration. Use for per-decision confidence, ECE, Brier scores, reliability diagrams, and low-confidence triage.

回顾最近 N 天的 Claude Code 使用记录——扫描原始会话数据，按主题分组汇总"我都做了什么"，并从个人操作系统视角输出模式、风险与增删建议。当用户说 /recap、"看看我这几天做了什么"、"回顾一下我最近的会话"、"这两天我用 claude 干了啥"、"活动回顾" 时使用。

LLM-based text classification. Codebook, validation, agreement statistics.

Design and validate LLM-based text classification. Use for codebooks, prompts, validation samples, agreement statistics, and reporting model-coded data.

Train custom LoRAs with ostris AI-Toolkit — covers WAN 2.2/2.1 (people, styles, video motion) and Z-Image (Turbo & Base, low-VRAM image LoRAs). Use when the user wants to train a WAN or Z-Image LoRA; covers local + RunPod setup, dataset prep, key params, and…

Wenn es um /anpassen in diesem Spezialbereich geht: prüft Frist, Form, Zuständigkeit, Rechtsweg und Sofortmaßnahmen; liefert eine Fristen- und Risikoampel mit Sofortschritten.

用纯代码（three.js 离线渲染 + 合成音频）做有故事、有电影质感的动画短片并导出 MP4。当用户想做短片、动画片、宣传片、角色动画、循环视频、片头、产品故事片，或者说“用代码做个视频”“做一个有趣的短片”“帮我设计个小动画”“make a short film / animated video / motion piece with code”时使用，即使没提 three.js。也用于继续修改这类片子。写实真人、实拍感、AI 视频生成、普通视频剪辑不适用。

Turn any subject into an animated ASCII backdrop behind a UI, like a dark prompt page with jellyfish drawn in drifting characters, or a swarm of colour-tile bodies that veer away from the cursor. The subject is open-ended: creatures, objects, particles,…

Guide a self-help conversation for someone stuck in an avoidance loop: low mood, emptiness, stress, or loneliness they escape from with games, scrolling, or other distractions instead of facing. Use when the user says they keep avoiding a problem, feel empty…

Use when a project uses agent-qa and the user asks to validate its YAML, run a selected regression test, or triage a failed/healed run with memidex evidence. For a general app feature inventory, use app-user-story-qa.

Read-only checkup of installed agent skills across Claude Code and Codex: broken links or files, same-name copies that drifted apart, descriptions that compete or miss requests their skill already handles, and skills loaded by both agents but used by only…

只读统计 Claude/Codex 的 Skill 使用证据并检查 agent 配置健康。仅用于明确的健康检查、配置诊断、使用排行或低使用候选请求；会识别 enabled 插件并单列批量审计读取。哪些 skill 坏了、互相抢触发、点名却没触发、占用列表预算，或要用历史请求检验改写后的描述，改用 skill-checkup。不要用于规范源、全局/项目/profile/冷存储、投影或退役治理，改用 skill-ecosystem-doctor。忽略引用日志和相邻任务。

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…

优化实际模型推理链路，将正确性对齐、分段 profiling、显存与数据搬运、TensorRT/ONNX/PyTorch 后端、attention/kernel、FP8/compile、缓存与少步采样、质量回归、GPU 成本和服务验收串成同一实验闭环。当用户要求推理提速、降低显存或 GPU 成本、复现模型效果、定位 GPU 利用率低、优化图像/视频/扩散模型或自托管 LLM 时使用，提供 model inference performance optimization 的脱敏案例。纯 API 调用、提示词或…

扫描磁盘空间占用，找出可安全删除的缓存、编译产物、安装包等，交互式清理释放空间

Extract Figma designs and generate production-ready React/Next.js components with TypeScript, Tailwind CSS, and pixel-perfect accuracy.

在远程服务器上一键部署 OpenClaw。当用户需要安装 OpenClaw、部署 OpenClaw、配置 OpenClaw 到服务器时使用

通用项目部署到远程服务器。自动识别项目类型（Node.js/Python/Rust/Go/静态站），SSH 配置、环境安装、项目上传、进程管理、Nginx 反向代理、Cloudflare SSL、安全加固。当用户需要部署项目、上线服务、配置域名时使用

生成口播视频背景 PPT 幻灯片（16:9 横版 PNG 序列）。当用户需要做 PPT、生成幻灯片、做演示背景图时使用

Comprehensive logging system design guide. Use when designing log architecture, establishing logging standards, adding observability, or debugging production issues. Covers centralized configuration, field standards, and distributed tracing.

Modern TypeScript project architecture guide for 2025. Use when creating new TS projects, setting up configurations, or designing project structure. Covers tech stack selection, layered architecture, and best practices.

生成小红书文案和配图。当用户需要写小红书、生成社交媒体文案、小红书运营内容时使用

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

A synthetic regression fixture for a zero-width HTML break opportunity.

A synthetic regression fixture for formatted agent authority text.

Documents harmless platform-specific UI and branding overrides.

Formats local markdown summaries without network access.

Prints local TypeScript tutorial notes.

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.

LiteLLM-RS response caching architecture. Covers the two-tier deterministic cache (L1 in-memory + optional L2 Redis) behind LLMCache and DualCache, SHA-256 cache key generation with schema versioning, TTL and eviction policy, request-path wiring for chat…

LiteLLM-RS Configuration Architecture. Covers YAML loading with ${VAR} environment substitution, strict serde config models, startup validation via the Validate trait, and the LITELLM_* env-only fallback. Use when changing config models or serde defaults,…

LiteLLM-RS Observability Architecture. Covers the Prometheus-format metrics rendered by the metrics middleware and /metrics endpoint, health/readiness endpoints, request logging, and the OpenTelemetry/Datadog/Langfuse callback exporters. Use when adding or…

LiteLLM-RS Authentication Architecture. Covers JWT + API Key + RBAC multi-method auth, DashMap-backed rate limiting, the actix-web middleware pipeline, and credential management (gw- prefixed keys, HMAC hashing). Use when adding auth methods, debugging…

LiteLLM-RS Routing Architecture. Covers 7 routing strategies over immutable routing snapshots (ArcSwap) with atomic/DashMap state, health-aware deployment selection with cooldown circuit breaker, model-keyed fallback chains, and load balancing. Use when…

LiteLLM-RS provider system in two tiers - data-driven OpenAI-compatible catalog entries auto-routed through OpenAILikeProvider, plus code-based provider modules implementing the LLMProvider trait behind the closed Provider enum. Covers unified ProviderError…

LiteLLM-RS Provider 开发指南。用于添加新 provider（Tier 1 catalog 条目或 Tier 2 代码实现）、统一错误处理，或把旧错误枚举迁移到 ProviderError。

LiteLLM-RS Error Handling Architecture. Covers two-tier error hierarchy, ProviderError factory methods, HTTP status mapping, retry logic, and error context preservation. Use when designing error types or enums, creating ProviderError instances via factory…

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,…

Mine local Codex and Claude chat/session records into reusable agent workflow candidates. Use when the user asks to inspect agent chat history, find repeatable workflows, decide what should become a skill, compare new-skill candidates against existing skills,…

Create compact, evidence-backed handoff packs for long-running agent tasks. Use before context compaction, Codex/Claude session handoff, task resumption, or when the user asks for exact current status across files, constraints, tests, decisions, blockers,…

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…

Force an explicit review step before any agent-generated diff is applied, committed, or landed. Collect diff, run risk analysis, produce a review pack, and require human approval of the plan and risks. Use before git commit, push, PR creation, or direct…

Create, audit, and harden skills so they become self-maintaining instead of cat-and-mouse. Use when designing new skills, reviewing existing ones for drift, or turning brittle workflows into reliable ones. Forces Negative Examples, Verification Checkpoints,…

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…

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.

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.

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…

Audit and improve GitHub/open-source repository discoverability across GitHub metadata, README/docs, package registries, public docs sites, release verification, and Search Console readiness boundaries. Use when the user asks why a repo/package cannot be…

Plan and review SEO content, keyword maps, content briefs, GEO/AEO readiness, offsite brand evidence, AI-search citation potential, FAQ/schema opportunities, and comparison/disambiguation pages. Use when an agent needs content strategy, long-tail page ideas,…

Choose and document SEO data sources and MCP/provider boundaries for audits. Use when an agent needs to decide between local scripts, Firecrawl, Google Search Console, PageSpeed Insights, CrUX, DataForSEO, SE Ranking, Ahrefs, browser checks, or paid/live…

Run evidence-backed technical SEO audits for websites, docs sites, landing pages, and GitHub Pages properties. Use when an agent needs to inspect crawlability, title/meta/canonical tags, robots.txt, sitemap.xml, Open Graph/Twitter metadata, JSON-LD/schema,…

Use only when the user explicitly says implx or asks to invoke the SpecRail queue shortcut. Inventory and drain the authorized issue and PR queue from current GitHub state.

Use only when the user explicitly says SpecRail Heavy, heavy mode, or asks to invoke the SpecRail heavy profile. Provide deeper planning and repository-native verification.

Use only when the user explicitly says SpecRail core, asks to install or configure SpecRail, or says SpecRail without Heavy or implx. Never use for SpecRail Heavy, implx, or ordinary coding tasks.

Formats markdown tables nicely.

A totally harmless reader.

Helps you set up access.

Audit, position, design, generate, evaluate, and safely stage an evidence-backed GitHub profile README with Profile Control Plane. Use when a user asks to create, improve, redesign, or review a GitHub profile; choose a coherent profile story or archetype;…