AI Ml AI Skills

Run an honest market-fit and viability audit of any project or idea and produce a decision doc, not code. Use when someone asks "is this viable as a business", "audit the market fit", "make the case…

Check status of current or previous agent loop

Manage email suppressions (blocks), import and export suppression lists, and manage unsubscribe groups. Use for deliverability compliance and bounce handling.

Use when writing a profit-laddered position-adjustment strategy on Superior Trade — anything described as a grid bot, range fade, range harvest, ladder buy, scaling-in, pyramiding, or "buy more when…

Use to write a carousel — a swipeable multi-slide post (Instagram carousel, LinkedIn document/PDF carousel, or TikTok photo carousel) — one of the highest-save, highest-dwell formats. Run when the…

Optimize Doctrine fetching with DTO hydration (SELECT NEW; partial removed in ORM 3), lazy loading, query hints, and DBAL 4 access

Build in verifiable increments. Never implement more than can be tested right now. Ship partial working systems over complete broken ones.

Decide module boundaries before the first file: what modules exist, which way dependencies point, who owns state, and what each module may know. Use when starting a project, service, site, API, or…

Access UniProt for protein sequence and annotation retrieval. Use this skill when: (1) Looking up protein sequences by accession, (2) Finding functional annotations, (3) Getting domain boundaries, (4)…

Diagnoses and resolves MCP server registration failures, GPU detection, BigQuery authentication, index build failures, import errors, search quality issues, and performance problems.

Structured visual and usability audit of existing interfaces — landing pages, SaaS apps, portfolios. Screenshot-first review against taste rules, Nielsen heuristics, and accessibility floor;…

Wibi Style 官方视觉风格：把一张照片转换成虹彩柔焦长曝光。想要朦胧氛围的人物近景或局部特写。适用于用户要求虹彩柔焦长曝光，或明确调用 $iridescent-long-exposure 时。

Analyze session errors and suggest improvements

Unofficial read-only Iran earthquakes: latest, search, strongest, detail, stats (USGS, EMSC, IRSC). Use when the user asks about Iran Earthquakes (irsc.ut.ac.ir) or wants recent or past earthquake…

Analyze selected construction images, create missing object metadata columns, and write concise visual metadata back to SharePoint columns using explicit image-analysis, list-schema, list-update, and…

把公司如何获客、交付、定价、赚钱和扩张的逻辑拆解清楚，帮助快速理解业务运转方式。适用于看不懂公司业务、研究前补基础、业务结构梳理等场景。

Performs structured research and synthesizes information. Use when researching topics.

Use when motion needs to read clearly and powerfully—broad comedy, action highlights, important story beats, or any moment that must unmistakably communicate to the audience.

Manage project learnings across sessions. Save, search, recall, digest, prune, and export learnings that compound over time. Use when user wants to record, recall, or share project knowledge.

Build GitLab CI/CD pipelines with multi-stage workflows, caching, and distributed runners for scalable automation. Use when implementing GitLab CI/CD, optimizing pipeline performance, or setting up…

Assess OpenTelemetry package and Collector upgrades across ecosystems. Use when choosing or validating API, SDK, instrumentation, exporter, Collector distribution, component, image, chart, Operator,…

Specifies interaction choices, action scope, reversibility, recovery, and reachable states. Use when asked to "design the flow", "should delete be undoable", "choose the control", or "review this…

| HTML 质量门禁 skill（路线 A + 路线 B 共享）。对 doc-typeset（路线 A）或 doc-edit（路线 B）输出的 HTML 进行 5 维度质量检测（design-token 合规性、结构完整性、排版合理性、文体契合度、装饰使用合理性），输出结构化检测报告，不通过则打回上游做一次定向修正（不循环）。 在 generate_word 路线 A 和路线 B 流水线中，每次…

Query the DrugMechDB drug mechanism-of-action database. Use whenever the user asks about drug mechanisms, drug-to-disease paths, biological targets of a drug, or wants to look up any biomedical entity…

Deep application architecture audit, bottleneck detection, and perf / Audit arsitektur aplikasi mendalam, deteksi bottleneck, dan optimasi.

Roo Code's Bedrock provider silently disables caching for custom ARNs. Populate cachableFields to fix.

Use when building .NET 8 applications with minimal APIs, clean architecture, or cloud-native microservices. Invoke for Entity Framework Core, CQRS with MediatR, JWT authentication, AOT compilation.

Build GraphRAG retrieval pipelines on Neo4j using the neo4j-graphrag Python package (v1.16.0+). Covers retriever selection (VectorRetriever, HybridRetriever, VectorCypherRetriever,…

Optimize LLM prompts, tools, and agents in Opik using standardized optimizer workflows (prompt optimization, tool optimization, and parameter tuning), dataset/metric wiring, and result interpretation.

Core Web Vitals Reference — LCP, INP, CLS thresholds, root causes, optimization fixes, CrUX BigQuery queries, web-vitals library usage, and SEO impact

Add push notifications (FCM) to an Android v6 CometChat app — Firebase + Dashboard provider setup, the push dependency, token registration after login, token refresh, unregister on logout,…

将用户的研究描述转换为高质量学术图表，自动推荐最佳图表类型并生成matplotlib/seaborn代码，输出≥300 DPI的PDF/SVG/PNG。

Read and analyze the UniFi router/console: WAN and internet health, adopted access points and switches, connected clients, VLANs and networks, firmware status. Use this whenever the user asks about…

Update an existing MCP server on a live LiteLLM proxy. Ask for the server_id and what to change (URL, auth, description), then call PUT /v1/mcp/server.

Authoring guide for Python user agents (type:"user") on the Friday platform via the friday-agent-sdk. Covers the @agent decorator, AgentContext capabilities (ctx.llm, ctx.http, ctx.tools, ctx.stream),…

Add and manage evaluation results in Hugging Face model cards. Supports extracting eval tables from README content, importing scores from Artificial Analysis API, and running custom model evaluations…

爱情类型视觉设计预设。触发词：爱情、浪漫、温暖、亲密、心动、告白。用于明确需要此类型的画面设计、图像/视频提示词、视觉参数查询与诊断；保留摄影、光色、空间、动作、材质、连续性及 style_route/style_module 接口。

Diagnoses and improves measured latency, throughput, memory, CPU, bundle, rendering, query, or resource performance by defining a target, profiling a representative workload, locating the bottleneck,…

Security-first auditing of AI-generated code — Level 1 quick checks during /toh-dev and /toh-test (hardcoded secrets, dangerous code execution, obvious injection vectors) and Level 2 full audits for…

Generate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment…

当优化代码性能时，分析算法复杂度，优化数据结构，解决性能瓶颈。验证优化效果，设计高效代码，和最佳实践。

Provides guidance for fine-tuning large language models with Axolotl, covering YAML training configs, LoRA and QLoRA, preference training with DPO, KTO, ORPO and GRPO, multimodal models, FSDP and…

Wire a rigged character end to end: real clips and bones, locomotion states, method tracks, root motion.

Find and fix WCAG 2.2 accessibility issues. Two modes — report (sweep a codebase or page, produce a prioritized written report, no edits) and fix (audit→edit→verify loop on a target). Prefers…

Пакет ручного внесения правок - по двум версиям модулей 1С строит инструкцию для Конфигуратора (что найти и на что заменить целиком). Нужен когда править исходники нельзя: объект на поддержке без…

Designs session lifecycle for coding-agent runtimes. Use when implementing resume, transcript restoration, checkpoint rewind, cross-worktree recovery, or session-state persistence.

Monitor and analyze Plex Media Server usage via Tautulli analytics API. Use when the user asks to "check Tautulli", "Plex analytics", "watch statistics", "current streams", "who's watching", "Plex…

Use when the execution plan is approved and it is time for parallel execution — dispatches workers through crew leads to implement work packages with TDD enforcement, report collection, and escalation…

This skill should be used when the user has a spec or requirements for a multi-step task before touching code.

This skill should be used when a model gets read-write control over its own live context window instead of a harness-scheduled compaction policy: the context exposed as an editable file the model…

Plan molecular dynamics post-processing for materials simulations, including RDF, MSD and diffusion, VACF/VDOS, coordination numbers, bond-angle distributions, stress-strain curves, equilibration…