AI Ml AI Skills

Use when auditing a large local skill collection, identifying duplicate or imported skills, comparing skill roots, or deciding what to keep, disable, or archive across Codex and adjacent agent skill…

Run a dbt Fusion project with Astronomer Cosmos. Use when running a dbt Fusion project with Astronomer Cosmos (Cosmos 1.11+, ExecutionMode.LOCAL on Snowflake/Databricks). Before implementing, verify…

Help founders and marketers nail their positioning. Use when someone mentions "positioning," "value proposition," "who is this for," "how do I describe my product," "messaging," "ICP," "ideal…

Writing: voice creation and validation, prose editing, anti-AI cleanup, professional communication, translation.

Writes effective OKRs using Christina Wodtke's best practices and Google's OKR methodology. Use when setting goals, aligning teams, creating measurement frameworks, or tracking quarterly progress.

Runs multi step work the way a careful senior engineer would. Triage before code, a short PRD in prds/, task.md kept current, docs synced after, and lessons recorded when a mistake repeats. Use when a…

Track commit accumulation and trigger PR when thresholds crossed

Measure GTM with the metrics that matter (net developer retention, DREAM funnel) instead of vanity numbers. Use when the user has dashboards full of stars and pageviews but can't tell if go-to-market…

A relentless interview to sharpen a plan or design.

Comprehensive Flutter API reference guide covering widgets, Material Design, Cupertino, animations, gestures, navigation, state management, and platform integration. Use when developing Flutter…

Analyze traditional market context for an investment case by identifying the current regime, cycle position, market expectations, liquidity and macro transmission, positioning and crowd psychology,…

Queries local analytics across OrchestKit projects for agent usage, skill frequency, hook timing, team activity, session replay, cost estimation, and model delegation trends. Privacy-safe with hashed…

Analyzes a company's content to extract and codify their brand voice into a comprehensive style guide. Reads website copy, blog posts, emails, and social media to identify tone, vocabulary patterns,…

Deep research report generation for Reviva's built-in deep-researcher agent. Use for learning and education research, teacher preparation research, document-based synthesis, literature/source reviews,…

Generate and inject Frida hooks for dynamic instrumentation — license bypass, SSL pinning bypass, function tracing, crypto interception, anti-debug bypass. Supports attach and spawn modes.

TRIGGER THIS when crafting job descriptions, posting new roles, defining position requirements, creating hiring briefs, updating JDs, or structuring role expectations. Creates compelling, inclusive,…

Build a RAG (retrieval-augmented generation) pipeline or a custom search engine on top of Bright Data's Discover API — using intent-ranked web results + parsed page content as the retrieval/ingestion…

在这个工作区里教用户一项新技能或新概念。

Analyze company financial reports (10-K, 10-Q, annual reports) and extract actionable investment insights — statement quality, red flags, and a signal. For a structured section-by-section summary…

Create a ai image prompt with structured process, quality checks, and system integration

把尚有关键取舍的功能或系统想法收敛为设计。用于用户要求讨论方案或需求尚未明确时；不用于 bug 修复、配置修改或照已有方案实现。

用于【AI科幻】题材下的场景单元施工、章节微型剧本与抓眼开场。作为题材包装层、兼容入口与路由层，负责保留AI科幻标准入口名、补充数字空间压迫、系统阻力与数据痕迹入场口感，并明确要求优先强制加载并使用 `通用-执行场景单元`。关键词：AI科幻场景单元、系统界面、数据面板、服务器机房、数字日常异化。

面试向 LLM Wiki 全流程：Raw 层在 raw/ 沉淀 _research.md、basic/、blog/（见 references/raw-layer.md）；Wiki 层只读 raw/、编译维护 wiki/（实体/概念、index、log，见 references/wiki-layer.md）。触发：建资料包、收录博客、从 raw 导入…

Router skill for LLMQuant rates and FX workflows. Use when the user needs yield curve, duration, central-bank divergence, FX carry, real-rate, dollar, or cross-currency analysis.

Create context save points to preserve conversation state before breaks, risky changes, or compaction. Use when user says "save my progress", "create checkpoint", "mark this point", or before clearing…

自定义页面表格批量录入技能。使用 `YidaCodeCanvas` 组件和 antd Table、Input、Select、DatePicker、React hooks 实现草稿、行级校验、分批并发提交和行级错误保留。`YidaCodeCanvas` 组件内不能直接调用 this.utils.yida.*；写入默认消费发布层注入的…

Teach any topic deeply from first principles and build evidence-based paths toward exceptional capability. Use when a user asks to understand, explain, learn, or deep-dive into a topic; asks why or…

Resume an interrupted agent loop from last checkpoint

Manage email inboxes, list and search inbound messages, threads, sender filters, and reply to or forward messages. Use for building email agents that read and respond to incoming email.

Use when writing a strategy that captures short-squeeze setups on Hyperliquid perps — squeeze, short squeeze fuel, negative funding rally, fade the shorts, paid to long. Goes long when funding APR is…

The long-form-to-Shorts + sound-off captions mini-skill (Opus Clip / CapCut / Submagic). Use when someone wants to "clip my podcast/webinar/long video into Shorts," "make TikToks/Reels from a YouTube…

React to Doctrine entity lifecycle in Symfony with attribute listeners (#[AsDoctrineListener]/#[AsEntityListener], ORM 3) and lifecycle callbacks

Converts vague ideas into concrete, testable specifications with acceptance criteria. No implementation begins without a spec.

Create production-quality pixel art and animations programmatically. Use when the user asks to "create pixel art", "draw a sprite", "make pixel animation", "generate sprite sheet", "convert image to…

Solubility-optimized protein sequence design using SolubleMPNN. Use this skill when: (1) Designing for E. coli expression, (2) Optimizing solubility of designed proteins, (3) Reducing aggregation…

Manages testing lifecycle including unit tests, integration tests, validation, and quality assurance.

Color craft for agent-built interfaces: palette construction in OKLCH, the 60-30-10 discipline, one-accent rule, WCAG 2.2 contrast math, semantic tokens, color-blind-safe pairs, and dark mode mapping.…

Wibi Style 官方视觉风格：把一张照片转换成复古家居日志。家里任意角落的随手照片，客厅、卧室、咖啡台、书架都行。适用于用户要求复古家居日志，或明确调用 $home-journal 时。

Break LLM name defaults with external entropy. Use when character names cluster around statistical medians (Chen, Patel, Maya, Marcus), when cast has collision risks, or when fantasy cultures need…

Organize project files with intelligent consolidation

Unofficial read-only Persian news RSS: Mehr, Tabnak, Entekhab, Zoomit, Varzesh3, more. Use when the user asks about Iran News RSS (mehrnews.com) or wants news headlines or full news articles in Iran.

Creates, initializes, synchronizes, repairs, and publishes the portable English Copilot Toolbox, including its list, review workflow, Toolbox.aspx, and English HTML Toolbook. Blocks incomplete…

同时搭建看多与看空逻辑，比较证据强弱、关键变量与情景路径，帮助识别核心分歧。适用于防止确认偏误、研究前辩论、投资观点校验等场景。

Analyzes and manipulates spreadsheet data (Excel/CSV). Use when working with tabular data.

Use when animation needs to convey feeling, tell a story, or connect emotionally—character moments, dramatic beats, or any motion that should make the audience care.

Launch Day Autopilot — prepare everything for a product launch. Use when user wants to launch, go live, announce, or prepare for Product Hunt / Hacker News / social media launch.

Create production-ready GitHub Actions workflows for automated testing, building, and deploying applications. Use when setting up CI/CD with GitHub Actions, automating development workflows, or…

Query FDA drug labeling data via openFDA. Use whenever the user asks about drug prescribing information — indications, warnings, dosage, adverse reactions, contraindications, or administration routes.…

API gateways, reverse proxies, and service mesh (Kong, Traefik, NGINX) / API gateway, reverse proxy, dan service mesh (Kong, Traefik, NGINX).

Use when configuring Django to store static and media files on AWS S3 with django-storages. Invoke when working with the STORAGES setting, S3 buckets, presigned URLs, CloudFront, or boto3-backed file…

Prove that a knowledge base actually works before trusting it — after building or adopting docs, a knowledge graph, or a wiki, verify it can orient a fresh agent and resist false premises. Use at the…