AI Ml AI Skills

Inactive-identity cleanup - finds inactive identities (users, groups, and non-human identities) across an account, business unit, or tag in every cloud provider Orca supports (AWS, Azure incl. Entra…

Search the user's long-term memory for stored facts and past context. Use when the user references something personal, past conversations, or people/projects by name. Do NOT use for current events,…

Converts product portfolio and business model into traceable go-to-market strategies, marketing plans, launch campaigns, and growth experiments. Use when planning market entry, launches, marketing…

Guides the agent through installing, configuring, and using Capacitor plugins from six sources — official Capacitor plugins, Capawesome plugins, Capacitor Community plugins, Capacitor Firebase…

Check the Codex CLI, sign-in and the Official plugin, and set the default model and effort in config.toml.

从《医宗金鉴》卷三十五「编辑运气要诀」（清·吴谦等编纂）蒸馏出的运气推算全框架——太极阴阳、五行生克、五运六气、脏腑经络映射、天符岁会、南北政、运气为病。用于"按年干支回查运气格局与病机框架"与"运气推算研读"，非临床处方指南。

Maintain stable user and project facts across sessions using workspace memory files and runtime memory state.

当用户明确要求优化镜像源、配置国内镜像、加速部署或切换依赖源时使用。分析项目技术栈并生成适配的镜像配置。⚠️ 不适用：用户只是询问镜像源概念、无需部署加速，或明确要求使用官方源。

Use when the user asks to validate a GitHub issue with Fable 5.1 and then autonomously drive it to a reviewed PR in one shot — "fable-validate-loop", "fable validate and work on #N", "fully automate…

Decide whether a UX need should reuse, compose, extend, or create a design-system component or pattern. Use when a designer asks whether something needs a new component, how a design fits the current…

Use when an interface needs purposeful feedback, transitions, or reduced-motion behavior, especially when animation risks jank, interruption bugs, or hidden no-JS content.

Use for dedicated mobile, tablet, ultrawide, touch, or breakpoint design passes where content priority, layout, navigation, imagery, interaction, and motion must be recomposed rather than simply…

Use when designing, building, or reviewing sharing, invite, or collaboration features — share dialogs, permission levels, link sharing, team invites, access requests, or presence indicators. Also use…

Master orchestration layer for Universal UI Skills v2. Orchestrates the rigorous design pipeline from Brief to Pre-Flight with first-class media and scroll storytelling.

Logo Outro Frame (Open Design) — use only when explicitly invoked, not for general design requests

Frame product direction for consumer workflows. Use when a feature needs a user goal, primary action, core object model, state coverage, or research-backed pattern selection before UI design.

Toggle or inspect the rtk token-filter mode used by /front-agent for the current session. Plugin-scoped; no global hook.

GitHub archive: issue/PR search, sync freshness, duplicate clusters, current GitHub handoff, and Gitcrawl repo work.

Use when creating new skills, editing existing skills, or verifying skills work before deployment

ASCII art: pyfiglet, cowsay, boxes, image-to-ascii.

Compressed code review - one line per finding with location, problem and fix. Use for /caveman-review, "review this PR", or "review the diff".

Build and query AI-powered knowledge bases from claude-mem observations. Use when users want to create focused "brains" from their observation history, ask questions about past work patterns, or…

Overlay doctrine for captions in HyperFrames videos — the caption MODEL (drop / rail / embed) and the rule that captions are an OVERLAY composited on top of the film, never a reserved bottom band you…

Update an OpenSpec change by revising its existing planning artifacts and keeping them coherent with one another. Use when the user wants to revise a change's plan, fold new decisions into it, or…

Use when Codex needs to understand or respond to automatic comment-checker feedback emitted after an edit-like PostToolUse hook.

DashScope (Alibaba Cloud Bailian / 阿里云百炼) integration — image generation (qwen-image-2.0-pro), text-to-speech (qwen3-tts-flash), and ASR with word-level timestamps (qwen3-asr-flash-filetrans). Use…

AI-native tutor and onboarding workflow for the four independent Claude certification tracks in AI Engineering from Scratch. Use when a learner wants to choose a Claude certification, prepare for…

Review code changes with several independent reviewers in parallel, then triage and present the findings. Use when the user says "run code review" or "review this code"

Technology-agnostic prompt generator that creates customizable AI prompts for scanning codebases and identifying high-quality code exemplars. Supports multiple programming languages (.NET, Java,…

Parses the Windows Amcache.hve registry hive with Eric Zimmerman's AmcacheParser and Timeline Explorer to extract evidence of program execution, application installation, and driver loading, including…

Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support

Use when the user wants to run the cognee API server (and optional UI) on their own machine — starting it, checking it's healthy, connecting the SDK or other clients to it, and choosing the right auth…

Use when processing large PDFs, document collections, or bulk text extraction tasks that benefit from GPU-accelerated processing. Triggers when the user provides large documents or needs bulk document…

Answer any question about Qwen Code usage, features, configuration, and troubleshooting by referencing the official user documentation. Also helps users view or modify their settings.json. Invoke with…

Recover the last verified state of an interrupted task and identify the next useful action.

Mandatory orchestrator for all LifeOS skill work — creating, editing, adding a workflow or tool, renaming, validating, or canonicalizing any skill. Handrolling skill files is forbidden; owns the full…

Expert knowledge for AI lead generation — web research, enrichment, scoring, deduplication, and report generation

Manage GPU compute jobs on the Qizhi (启智) platform using qzcli — a kubectl-style CLI tool. Use when user says "qzcli", "启智平台", "submit job", "stop job", "查计算组", "avail", "list jobs", "batch submit",…

KubeSphere Gateway extension management Skill (ingress-nginx based, uses Kubernetes Ingress API + Gateway CRD gateway.kubesphere.io/v2alpha2). For the newer Kubernetes Gateway API (Traefik +…

AI Berkshire skill: 管理层纵深研究：买股票就是买人. Source: skills/management-deep-dive.md.

Complete Foundry PoC writing guide + all cheatcodes + DeFiHackLabs reproduction patterns. Use this when building a proof of concept exploit, setting up a fork test, using Foundry cheatcodes, or…

Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with minimal accuracy loss, or…

Review prompt and tool-description changes in a branch or PR. Use when asked to audit system prompts, prompt builders, tool descriptions, prompt inputs, or nearby evals/tests; summarize what changed;…

Maintain the Phoenix llms.txt documentation index at docs/phoenix/llms.txt — the machine-readable docs map used by AI agents and the `px docs fetch` CLI. Use this skill whenever adding, auditing, or…

Prepare likely interview questions, STAR answer scripts and mock follow-ups from a resume and target role, delivered as Markdown

长文任意语言互译、术语一致性、分段续跑与章节审校方法。Used by InkOS translation workers.

Optimize web performance: bundle size, images, caching, lazy loading, and overall page speed. Use when site is slow, reducing bundle size, fixing layout shifts, improving Time to Interactive, or…

Create a new academic paper or LaTeX manuscript through a citation-aware drafting and validation DAG; explicit full/PDF requests include artifact compilation. Do not use for repairing an existing…

Walk users through the SDD workflow on the real codebase. Trigger: orchestrator launches onboarding for the full SDD cycle.

后渗透/提权+凭据破解+密码学:反弹shell,Linux/Windows提权,横向,隧道,免杀,C2持久化,hashcat/Padding Oracle/hash长度扩展。Use when post-exploitation, privilege escalation, lateral movement, or cracking crypto.

Detect tool misuse and unexpected code execution via dialogue testing. Use when the agent exposes file, code-execution, or network tools.