AI Ml AI Skills

Build an ordered, evidence-linked incident timeline with first/last seen, dwell time and pivot points; use when a case spans multiple alerts, hosts or stages and needs a clear narrative.

Record environment, harness, or tooling issues that block or degrade agent work into an append-only, deduplicated log so the environment can be improved incrementally.

Odoo-specific grilling session that stress-tests addon plans, migrations, model/view/security designs, OWL frontend changes, and verification strategy. Use when the user wants to be grilled on an Odoo…

Review existing test cases (legacy, others', AI) for coverage and executability: build a testable-points baseline, assess independently, revise in place with records. Not for: writing cases from…

Advisory-only Kafka tuning for Confluent Cloud or Confluent Platform by priority: latency, throughput, availability, or durability. Use when asked to size a planned topic or tune an existing cluster,…

用百炼 CLI (`bl`) 走完"数据→微调训练→导出→部署→调用"的完整闭环，或跳过训练直接部署基座模型。支持文本模型（SFT/DPO/CPT）、音频 TTS 模型（CosyVoice）、图像生成模型（Wan2.7）和视频生成模型（Wan i2v/kf2v）微调。涵盖数据集校验/上传、创建微调任务、等待训练、导出最佳 checkpoint、创建推理部署、等待就绪、给出调用示例。当用户提到在百炼…

标签智能推断引擎 — 基于启发式规则和拓扑分析推断标签归属。触发词：智能推断标签、自动识别标签、标签建议

Audit live URLs using Playwright and Axe combined with WCAG skills

CVE blast-radius analysis — given a single CVE-ID, find every affected asset across all accounts, rank by real exposure (internet-facing, attack-path participant, crown jewel) instead of static CVSS.…

Create or update AnkaLoop skills. Use when designing, structuring, or packaging skills with scripts, references, and assets. This skill should be used when users want to create a new skill (or update…

Search file contents using regex patterns

Help users build effective AI applications. Use when someone is building with LLMs, writing prompts, designing AI features, implementing RAG, creating agents, running evals, or trying to improve AI…

Chief Operating Officer (COO) orchestrator for cross-functional execution, process design, delivery cadence governance, vendor escalation, resource arbitration, and operational playbooks. Orchestrates…

A skill nested one category level deep, exercising the catalog layout.

Guides the agent through adding, configuring, and using the Capawesome desktop platforms for Capacitor — @capawesome/capacitor-electron and @capawesome/capacitor-tauri. Covers choosing between…

Legal due diligence review for seed-stage and Series A startups (US, Delaware C-Corp focus). Supports both investor and founder perspectives. Capabilities include: (1) Interactive document review and…

Delegate an implementation task to Codex, then Claude reviews the result. Use when asked "codex rescue", "delegate to codex", "have codex do it", or wants Codex to implement or fix something.

从明·张介宾（张景岳）《类经图翼》卷一「运气上」、卷二「运气下」蒸馏出的运气学「图翼·象数基础」层框架——太极—阴阳—五行生成数—气数—五运（五天五运/五音建运太少相生/主客运）—六气（正化对化/主客气/司天在泉）—天符岁会—南北政脉不应，逐字照明本底本。用于「象数基础研读」与「图翼推算细节补足」，非临床指南。

Host hardening and ClawLite runtime health checklist with safe, approval-first operations.

DevOps 与运维专家。精通 CI/CD、容器化、编排、基础设施即代码、监控告警和自动化部署。用于构建高效、可靠的软件交付流水线和运维系统。

Create a high-quality pull request description for UX-related implementation that explains why the change exists, what behavior changed, design-system usage, states, accessibility, testing, risks, and…

Guide for llama.cpp, the C/C++ LLM inference framework by ggml-org. Covers the C API (llama.h), GGUF format, quantization (Q4_K_M, Q8_0, IQ4_XS), CMake builds, GPU backends (CUDA, Vulkan, Metal,…

Form UX and accessibility pass. Use for forms, inputs, checkout, signup/login, validation, labels, autocomplete, mobile keyboards, inline errors, required fields, disabled submits, and field-level…

Use when designing, building, or reviewing pricing pages, paywalls, free trials, subscription upgrade/downgrade flows, cancellation flows, or win-back campaigns. Also use when users report…

Enforces persistent product styling across sessions, preventing the AI from defaulting to its favorite generic aesthetic.

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

Maintain the AI Design Context knowledge graph. Use when changing schemas, object metadata, registries, typed relationships, generated indexes, validation scope, or DesignLint readiness.

Implement a Figma design with the merged ui-builder flow

Use to talk to the Discord-backed OpenClaw agent/session; not for archive search.

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback

Build a source-derived writing style profile from real posts, essays, launch notes, docs, or site copy, then reuse that profile across content, outreach, and social workflows. Use when the user wants…

Query Solana wallets, tokens, txs, and NFTs in USD.

Quick-reference card for caveman modes, skills and commands. Trigger: /caveman-help or "caveman help".

Set up or check claude-mem cloud sync with cmem.ai Pro. Use when the user says "set up cloud sync", "sync my memories", "cmem pro", "cloud backup", "sync status", or wants their memory database backed…

Use this skill when the user uploads Excel (.xlsx/.xls) or CSV files and wants to perform data analysis, generate statistics, create summaries, pivot tables, SQL queries, or any form of structured…

Read first to make, edit, animate or render any video with HyperFrames (HTML rendered to video), including launch films, explainers, music videos, charts, maps, vertical clips, title cards, captions…

Start a new OpenSpec change using the experimental artifact workflow. Use when the user wants to create a new feature, fix, or modification with a structured step-by-step approach. Also use when the…

Thorough, file-cited technical debt audit across 9 dimensions using AST-grep (tree-sitter), grep, LSP, and language-native tooling. Produces TECH_DEBT_AUDIT.md with severity, effort estimates, and…

Review local character animation with schema checks, Playwright browser previews, frame sampling, and FFmpeg/ffprobe final output checks.

Design and test explicit human, implicit model or agent, programmatic application, bounded skill-composition, and harness activation policies for an Agent Skill catalog.

Work out and record the architecture decisions that keep separately built parts of a system consistent, in a short architecture document. Creates, updates, or validates one; works from a spec, a raw…

Створення або оновлення файлів CLAUDE.md відповідно до найкращих практик для оптимального онбордингу AI-агента

Reorient in the current Claude Code session with an evidence-backed map of its goal, pivots, outcomes, current step, and open decisions.

Triage and resolve CentOS issues using RHEL-compatible tooling, SELinux-aware practices, and firewalld.

Generate domain permutations with dnstwist and check DNS resolution to detect typosquatting, homograph phishing, and brand impersonation domains registered against your organization. Use when asked to…

Create, analyze, proofread, and modify Office documents (.docx, .xlsx, .pptx) using the officecli CLI tool. Use when the user wants to create, inspect, check formatting, find issues, add charts, or…

Distributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. Built-in hyperparameter tuning with Ray Tune, fault tolerance, elastic scaling.…

Use when dealing with cognee database migrations — understanding when they run automatically, checking or repairing migration state with cognee-cli upgrade/downgrade/stamp/current, a write blocked by…

Perform a market analysis for a product category or segment. Trigger on: market analysis, market size, TAM SAM SOM, market opportunity, industry analysis.

Create, scaffold, customize, validate, and locally test Qwen Code extensions. Use when the user wants a new Qwen Code extension, needs help choosing an extension template, wants to add QWEN.md…

Analyze one discovery interview for observed behavior, needs, workarounds, and unanswered questions.