AI & ML

slash9494 Skill

Choose one external agent for bounded comparison work.

liuliuliushifu Bundle

Manage script-driven handoffs and responsibility-based dispatch between Codex agents across directories. Use when the user asks to pass results to another agent, wake another named agent, coordinate multi-agent work, return work upstream, inspect which agents participated in a goal, audit co-agent handoff history, or when the current registered agent is asked to do work outside its responsibilities and another registered agent appears to own that work.

gebilaoman Bundle

生成（并可直接打印）100以内口算练习 PDF，支持加法、减法、乘法、连加、连减、加减混合、乘加、乘减八种题型，按百分比占比混排，可多套多页、可出带答案的批改卷。Whenever the user wants oral-math / mental-math / arithmetic practice worksheets — 口算题、口算练习、算术练习卷、给孩子出题、打印练习卷、100以内加减乘 — use this skill, even if they don't say "PDF" or "skill". Also use it when an automation agent (OpenClaw / WorkBuddy) needs a programmatic entry point to auto-generate or auto-print such worksheets.

abdulyasir100 Skill

CC_GodMode v5.11.3 - Self-orchestrating multi-agent development workflows. Delegates tasks to 8 specialized agents: researcher, architect, api-guardian, builder, validator, tester, scribe, and github-manager. Automates new features, bug fixes, and API changes with dual quality gates.

liuliuliushifu Bundle

Track and query local Codex token usage by date, session, owner session, or registered agent. Use when the user asks how many Codex tokens were used on this machine, wants daily per-session/per-agent usage reports, asks questions like "skill agent 昨天消耗了多少 token", wants to inspect or install Stop/SubagentStop hook usage accounting, or wants to test whether agent/subagent hooks expose transcript token data.

andersonlimahw Bundle

Expert agent for the Apple Store Connect API. Use when the user asks questions about the App Store Connect API or needs to automate tasks involving TestFlight, In-App Purchases, Provisioning, App Metadata, Reporting, or Game Center.

andersonlimahw Bundle

Senior Prompt Engineer

resilientmindset01-commits Skill

Stop a coding agent starting every session from zero -- keep a small curated memory file it writes at the end of a session and reads at the start, so it stops re-asking what you already told it and stops repeating a wrong guess it already ruled out. Use when you work with Claude Code across more than one session on the same project. Distinguishes durable memory (decisions, conventions, dead ends) from transcript noise, and closes the "brilliant new hire with amnesia" gap. NOT a transcript dump -- dumping the old session back in tends to bury the one useful fact and slow the agent down (lost-in-the-middle).

howdow698-ui Skill

基于 LLM 的智能知识库管理工具，接收用户传入的新文章或内容，自动提取关键信息并整合到现有 wiki 中，更新实体页面、修订主题摘要、标记矛盾点。

jin-bo Bundle

OCR image files using the Qwen VL model via the bundled scripts/ocr.py (lives in this skill's directory, NOT your cwd). Use when the user asks to extract text from an image, perform OCR on a photo or screenshot, or recognize characters in an image file (.jpg, .jpeg, .png, .gif, .webp). Requires QWEN_API_KEY and QWEN_BASE_URL (env vars, or a .env in the skill directory).

jin-bo Bundle

使用 agentao-kanban 看板进行任务管理（拆任务 / 状态流转 / 后台服务 / 看产物）。 本技能负责：① 初始化 .kanban/ 项目 ② 把需求拆成原子卡片入板 ③ 推动状态流转 INBOX → READY → DOING → REVIEW → DONE ④ 启停 daemon 与 Web UI ⑤ 察看卡片状态与产物。 触发关键词（中/英）：看板 / kanban / 任务管理 / task board / 拆任务 / 任务卡 / 排期 / WIP / dispatcher / orchestrator。 复合触发短语（一键启停）： • "启动 kanban" → daemon（mock 执行器，后台）+ Web UI（自动开浏览器） • "启动 kanban 真跑" → daemon（--executor agentao，真调 sub-agent）+ Web UI • "停止 kanban" → 先停 Web UI，再停 daemon

andersonlimahw Bundle

ai-workspace-orchestrator plugin. Routes to its sub-skills: adversarial-setup-review, build-agent-orchestrator, context-handoff, setup-ai-workspace, workspace-contract, write-project-skill. Use when the task matches any of the capabilities listed below.

andersonlimahw Bundle

agent-sdk-dev plugin. Routes to its sub-skills: agent-sdk-dev, agent-sdk-verifier-py. Use when the task matches any of the capabilities listed below.

megana05082003 Bundle

AI驱动的电商评论深度分析工具，支持22维度智能标签、用户画像识别、VOC洞察和可视化看板生成。 当用户需要以下功能时触发： - 分析电商产品评论（Amazon/eBay/AliExpress等平台） - 从评论中提取用户画像、痛点和VOC（客户之声） - 生成产品洞察报告和机会点分析 - 创建专业的可视化分析看板 - 进行竞品分析和市场定位研究 触发关键词：电商评论分析、评论分析、竞品分析、用户洞察、VOC分析、产品优化、市场调研、评论数据挖掘 AI Agent 约束：必须通过 AskUserQuestion 收集分析数量、AI引擎选择、报告署名后再执行分析

andersonlimahw Bundle

Google Play Developer API knowledge base and automation expert. Use when interacting with or integrating the Google Play Developer API for publishing, in-app products, subscriptions, reviews, or reporting. Note that this skill provides the API knowledge (e.g. fastlane supply, googleapis endpoints) and differs from google-play-release-agent which is for release checklists and audits.

andersonlimahw Bundle

Design model-agnostic workflows using narrow typed decisions, deterministic composition, uncertainty routing, and measured token/cost comparisons. Use for typed AI decisions, bounded choice/score/binary-probability questions, structured-output routing, token-efficiency benchmarks, or replacing fragile LM parsing.

andersonlimahw Bundle

Design or review CLIs so coding agents can run them reliably: non-interactive flags, layered --help with examples, stdin/pipelines, fast actionable errors, idempotency, dry-run, and predictable structure. Use when building a CLI, adding commands, writing --help, or when the user mentions agent-friendly CLIs.

kewang0622 Skill

Diffusion MRI (dMRI) expert — acquisition, preprocessing, modeling, and tractography. Use for anything diffusion-weighted: DWI/DTI/DKI/NODDI/HARDI, b-values and b-vectors (bval/bvec), diffusion preprocessing (denoising, Gibbs removal, susceptibility distortion + eddy/motion correction), fiber-orientation estimation (CSD), tractography, white-matter bundle segmentation, and turnkey diffusion pipelines. Tools: MRtrix3, DIPY, FSL (eddy/topup/FDT), AMICO (NODDI), TractSeg, QSIPrep. Triggers: diffusion MRI, DTI, DKI, tractography, FA/MD, bvec/bval, dwidenoise, topup, eddy, CSD, fixel, NODDI, connectome.

kewang0622 Bundle

Actionable MRI image reconstruction — turn raw k-space into an image, and actually run it. Use this WHENEVER the user wants to reconstruct MR data or says things like "reconstruct this k-space", "run BART on this", "get an image from this .cfl / .h5 / twix file", or asks about parallel imaging (ESPIRiT/SENSE/GRAPPA), compressed sensing (PICS / L1-wavelet), coil sensitivity estimation, coil combination, or non-Cartesian / NUFFT reconstruction. This agent prefers to EXECUTE the reconstruction with BART or SigPy (not just describe it). Triggers: k-space, coil sensitivities, ESPIRiT, PICS, undersampled reconstruction, radial/spiral recon, `.cfl`/`.hdr`, ISMRMRD, Siemens twix, GE P-file.

kewang0622 Skill

Deep-learning MRI reconstruction expert. Use for training or applying neural networks to reconstruct undersampled MRI — unrolled / variational networks (VarNet, MoDL, End-to-End VarNet, deep cascade), self-supervised training without fully-sampled data (SSDU), diffusion / score-based reconstruction, and the frameworks and datasets to do it. Tools: DIRECT, fastMRI, mridc, torchkbnufft; datasets fastMRI / mridata. Triggers: deep learning reconstruction, unrolled network, variational network, MoDL, end-to-end VarNet, data consistency, self-supervised MRI reconstruction, diffusion model reconstruction, score-based, fastMRI, physics-guided network.

andersonlimahw Bundle

Reusable closed loop for exploratory QA over ANY live web app via the Chrome DevTools MCP. You trigger it → Claude navigates the app with full per-screen doc context → writes one markdown report per finding → you review → hand back for triage → fixes enter a Feature-Development loop. Product-agnostic: target URL, screen manifest and report paths come from chrome-qa-loop.config.json. Trigger with "/chrome-qa-loop", "qa loop", "explore the app", "test the live app", "chrome qa".

andersonlimahw Bundle

Routes tasks to the cheapest adequate agent, model, or provider using deterministic bypasses, calibrated escalation, and optional typed option scoring through smart-sub-agents. Use for features, fixes, refactors, or multi-step development where model tier, effort, cost, latency, or verification strategy matters.

andersonlimahw Bundle

Compacta a conversa atual em um documento de handoff para outro agent continuar o trabalho. Preserva o contexto sem duplicar artefatos.

andersonlimahw Skill

Ready-to-paste prompts for API and CLI tooling — OpenAPI specs from code, Postman collections, agent-friendly CLI design, generated CLIs from specs, and wrapping external CLIs for token savings.

andersonlimahw Skill

AI Tuning Loop. Goal: raise chat answer quality for one agent + category per iteration.

andersonlimahw Skill

Thoroughly verifies Python Agent SDK applications for correct setup and best practices.

andersonlimahw Skill

Ready-to-paste prompts for extending and operating the AI harness itself — prompt refinement, skill selection, decision-native routing, portable subagents, authoring skills and plugins, hooks, migration, and token economy.

andersonlimahw Bundle

Maintains docs/ in the Karpathy-style LLM-wiki standard. Generates docs/llms.txt (flat machine-readable index conforming to llmstxt.org), validates broken links, enforces a minimum front-matter in new .md files (title, status, updated, related), groups orphan docs. Use when the user says "update docs index", "generate llms.txt", "audit docs", "organize wiki", "cure documentation", or after adding/renaming a file in docs/.

andersonlimahw Skill

A comprehensive skill for creating new Agent SDK applications. Guides through creating TypeScript or Python SDK apps with verification.

andersonlimahw Bundle

Save a resumable handoff when a session's context/usage budget is nearly exhausted, so any AI runtime (Claude Code, Codex, Antigravity/Agy, OpenCode, Gemini CLI, or any future agent) can pick the work up with zero lost context. Use proactively when you estimate you're at or above ~90-95% of your context window, token budget, or usage limit for this session, OR when the user explicitly asks to "save a handoff", "prepare handoff", "continue later", or invokes this skill by name.

andersonlimahw Bundle

Creates and routes portable subagents by harness, provider, model, and effort, with optional calibrated typed-decision routing and safety floors. Use when a task needs explicit model selection, multi-provider delegation, dynamic effort, parallel subagents, probability-based routing, or configuration for Claude Code, Codex, OpenCode, Antigravity, Gemini CLI, or lemon-code.

andersonlimahw Bundle

Security review for generated code. Provides pattern warnings for known-dangerous patterns, LLM diff review for vulnerabilities, and agentic commit review.

andersonlimahw Skill

Ready-to-paste prompts for model-agnostic typed decisions — atomic choice/score/binary-probability design, provider adapters, runtime validation, uncertainty routing, and comparable token/cost benchmarks.

andersonlimahw Skill

Adversarial code review where the reviewer plays a senior/expert software engineer who owns and deeply knows this codebase, reviewing a Pull Request as if it was opened by a junior developer. Ships sensible defaults but offers interactive configuration: which model the reviewer uses, criticality/severity threshold, whether to post inline PR comments and then resolve them, review scope (working diff, staged, branch-vs-main, or a GitHub PR number), and optional auto-fix. Use when the user runs /code-review-adversary, says "review this PR as a senior", "adversarial review", "review as if I'm a junior", "revisa como sênior", "revisa essa PR com rigor", or wants a strict expert-grade review with mentoring feedback.

andersonlimahw Skill

Write compact handoff documents for AI workspace setup and agent orchestration work. Use when a session needs to transfer current decisions, suggested skills, open questions, and next actions to another agent or future session.

andersonlimahw Skill

Interactive AI workspace setup wizard for projects, monorepos, workspaces, and product domains. Use when the user wants to configure AGENTS.md/CLAUDE.md, choose low/medium/high/max setup depth, create global or project skills, or design agent/subagent orchestration.