AI & ML

audn-ai Skill

Register and verify an AI agent on Audn.ai for security testing. Supports text API agents (OpenAI, Anthropic, custom LLMs) and voice agents (Twilio, Genesys, Amazon Connect). Use when the user wants to add a new agent to test.

audn-ai Skill

Create custom adversarial attack scenarios for AI agent red-teaming. Supports prompt injection, jailbreak, data extraction, social engineering, emotional manipulation, and role confusion attacks. Use when the user wants to design a specific attack test.

loonghao Skill

Teaches AI agents how to use vx, the universal dev tool manager. Use when the project has vx.toml or .vx/, or when the user mentions vx, tool version management, or cross-platform setup. vx auto-manages Node.js, Python, Go, Rust, and 105 tools via Starlark DSL providers. Also covers MCP integration patterns and GitHub Actions.

surajhk Skill

A personal investment research agent. Runs a mandatory macro → opportunity scan → valuation → holdings sequence before any recommendation. Enforces portfolio discipline with dynamic concentration limits, exit rules, and tracks a watchlist and trade log across sessions.

zrtch Bundle

Count tokens and estimate costs for 300+ LLM models. Primary use: audit OpenClaw workspace token consumption (memory, persona, skills).

xukai-ye Bundle

Use when a coding task is medium or high-risk and Claude Code should do the main implementation work. Pass -Tier to select model preference: medium uses Sonnet 4.6 first, high-risk uses Opus 4.6 first. Codex reviews, verifies, and applies only short follow-up patches.

xukai-ye Bundle

Use for plan reviews and checkpoint reviews during implementation. Pass -Tier to select model preference: high-risk uses Opus 4.6 first, medium uses Sonnet 4.6 first. Supports relaxed cadence after 2 consecutive clean reviews.

isaac-flath Bundle

General-purpose OpenAI assistant for tasks requiring OpenAI-specific capabilities or GPT models. Use when you need OpenAI model features.

jack-pision Skill

Engineers backend systems for LLM-driven agents. Use when designing APIs, orchestrators, tool runtimes, persistence, jobs, auth, retrieval and memory services, approvals, budgets, and reliability controls.

jack-pision Skill

Database engineering skill for agentic systems. Use for schema design, migrations, query correctness, performance, transactions, multi-tenant boundaries, privacy, backups/rollback, and safe DB operations.

jack-pision Skill

Establishes reliability, safety, and release readiness for LLM-driven agents. Use for eval suites, adversarial testing, observability, budgets, policy gates, prompt-injection defenses, and rollout controls.

jack-pision Skill

Orchestrates production-grade LLM-driven agent systems in 2026. Use for agent architecture, control loops, topology choice, tool contracts, memory, approvals, safety boundaries, evals, and observability.

jack-pision Skill

Plans and specifies production-grade agent systems. Use when scoping work, writing implementation plans, defining state and tool contracts, sequencing milestones, and producing clear done criteria for LLM-driven systems.

jack-pision Skill

Designs production-grade AI agent experiences. Use for PRDs, user journeys, interaction models, trust and approval UX, failure handling, provenance, and measurable acceptance criteria for agentic products.

lucianfialho Bundle

Process multiple GitHub issues in parallel using agent teams

thanabordeen Bundle

Use SiYuan Note as a personal second memory and Knowledge Graph. Triggered when the user wants to remember, recall, link, organize, or reason over personal knowledge — including saving insights, creating concept maps, building topic clusters, logging decisions, and retrieving past context. This skill enforces three hard connection rules: every new document must link to at least one existing document (Mandatory Link Prompt), every outgoing link must create a matching backlink on the target (Backlink Enforcement), and orphan documents are tracked in a weekly review queue. Use it when the user says: 'remember this', 'save this idea', 'what do I know about X', 'link this to Y', 'build a concept map', 'add to my second brain', 'log this decision', 'what have I noted about Z', 'review my notes'.

maleick Bundle

Use when working against a local GhidraMCP GUI or headless server, especially for binary import, metadata verification, analysis, export checks, or raw endpoint access.

saolalab Skill

Framework for tracking and evaluating technology choices using a four-ring radar model. Use when evaluating new technologies, planning migrations, or maintaining the tech stack.

saolalab Skill

Search and install agent skills from agentskill.sh, the AI agent skills directory.

thanabordeen Bundle

A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. AI-Agent should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).

kwongfuk Skill

Enforce a general path planning and storage policy: keep /home for code, configs, manifests, and standard lightweight experiment results, while placing caches, environments, datasets, model weights, checkpoints, intermediate artifacts, and any large files under /scratch. Use when deciding where to create files, store outputs, download assets, configure caches, or lay out experiment directories.

kwongfuk Bundle

Run research/paper/code reproduction tasks with strict execution logging. Use when requests involve reproducing results, debugging training/evaluation pipelines, Slurm/HPC experiments, dataset/model setup, or iterative small-task execution where every subtask must be written to a repository-level CODEX_RECORD.md.

kwongfuk Bundle

Enforce safe Slurm job templates on Palmetto: keep /home for code and lightweight standard results, keep caches/checkpoints/models/data and other large files on /scratch, plus preflight safety checks, periodic low-noise GPU/process monitoring, resumable/atomic result saving, and signal-safe shutdown handling. Use whenever writing or updating sbatch scripts or long-running translation/training/inference jobs.

kwongfuk Bundle

Enforce Palmetto storage policy: keep /home for code, configs, and standard small experiment results, while placing Conda envs, caches, datasets, models, containers, checkpoints, and other large files under /scratch; run preflight checks for login-vs-compute node, GPU visibility, and CUDA tools/runtime before installs or training. Use when creating/updating envs, pulling HF models/datasets, preparing Apptainer images, debugging missing GPU/CUDA, or validating cluster node context.

enlivenapp Bundle

Comprehensive CodeIgniter 4 framework skill. Use when working with any CodeIgniter 4 project — routing, controllers, models, views, query builder, migrations, filters, services, Spark CLI, and Shield auth. Activates on mentions of "CodeIgniter", "CI4", "spark", "CI4 model", "CI4 controller", "CI4 route", or any CI4-specific pattern.

enlivenapp Bundle

Comprehensive CodeIgniter 4 Shield authentication and authorization skill. Use when working with Shield auth — session login, access tokens, HMAC tokens, JWT, groups, permissions, user model/entity, filters, email activation, two-factor auth, magic links, banning, force password reset, or customizing auth views/controllers. Activates on mentions of "Shield", "auth()", "loggedIn", "groups", "permissions", "access token", "HMAC", "JWT", "Email2FA", "EmailActivator", "magic link", "Shield filter", or any Shield-specific pattern in a CI4 context.

farawayshore Bundle

Use when Codex needs Markdown rather than JSON from MinerU, especially for local PDF directories that should become stable per-PDF `.md` artifacts with extracted linked assets, or for one-off small-PDF parsing through MinerU's lightweight Agent API.

ray-suton Bundle

Analyze machine learning problems with research-grade rigor. Use when the user wants strong technical reasoning about model choice, data regime, training dynamics, evaluation design, failure modes, ablations, or system-level ML tradeoffs across deep learning, LLMs, vision, tabular ML, probabilistic modeling, RL, and related areas.

ray-suton Bundle

Infer the real assignment or repository task from local evidence, then complete it end to end with explicit coordination, validation, and submission-ready reporting. Use when the user wants Codex to figure out what the repo most likely needs and execute it like coursework, lab, homework, or structured project delivery instead of answering a single narrow coding prompt.

juliushamm Bundle

Use the Obsidian MCP server to read, write, and search your Obsidian vault from Claude Code. Trigger when the user asks to save notes, check their vault, log meeting output, write to a daily note, search for prior context, or do anything involving Obsidian. Also trigger when asked to "remember" something that should persist as a note rather than a Claude memory.

doitintl Bundle

Use this skill when the user asks to integrate with the DoiT API, generate API code, build programmatic queries, or needs DoiT API reference. Triggers on requests like "call the DoiT API", "write code to query costs", "DoiT API example", "integrate DoiT into my app", or any DoiT API development task. For interactive cost queries and reports, prefer the doit-mcp-reporting skill instead.

doitintl Bundle

Set up the DoiT MCP server in supported clients and verify the connection flow. Use when the agent needs to configure ChatGPT, Claude, Claude Code, Codex, Cursor, or Gemini CLI for DoiT MCP access, produce the correct connection snippet, explain required credentials, or troubleshoot why a DoiT MCP client is not connecting.

doitintl Bundle

Use this skill ALWAYS when the user asks about cost anomalies, spending spikes, unexpected charges, or suspicious costs. Triggers on requests like "show anomalies", "why did my costs spike", "investigate this charge", "what happened to my spending", "unusual costs", "cost alert", or any anomaly analysis. This skill MUST be used before calling any DoiT anomaly MCP tools directly.

someant Bundle

Use MiniMax MCP to perform web searches and retrieve up-to-date information from the internet. Use when the user asks to search the web, find current information, look up news, or research topics online via MiniMax API.

someant Bundle

Use MiniMax MCP to analyze images, extract text (OCR), identify objects, describe visual content, and answer questions about images. Use when the user wants to understand, describe, or extract information from image files or URLs via MiniMax API.

az9713 Skill

Discovers and invokes agent skills. Use when starting a session or when you need to discover which skill applies to the current task. This is the meta-skill that governs how all other skills are discovered and invoked.