AI & ML

davidvkimball Bundle

Operations, syncing, versioning, and release management for Obsidian projects. Load when running builds, syncing references, bumping versions, or preparing for release.

davidvkimball Bundle

Technical references, manifest rules, file formats, and UX guidelines for Obsidian. Load when checking API details, manifest requirements, or UI/UX standards.

zeropointrepo-zillow-skills Bundle

Complete Zillow property data toolkit via the zillapi API. Looks up any US property by address, zillow.com URL or zpid and returns price, Zestimate, rent Zestimate, photos, schools, taxes, price history and listing agent contact; also searches for sale, for rent and sold listings by location and filters. Use when the user asks about a specific US property, home values, Zestimates, real estate listings, rentals, comps or housing data, or pastes a zillow.com link and asks about it. Do not use when an address appears incidentally (signatures, unrelated documents) or the conversation is abstract real estate talk with no specific property or search request.

openclaw Skill

Use acpx as a headless ACP CLI for agent-to-agent communication, including prompt/exec/sessions workflows, session scoping, queueing, permissions, output formats, system-prompt overrides, and multi-agent flows authored with defineFlow/decision/decisionEdge.

andreagriffiths11 Bundle

A persistent local-only memory system for AI coding agents. Two files, one idea — AGENTS.md (committed, shared) + .agents.local.md (gitignored, personal). Agents read both at session start, update the scratchpad at session end, and promote stable patterns over time. Works across Claude Code, Cursor, Copilot, Windsurf. Subagent-ready. No plugins, no infrastructure, no background processes.

deeqyaqub1-cmd Bundle

Intercept deterministic tasks (math, time, currency, files, scheduling) BEFORE they hit the LLM. Saves 50-70% on token costs by resolving simple queries locally with zero API calls.

solizardking Skill

Use the Agent Auth CLI (auth-agent) to discover providers, connect agents, manage capabilities, and execute operations. Use when the user wants to interact with an Agent Auth provider from the terminal, authenticate an agent, execute capabilities, or manage agent connections.

solizardking Skill

Use the Agent Auth MCP tools to discover providers, connect agents, manage capabilities, and execute operations through the MCP protocol. Use when working inside an MCP-enabled environment (Cursor, Claude Code, etc.) and need to authenticate agents, execute capabilities, or interact with Agent Auth providers.

callmedas69 Bundle

Register and manage AI agent identities, reputation, and validation on-chain via ERC-8004

influxdata Bundle

This skill should be used when the user asks to "run tests", "run the test suite", "check test results", "why are tests failing", "debug test failures", "add a test", "write a test", "update EXPECTED_TOOL_COUNT", "run protocol tests", "run integration tests", "test against InfluxDB", or needs to run, analyze, extend, or troubleshoot the MCP server test suite.

fcavalcantirj-proactive-amcp Bundle

Your agent's safety net. Watchdog resurrection, free IPFS pinning via Solvr, learning commands (/remember, /stuck, /learned), and a plugin that checkpoints automatically on lifecycle events.

apollographql Skill

Syncs MCP Apps documentation with the @apollo/client-ai-apps changelog. Always use this skill whenever: (1) the user wants to update or sync the mcp-apps-*.mdx docs based on a new release or version range, (2) phrases like "sync docs from version X", "update docs from changelog", "what changed since v0.x.x", "docs are out of date", or "check the changelog" appear in context of MCP Apps documentation, (3) checking whether mcp-apps-*.mdx files reflect recent releases. The changelog URL and doc file paths are pre-configured — the user only needs to provide the minimum version to sync from.

arun-mosai Skill

Use when continuing a vertical slice that was stopped mid-build — context exhausted, user ran /clear, session ended, validator stuck, or manual pause. Reads PROGRESS.md + INTAKE.md from the slice directory and picks up at the exact documented checkpoint without re-asking Phase 1 questions. Companion to /slice. Uses the same sub-agent delegation pattern. Invoked as /slice-resume or /slice-resume <SLICE_ID>.

kent-x1 Bundle

Purchase physical products through SP3ND with USDC on Solana. Use this skill to register an agent, create server-priced carts, place idempotent orders, handle manual-review and shipping-quote lifecycles, pay payment-ready orders through x402, and track fulfillment.

refined-element Skill

Scaffold a new MCP tool with models, service method, and DI registration

refined-element Skill

Prepare MCP package for publishing (version bump, changelog, validation)

ibm Bundle

Use this skill when a user wants to create, publish, or set up a new data product in IBM watsonx.data intelligence (wxdi) / Data Product Hub. Trigger when the user says things like "create a data product", "publish a dataset as a data product", "I want to share this data as a product", "set up a data product for X", "onboard this asset to the catalog as a product", or "build a data product from my data". This skill uses a file-based specification approach where data product definitions are created as JSON/YAML files in the workspace, reviewed and refined iteratively, then batch-submitted to DPH. This enables version control, collaboration, and reusability.

ouro-ai-labs Bundle

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

awslabs Bundle

Use when building or modifying a Swift app that uses the AgentSquad Swift framework — on-device multi-agent orchestration for iOS 16+ / macOS 14+: orchestrator, agents (Agent, GroundedAgent), classifier routing, LLM clients (OpenAI-compatible), tools (native + MCP), tool UIs/widgets, on-device storage, tracing, and realtime voice — built-in types and custom implementations.

lagz0ne Skill

Delegate well-scoped coding, analysis, and review tasks to the OpenAI Codex CLI (gpt-5.5) as a cross-model collaborator. Use for implementation chunks you want a second model to write or cross-check, independent second-opinion review of a design or diff, and applying Codex-authored changes. Triggers: "ask codex", "have codex implement/review X", "second opinion from codex", "cross-check with codex".

pymc-labs Bundle

Bayesian statistical modeling with PyMC v5+. Use when building probabilistic models, specifying priors, running MCMC inference, diagnosing convergence, or comparing models. Covers PyMC, ArviZ, pymc-bart, pymc-extras, nutpie, and JAX/NumPyro backends. Triggers on tasks involving: Bayesian inference, posterior sampling, hierarchical/multilevel models, GLMs, time series, Gaussian processes, BART, mixture models, prior/posterior predictive checks, MCMC diagnostics, LOO-CV, WAIC, model comparison, or causal inference with do/observe.

agentailor Bundle

Design and verify tools that AI agents can actually use — for any framework or language (MCP servers, LangChain/LangGraph, function-calling, raw JSON schema; TypeScript, Python, or otherwise). Use when writing a new tool for an agent, reviewing or fixing an existing tool definition, deciding how to split capabilities into tools, writing tests or evals for a tool, checking that a tool's output matches what its description promised, or debugging why an agent misuses, mis-selects, misreads the output of, or floods its context with a tool. Applies equally to standalone tools and MCP-server tools — a tool is a tool.

agentailor Bundle

Decide which AI agent behaviors are worth an eval case, then write those cases — harness-, framework-, and language-agnostic. Use when writing a first eval suite for an agent, adding cases to an existing one, reviewing eval cases or scorers someone else wrote, choosing between a deterministic check and an LLM judge, deciding how many times to repeat a case, or reading a red run and working out whether the agent or the grader is wrong. Also use when a tool or prompt change "needs an eval" and it is not clear what to actually test, or when an agent misbehaves in a way no unit test can catch. Covers cases, tasks, scorers, graders, evaluators, judges, and pass@k. Does not build eval harnesses — it detects one and asks before anything gets built.

agentailor Bundle

Comprehensive guide for designing, refining, and auditing system prompts for autonomous AI agents based on Anthropic's production practices. Use when creating or refining prompts for agents that operate in loops with tool access, including when asked to write agent instructions, system prompts, agent configurations, or when improving agent reliability and decision-making capabilities. Also use to audit a prompt that already exists — trimming one that has grown long, re-fitting it after upgrading or downgrading the model behind it, or debugging an agent that seems over-constrained.

hanlulong-econ-paper-review-skill Bundle

Review economics papers, working papers, theses, and submissions with referee-grade rigor and exhaustive verified comments. Use when the user asks to evaluate, referee, audit, stress-test, pre-review, find all problems, or comprehensively review empirical, experimental, descriptive, forecasting, prediction/ML, historical, archival, qualitative, meta-analytic, structural, quantitative, macro, theoretical, or mixed economics work; assess identification, inference, logic, equations, evidence, novelty, clarity, or journal readiness; or produce a grounded referee report, separate editing comments, optional requested journal-fit analysis, findings ledger, and prioritized fix plan. Use econ-review to judge papers; use econ-write to draft or rewrite paper text after the judgment is settled.

ihmissuti Skill

Audit websites for AI search visibility and Generative Engine Optimization (GEO). Use when auditing a website for LLM/AI search presence, checking how ChatGPT or Perplexity see a brand, or optimizing content for AI recommendations.

ihmissuti Skill

Generate and optimize Schema.org structured data for AI/LLM visibility. Use when adding schema markup, improving structured data, or optimizing for rich results and AI search engines.

sepinetam Bundle

Run a local smoke test for the Stata-MCP server.

sepinetam Bundle

Inspect, validate, summarize, and render local Stata-MCP audit evidence under .statamcp. Use when a user asks what tools ran, whether a security guard blocked anything, how one run links across JSONL files, whether snapshots are intact, or wants an interactive audit dashboard.

sepinetam Bundle

A packaged Stata Runner skill via official MCP-for-Stata server including stata_do, ado_package_install, help, read_log and get_data_info tools. Use it when (1) need to execute Stata do-file; (2) missing ado-packages; (3) find code error caused by syntax in Stata; (4) want to read smcl and text format log file with rich text output; (5) first encounter a data file and want to understand its structure and content.

strantalis Bundle

Run an iterative, hypothesis-driven “debug mode” loop to diagnose and fix a bug using targeted instrumentation and log capture. Use when the user wants an interactive debug loop, when you need to quickly narrow a failure via added debug statements, or when you need a lightweight way to centralize logs from a repro run (via `agent-skills debug` server + SSE UI).

0xpolygon Skill

Swap, bridge, and deposit on Polygon using the Polygon Agent CLI. Covers same-chain token swaps, cross-chain bridging, yield deposits into Aave v3 and Morpho vaults, and withdrawals from those positions. Write commands preview by default; add --broadcast (or enable `agent mode auto`) to execute.

0xpolygon Skill

Complete Polygon agent toolkit for on-chain operations on Polygon. Use this skill whenever helping an agent set up a wallet, check balances, send or swap tokens, bridge assets, deposit or withdraw from yield (Aave aTokens, ERC-4626 vaults), register on-chain identity, submit or query reputation/feedback, or make x402 micropayments. Covers the full lifecycle: OMS smart contract wallets, Trails DeFi actions, ERC-8004 identity + reputation, x402 payments. Single CLI entry point (`agent`), AES-256-GCM encrypted storage.

0xpolygon Skill

Place bets on Polymarket prediction markets using the Polygon Agent CLI (CLOB V2). Browse markets, check prices, buy YES/NO positions, sell positions, manage orders. Collateral is pUSD (auto-wrapped from USDC.e). All commands are JSON output. Dry-run by default — always add --broadcast to execute.

jeongjaesoon Skill

Install or refresh Agent Guard's plugin-local shell integration. Use when the user explicitly asks to enable or update shell command masking, or when a shell-integration warning directs them to rerun setup-shell.

jeongjaesoon Skill

Diagnose, install, and verify Agent Guard's plugin-local binary, jq and gitleaks dependencies, the active host integration, and live hook protection. Use when Agent Guard reports degraded protection, a SessionStart warning asks for setup, plugin hooks fail or appear bypassed, or a user asks to finish or repair Agent Guard installation.