Loading...
Loading...
Found 77 Skills
Validate agent skills for correctness, readability, workflow clarity, and isolation, ensuring they can be installed independently without dependencies on other skills.
Agent harness performance system for Claude Code and other AI coding agents — skills, instincts, memory, hooks, commands, and security scanning
Review and analyze a skill against best practices for length, intent scope, and trigger patterns
Evaluates and optimizes agent skills using a DSPy-powered GEPA (Generate/Evaluate/Propose/Apply) loop. Loads scenario YAML files as DSPy datasets, scores outputs with pattern-matching metrics, and optimizes prompts via BootstrapFewShot or MIPROv2 teleprompters. Also generates new scenario YAML files from skill descriptions.
Quick install of the Google Workspace CLI (gws) on an additional machine using existing OAuth credentials. Requires client_secret.json from a previous gws-setup. Use when setting up gws on a new computer, reinstalling after a fresh OS, or configuring a second workstation. Triggers: "install gws", "gws on new machine", "gws install", "set up gws again".
Set up the Google Workspace CLI (gws) from scratch. Guides through GCP project creation, OAuth credentials, authentication, and installing 90+ agent skills for Claude Code. Use when setting up gws for the first time, configuring Google Workspace API access, or troubleshooting gws auth issues. Triggers: "set up gws", "google workspace cli", "gws setup", "install gws".
Use when creating a new skill, adding a skill to the user's setup, or the user says "make this a skill". All personal skills live in the arjit-skills monorepo and are symlinked into place.
Apple Human Interface Guidelines as 14 agent skills covering platforms, foundations, components, patterns, inputs, and technologies for iOS, macOS, visionOS, watchOS, and tvOS.
Improve prompts with design specs and UI/UX vocabulary. Useful for design-to-code workflows and clarifying requests for visual output.
Transform rough ideas into fully-formed designs through structured questioning and alternative exploration. Useful early in concept work.
Improve an existing skill in diegocanepa/agent-skills based on conversation learnings and submit the changes via a Pull Request.
Index skill for the blockint-skills bundle—includes a “choosing a skill” routing map and routes to focused skills on blockchain intelligence fundamentals, address clustering, analytics, tokenomics, investigation ethics, Phalcon Compliance documentation pointer, Chainalysis public Sanctions API/oracle router, FATF official AML/CFT glossary, Arkham Intel research article on leading crypto analysis tools for traders, Christoph Michel cmichel.io guide on becoming an EVM smart contract auditor, risk exposure, behavioral risk, address and transaction screening workflow concepts, Range AI investigation playbook (MCP), crypto market mechanics, OSINT (Bellingcat toolkit), Solana external stacks (Helius, Range MCP, Tavily, PayAI, React Flow, Solana Policy Institute), DeFi/MEV/rug skills, privileged-access mitigation lessons (Chainalysis Drift case study), coral-xyz sealevel-attacks Solana security examples, Neodyme Solana Security Workshop (workshop.neodyme.io), Osec (osec.io) Solana auditor introduction blog post, canonical X post citation for @armaniferrante status 1411589629384355840, BlockchainSpider open-source data collection, MoTS (Know Your Transactions / transaction semantics research repo), Impersonator dApp devtools (EVM + Solana read-only address presentation), Katana web crawling, lcamtuf American Fuzzy Lop (AFL) classic documentation (lcamtuf.coredump.cx/afl), and the official Agent Skills open-format specification (agentskills/agentskills, agentskills.io/llms.txt doc index). Use when the task spans multiple topics or the user needs help picking which named skill to load.