Shape agent capabilities into your workflow.

Ian Handdrawn PPT helps Codex turn articles, course notes, outlines, or talks into a visual sequence before generating the pages. It produces a 21:9 cover, 16:9 hand-drawn Chinese explanation images, and a contact sheet for reviewing consistency. The workflow is suited to article illustrations, lessons, and knowledge cards, but its deliverables are PNG page images rather than editable PPTX, PDF, vector, or interactive files.

iPolloWork combines agent conversations, files, a browser, editable canvases, design controls, and a video timeline in a local-first workspace. Users can ask an agent to produce code, documents, presentations, websites, or scenes, then directly revise text, images, layout, responsive states, and timing. It can be extended with models, Skills, plugins, and MCP, but there is currently no public installer, so use requires a source build; the source-available license also restricts external commercial use.

Caliber analyzes a repository and creates tailored context files, rules, skills, and MCP settings for tools such as Claude Code, Cursor, Codex, OpenCode, and GitHub Copilot. After setup, refresh hooks keep those files aligned with code changes. Proposed edits are shown as diffs and backed up, while generation uses an existing agent subscription or a user-provided model key.

This large library supplies reusable skills for product, engineering, marketing, legal, finance, careers, and many other professional tasks. Users can try skills in a browser or install them through CLI, MCP, and several agent platforms, with tools for search and chained document or slide workflows. Because the monorepo is extensive, most users will want only selected skills or bundles.

Use Hope Agent as a desktop assistant that remembers prior work and keeps long-running goals moving through resumable workflows and multiple agents. The same conversation can move between the native app, a browser, and messaging channels, or run continuously as a server on a NAS or cloud host. macOS is the primary supported environment; Linux and Windows remain less mature, and direct computer control is currently macOS-only.

This skill set measures repeatable clean and incremental Xcode builds, then examines Swift compile hotspots, schemes, build settings, script phases, target dependencies, and Swift Package Manager costs. The orchestrator produces an optimization plan before touching project files. Approved changes can then be applied by a fixer skill and checked with another benchmark run.

Google Calendar MCP Server lets an AI assistant query multiple accounts and calendars together, detect conflicts, check free or busy time, and create, update, delete, search, or respond to events, including recurring ones. It can also derive events from images, PDFs, or web links, and administrators may expose only selected tools. Setup requires a Google Cloud project with the Calendar API enabled, desktop OAuth credentials, and an initial browser authorization; test-mode tokens normally expire after seven days.

Give a compatible AI agent repeatable workflows for solopreneur tasks such as SEO and GEO optimization, demand research across social platforms, domain comparison, and creating logos or banners. OPC Skills installs through the common skills CLI across Claude Code, Cursor, Codex, Gemini CLI, and other tools, so these workflows can stay inside an existing agent setup.

thClaws is an open-source agent harness that exposes a desktop GUI, CLI, headless mode, and web app from one Rust binary. It lets you switch among hosted or local model providers, attach MCP servers and skills, use persistent memory and knowledge bases, and coordinate scheduled jobs or agent teams without changing runtimes. Prebuilt releases cover macOS, Windows, and Linux. On headless Linux machines, the GUI build may require Wayland and WebKit libraries, while the CLI mode avoids those desktop dependencies.

TUUI is a desktop LLM chat and experimentation workspace built around the Model Context Protocol. It lets users configure hosted or self-managed model endpoints and work with MCP tools, prompts, resources, sampling, elicitation, registry discovery, and MCP bundles. The application is available as a direct download, but MCP use requires a model backend with tool calling and the appropriate Node.js, Python/uv, or Docker runtime for each configured server.

Keinsaas Navigator is an open-source AI workspace for individuals and teams. It combines multi-provider chat with custom agents, MCP tools, visual workflows, and optional capabilities such as image generation, code execution, and realtime voice interaction. The application can run locally, in Docker, or on Vercel. A model-provider API key is the minimum requirement, while features such as web search, file storage, or particular integrations need their own service configuration.

iOS Simulator Skill for Claude Code wraps xcodebuild for builds and tests, then uses simctl and optional idb to navigate simulators through accessibility semantics rather than fragile coordinates. Its 27 scripts cover logs, screenshots, permissions, device lifecycle, accessibility checks, and visual diffs, with progressive result caching to keep agent output focused. It requires macOS 12+, Xcode Command Line Tools, and Python 3; idb and Pillow are optional.

ResumeSkills covers ATS checks, job matching, truthful resume tailoring, stronger achievement bullets, cover letters, LinkedIn profiles, interview stories, salary negotiation, and offer comparison. It includes workflows for technical, executive, academic, creative, and career-changing candidates. The set is designed for job seekers who want structured help across the application process rather than a single resume rewrite.

Bring domain guides, specialist-agent instructions, and multi-step workflows from the Claude Code ecosystem into Google Antigravity's skill format. The vault spans software development, infrastructure, security, and business work, but Antigravity loads metadata for every installed skill at session start, so targeted installation is recommended over adding the entire collection.

SkillNet offers a public skill library, Python SDK, CLI, and visual explorer for keyword or semantic search and GitHub installation. It can also create skills from repositories, documents, prompts, or execution traces, evaluate their readiness, and infer relationships between them; public search and downloads are credential-free, while creation, evaluation, and analysis require an OpenAI-compatible endpoint.

Waza is a Go CLI for scaffolding Agent Skills evaluation suites, running benchmarks, and comparing outcomes across models or executors. Its readiness checks cover frontmatter compliance, token budgets, evaluation files, and agentskills.io specification rules, and the workflow can be integrated into CI. It is aimed at skill authors and teams that need repeatable quality measurements and regression checks.

Hercules converts readable Gherkin feature files into automated end-to-end browser tests, using Playwright to interact with web applications and producing JUnit XML and HTML reports. It is useful for QA or business teams that want to describe behavior without writing test code. The agent can consume tools from external MCP servers or run as an MCP server that exposes test generation, execution, and result retrieval.

ClawBio packages pharmacogenomics, variant lookup, ancestry analysis, UK Biobank search, and other bioinformatics workflows as skills callable from the CLI, Python, or an AI agent. Many skills emit replay commands, environment metadata, and checksums for later verification. Some workflows still depend on external databases, hosted APIs, or additional bioinformatics tools.