Start with the job, then find an open-source answer

Think Better installs scenario-triggered skills that help Claude, Copilot, and similar assistants break down problems, compare options, review architecture, and make more explicit decisions. Skills can activate automatically or through named commands, while the CLI manages installation and checks. Running the skills requires Python 3; building or installing the CLI from source also requires Go 1.25+.

This repository packages four agent skills for analog-circuit work: introductory ngspice simulations, gm/ID characterization and sizing, a PTM transistor-model library, and a Sky130A PDK workflow. The skills include runnable scripts, examples, plots, and model assets for teaching, research, and early design exploration. Users need ngspice, Python, and the listed scientific packages. The Sky130 skill explains how to install or locate the PDK and run PVT and Monte Carlo checks, but it does not bundle the PDK payload.

.context is a collection of portable Agent Skills for security auditing with Claude Code, Codex, Gemini CLI, Copilot, and other compatible agents. After a global or project-level install, users can ask an agent to audit a scoped codebase and produce structured findings. The collection covers smart-contract and infrastructure audit frameworks, plus supporting workflows for proofs of concept, sandboxed runs, forensics, and report preparation.

Use shared skills and runtime-specific prompts to apply Spec Kit in Claude Code, Codex CLI, GitHub Copilot CLI, or Gemini CLI. The workflow moves from project principles and feature specifications through clarification, technical planning, consistency checks, ordered tasks, and implementation, with a baseline path for existing codebases. Spec Kit and the chosen agent CLI must be installed before these skills can run.

These Claude skills guide developers beyond surface-level code explanations by examining design intent, core concepts, important snippets, dependencies, and evidence of understanding. Quick, standard, and deep modes support anything from a brief review to a detailed study of a large codebase. The pack is suited to codebase learning, research, and interview preparation, and is used by installing the skill files or supplying their instructions to Claude.

System Prompt Skills packages 15 reusable design patterns for building AI products and agents. The skills cover persona and personality, tool permissions, safety, memory, conversation routing, search and citations, context management, delegation, prompt-injection defenses, and adaptations for voice, mobile, and coding agents. Rather than serving as a prompt template dump, the repository is meant to be composed by use case: users choose a path from the index and integrate the relevant SKILL.md instructions into their own agent framework.

@helpfeel/cosense-cli packages a command-line client and Agent Skill for reading, researching, and editing Cosense pages from compatible agents such as Claude Code and Codex. The skill depends on the globally installed CLI for its actual operations. Claude Code users can install it through the plugin marketplace and enable automatic updates, while Codex users install it with the skills tool and update it manually.

SubManager is a cross-platform Python utility that follows GitHub users who follow your account and unfollows users who later leave. Two blacklist files let you exclude selected accounts from either side of the automation. After configuring a username and personal access token, the script can run manually or on a schedule through cron on macOS and Linux or Task Scheduler on Windows. It is intended for users who want recurring relationship maintenance rather than manual list updates.

Remote Sensing Research Radar is a Codex skill for daily or weekly monitoring of geospatial AI, optical remote sensing, large-scale Earth-observation data, and computer-vision methods that may transfer into the field. It discovers and ranks papers, repositories, datasets, benchmarks, and trends by novelty, evidence, reproducibility, and research fit, then produces reading queues, related-work tables, reproduction plans, or publishable directions. SAR, PolSAR, InSAR, microwave-only, and SAR-optical fusion work are excluded by default unless explicitly requested.

thesis-figure-skill helps Claude turn a paper section or reference image into an academic diagram. It can produce LaTeX/TikZ for structured figures and draw.io XML for editable roadmaps or presentation graphics. The skill can reuse tested layouts, create an original composition, reproduce an existing figure, or save a successful design as a template, then compile and check TikZ output before delivery. It handles the compile environment when run in Claude Code; manual compilation or export still requires the relevant TeX, font, and utility setup.

Amazon Skills is a public collection of agent workflows for Amazon sellers. Its current skills cover product research, validation of feature demand, listing health checks, search-term report analysis, CVR threshold diagnostics, and creation of additional seller skills. Depending on the task, they can use Sorftime, web search or local review bundles, Amazon pages, local business reports, and the user's own SIF MCP. The repository deliberately excludes real store data, private brand materials, internal infrastructure, and proprietary operating records.

Mine StableDiffusion is a local AI image studio for Android, iOS, Windows, macOS, and Linux. It uses stable-diffusion.cpp to run SD, SDXL, SD3, FLUX, and related models on the device, with LoRA support and detailed generation controls. Images and prompts can remain offline, making it suitable for users who want to manage their own models and data. Performance and model choice depend on Vulkan or Metal support and available memory; iOS is still beta, and lower-spec devices should begin with smaller models such as SD 1.5 or SD-Turbo.

Story Skills gives writing agents a shared Markdown project format for planning and drafting fiction. Story bibles, characters, worldbuilding, factions, artifacts, plot arcs, timelines, scene state, promises, payoffs, and chapter drafts are kept as plain files with YAML frontmatter. Compatible agents handle the creative workflow, while an optional companion CLI initializes projects and performs deterministic continuity checks, such as detecting dead characters returning or payoffs appearing before setup. The bundle supports Codex, Claude Code, and other Agent Skills environments.

Design Buddy is a collection of visual-production Agent Skills for creators, product managers, independent developers, and design collaborators. It first interprets the content and selects an appropriate visual structure, then produces outputs such as article covers, illustrations, infographics, architecture diagrams, logos, storyboards, slide decks, WeChat layouts, or social images. Users can install the full repository or copy individual skills, while the available output formats and generation steps still depend on the chosen agent runtime and image services.

Ship Studio combines an AI agent terminal, live responsive preview, visual editing, Git branches and pull requests, conflict handling, and Vercel deployment in one local desktop workspace. It works with existing Claude Code, Codex, or OpenCode installations and keeps the repository on your machine, making it useful for developers, designers, freelancers, and agencies that want fewer tool switches. Users bring their own agent, GitHub, and hosting accounts. Official builds include anonymous usage analytics and crash reporting, both of which can be disabled in the application settings.

Skill Conductor manages the lifecycle of an AI skill from design through distribution, requiring authors to choose an architecture pattern before writing `SKILL.md`. It supports creation, improvement, validation, third-party review, trigger-description optimization, and packaging, combining deterministic checks with benchmark tasks and evidence-backed binary quality questions. It is aimed at systematic skill authoring and review rather than a one-off prompt test.

cc-statistics reads local records from Claude Code, Gemini CLI, Codex CLI, and Cursor to combine token use, estimated costs, sessions, tool calls, and project activity. Use its CLI or web dashboard to compare tools, search and resume sessions, generate periodic reports, or set usage alerts; macOS also has a native menu bar app. Core analysis needs no account or API key, while the Windows tray build remains a development preview.

AgentCall lets a coding agent participate in Google Meet, Microsoft Teams, and beta Zoom calls as a meeting bot. The agent can hear live transcripts, speak through text-to-speech, inspect shared screens, exchange chat messages, and present content while retaining its coding session context. Setup requires a compatible agent runtime, Python or Node.js dependencies, and an AgentCall account.