agency-agents vs cc-polymath
Role-specific AI instructions and Claude Code skills compared
agency-agents provides reusable instructions for specialists across many professional roles, with scripts for installing selected agents into compatible tools. cc-polymath is a Claude Code skill catalog focused on technical guidance that users discover and load progressively. The main difference is broad role coverage and tool installation versus on-demand technical references for Claude Code.
agency-agents: Install Role-Specific AI Agent Instructions
A large collection of specialized AI agent instruction files, organized by professional role and supported by scripts for installing them into compatible coding tools. Useful when you want reusable role-specific workflows rather than a single general-purpose prompt.
cc-polymath: Context-Efficient Skills for Claude Code
cc-polymath is a collection of atomic skills and workflows for Claude Code, designed to provide broad development knowledge without loading everything into the context window. Progressive discovery helps surface relevant skills as needed, from cloud infrastructure to advanced mathematics.
| agency-agents | cc-polymath | |
|---|---|---|
| Language | Shell | Python |
| License | MIT | MIT |
| Stars | 156k | 190 |
| Forks | 25.2k | 15 |
| Last analyzed | Oct 3, 2026 | Oct 29, 2026 |
Key differences
- agency-agents spans professional areas such as engineering, design, marketing, security, finance, and support; cc-polymath focuses on technical domains including software, infrastructure, AI, mathematics, and formal methods.
- agency-agents provides Markdown role instructions and shell scripts to convert and install selected agents; cc-polymath organizes self-contained skills through gateways, category indexes, and individual guides.
- agency-agents supports installation into compatible coding tools; cc-polymath is specifically for Claude Code and includes a `/skills` command and keyword-based discovery.
- agency-agents lists Shell as its language, while cc-polymath lists Python. Both projects use the MIT license.
- The provided project data lists 156k stars and 25.2k forks for agency-agents, compared with 177 stars and 12 forks for cc-polymath.
Choose agency-agents if you…
- want role-specific instructions across a broad range of professional fields.
- need scripts to select and install agent instructions into a compatible coding tool.
- prefer Markdown instructions that can be browsed, copied, or adapted directly.
Choose cc-polymath if you…
- use Claude Code and want to load focused technical guidance on demand.
- need to discover and combine skills across software, infrastructure, AI, or mathematics.
- want examples of progressive discovery and validation practices for skill collections.
Compare the numbers side by side, or add more projects
This comparison is generated with AI from the OSRepos analyses of both projects. Always check each project's repository and documentation before choosing.