--- title: "agent-kit vs pm-skills" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/keyid-ai-agent-kit-vs-phuryn-pm-skills" tools: ["keyid-ai-agent-kit", "phuryn-pm-skills"] --- # agent-kit vs pm-skills *GraphCanon updated Aug 6, 2026* ## Verdict Pick agent-kit if agent-kit enables creation of AI agents with the capability to handle email and digital communications through a JavaScript library; pick pm-skills if pM Skills provides a broad range of plugins for Codex to assist with product management tasks from discovery through growth. [agent-kit](https://keyid.ai) reports 677 GitHub stars, 10 forks, and 1 open issues, last pushed Mar 13, 2026. [pm-skills](https://www.productcompass.pm/p/pm-skills-2-red-team-ship) has 25k stars, 2.7k forks, and 40 open issues, last pushed Jul 3, 2026. Figures are from public GitHub metadata via [agent-kit's repository](https://github.com/KeyID-AI/agent-kit) and [pm-skills's repository](https://github.com/phuryn/pm-skills). | | [agent-kit](/tools/keyid-ai-agent-kit.md) | [pm-skills](/tools/phuryn-pm-skills.md) | | --- | --- | --- | | Tagline | Give Claude/Cursor email powers with 27 tools | A repository of PM-related skills and plugins for Codex. | | Stars | 677 | 24,889 | | Forks | 10 | 2,658 | | Open issues | 1 | 40 | | Language | JavaScript | - | | Adopt for | Agent-kit enables creation of AI agents with the capability to handle email and digital communications through a JavaScript library. | PM Skills provides a broad range of plugins for Codex to assist with product management tasks from discovery through growth. | | Persona | - | - | | Runtime | - | - | | License | - | MIT | | Categories | AI Agents | AI Agents | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [agent-kit](/tools/keyid-ai-agent-kit.md) | [pm-skills](/tools/phuryn-pm-skills.md) | | --- | --- | --- | | Maintenance | Slowing (36%) | Steady (60%) | | Days since push | 136d | 33d | | Open issues (now) | 1 | 40 | | Owner type | Organization | User | | Full report | [trust report](/tools/keyid-ai-agent-kit/trust.md) | [trust report](/tools/phuryn-pm-skills/trust.md) | ## Decision facts: agent-kit - **Adopt for:** Agent-kit enables creation of AI agents with the capability to handle email and digital communications through a JavaScript library. ## Decision facts: pm-skills - **Adopt for:** PM Skills provides a broad range of plugins for Codex to assist with product management tasks from discovery through growth. ## Choose when ### Choose agent-kit if… - Tags unique to agent-kit: agent, ai-agent, claude, email. - If you are working on an AI project that requires interaction with email services and other communication methods, such as SMS, using Claude or Cursor. - Leaner open-issue backlog (1). ### Choose pm-skills if… - Tags unique to pm-skills: codex-platform, plugins, product-management. - When you need comprehensive support across multiple phases of product management on the Codex platform - More GitHub stars (25k vs 677) - visibility, not fit. ## When NOT to use agent-kit - If your project language does not align with JavaScript, considering that Agent-kit specifically requires JavaScript for its implementation. - For scenarios where strict tool licensing and version control are critical since the license information for this library is unknown. ## When NOT to use pm-skills - Avoid if you require specific Claudia Code slash commands, as they do not function identically in Codex - Not suitable for users who prefer to cherry-pick individual skills rather than installing whole plugins ## Common questions ### What is the difference between agent-kit and pm-skills? agent-kit: Give Claude/Cursor email powers with 27 tools. pm-skills: A repository of PM-related skills and plugins for Codex.. See the comparison table for live GitHub stats and shared categories. ### When should I choose agent-kit over pm-skills? Choose agent-kit over pm-skills when Tags unique to agent-kit: agent, ai-agent, claude, email; If you are working on an AI project that requires interaction with email services and other communication methods, such as SMS, using Claude or Cursor; Leaner open-issue backlog (1). ### When should I choose pm-skills over agent-kit? Choose pm-skills over agent-kit when Tags unique to pm-skills: codex-platform, plugins, product-management; When you need comprehensive support across multiple phases of product management on the Codex platform; More GitHub stars (25k vs 677) - visibility, not fit. ### When should I avoid agent-kit? If your project language does not align with JavaScript, considering that Agent-kit specifically requires JavaScript for its implementation. For scenarios where strict tool licensing and version control are critical since the license information for this library is unknown. ### When should I avoid pm-skills? Avoid if you require specific Claudia Code slash commands, as they do not function identically in Codex Not suitable for users who prefer to cherry-pick individual skills rather than installing whole plugins ### Is agent-kit or pm-skills more popular on GitHub? pm-skills has more GitHub stars (24,889 vs 677). Stars measure visibility, not whether either tool fits your constraints. ### Are agent-kit and pm-skills open source? Yes - both are open-source projects on GitHub. ### Where can I find alternatives to agent-kit or pm-skills? GraphCanon lists graph-backed alternatives at [agent-kit alternatives](/tools/keyid-ai-agent-kit/alternatives) and [pm-skills alternatives](/tools/phuryn-pm-skills/alternatives) ([agent-kit markdown twin](/tools/keyid-ai-agent-kit/alternatives.md), [pm-skills markdown twin](/tools/phuryn-pm-skills/alternatives.md)), ranked by typed relationship edges rather than popularity votes. ### Is there a machine-readable version of this comparison? Yes. The markdown twin at [this comparison](/compare/keyid-ai-agent-kit-vs-phuryn-pm-skills.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, agent-kit or pm-skills? agent-kit: Slowing. pm-skills: Steady. Compare maintenance labels, days since push, and release cadence in the trust section below - stars alone do not measure maintenance. ### Where are the full trust reports for agent-kit and pm-skills? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [agent-kit trust report](/tools/keyid-ai-agent-kit/trust); [pm-skills trust report](/tools/phuryn-pm-skills/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=keyid-ai-agent-kit`](/api/graphcanon/graph?tool=keyid-ai-agent-kit) - LLM index: [/llms.txt](/llms.txt) - Full corpus: [/llms-full.txt](/llms-full.txt) _GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_