FygmentResources
How to build AI skills that work, test them, keep them current and govern them across Claude, ChatGPT, Copilot and the other AI tools your team uses. Setup guides for technical teams are further down.
AI skills spread from person to person and from AI tool to AI tool, usually after working once or twice for their author. Some come from the internet, unchecked. This is not a reason to stop sharing. It is a reason to give skills a proper path: tested, checked, approved and kept in one place.
Read articleGoverning AI skills does not need a committee. It needs eight things: know what you have, give every skill an owner, set the rules for who may create and share, check outside skills, approve by risk, roll out the approved version to every AI tool, review on a cycle, and see what is actually used.
Read articleEvery company depends on knowledge that only a few people have. Documents never really captured it, because nobody reads them at the moment of doing the work. AI skills change that: the knowledge does the work, every time, for everyone. Here is why that makes skills a company asset, and what leaders should do about it.
Read articleTurning company knowledge into AI skills works best as a repeatable method, not a one-off project: find the knowledge you cannot afford to lose, capture it with the expert, structure and test it, publish it with an owner, and keep it alive through use. Seven steps, with what each one produces.
Read articleBefore you turn a process into an AI skill, check the data around it: where it lives, whether it is current, whether good examples exist, and whether the AI may use it. Nine checks, each with a quick test and a fix.
Read articleMost AI skills are written once, tried twice and shared with the whole team. These are the six mistakes we see most often, why they happen, and what the teams that get skills right do differently.
Read articleA reliable AI skill has a clear job, a process with steps, data sources and checks, tests with expected results, and an owner who keeps it current. Here are the 23 elements we look for, with a worked example of a skill that drafts client proposals.
Read articleAn AI Skills registry is the shared inventory, review surface, and package lifecycle for reusable agent capabilities that need ownership, versioning, and install state.
Read articleMCP setup should be managed as shared configuration with ownership, review, install instructions, and a clear boundary between local credentials and team policy.
Read articleAgent-toolchain governance is the operating model that keeps reusable Skills, prompts, MCP setup, and local agent configuration owned, versioned, approved, auditable, and safe to install.
Read articlePortable Skills become manageable when a governed registry, the fygment CLI, local inventory, lockfiles, and check/update flows keep supported harness installs reviewable.
Read articleHand-edited agent config is fine for a small personal setup, but teams eventually need governed packages, reproducible installs, approvals, and visible setup health.
Read article