A Claude skills library: 40 shared, 80+ behind the scenes
Reusable skills and automations that turn one team’s process into something every team can run, backed by the specs and instruction sets my own agents follow.
skills and automations shared across departments
internal project specs and instruction sets
people through my sessions, classes and demos
What a skill is
A Claude skill is a set of written instructions Claude follows for one kind of task: the steps, the standards, and the files, knowledge bases and tools it should draw on. Because it’s plain text, it’s easy for people to read and edit and easy for the model to follow, so it works like a reusable playbook.
Two layers
Shared. About 40 skills and automations I’ve shared across departments, so a process one team figured out becomes something every team can run.
Behind the scenes. About 80 more that stay internal and are part of my own process and agentic workflows: project specs and instruction sets that point Claude to the right knowledge bases, so every agent follows the same standards and teams get consistent results.
Tracking and metrics
A library only earns its place if you can see it working, so I track it the same way I track every project in the AI portfolio:
- What exists. Every skill, spec and instruction set is counted: about 40 shared across departments and 80+ internal. Before anyone builds something new, I can check whether it already exists.
- No duplicates. Because I keep contextual awareness of everything being built, overlapping skills get caught and merged instead of multiplying.
- Ownership. Skills that come out of a project are tracked in Linear alongside that project, with its portfolio owner and executive stakeholder, so every skill has someone accountable for it.
- Usage and cost. The AI usage and cost dashboard I’m building shows each person their own token usage and spend, and gives admins a view by person, so adoption and cost are measured instead of guessed.
- Change history. Skills and their code live in GitHub, so every change is tracked, reviewed and reversible, and the reasoning behind them is documented in Obsidian.
- Adoption. More than 50 people have been through my sessions, classes and demos, which is where most skill use starts.
Getting people to use them
A skill nobody uses doesn’t help anyone, so the library goes hand in hand with training. More than 50 people have been through my sessions, classes and demos, and I help people build their own skills and connect them to the third-party services they already use.