Many know the concept of Agent Skills but struggle to decide what to build as their first Skill. This post provides an interactive 'Selection Wizard' to diagnose and generate your prioritized Skill checklist based on your role, system, scale, and pain points.
Markdown tools are a dime a dozen—I still built Sheaf: a local-first macOS writing desk for editing, AI polish, WeChat HTML export, and social cards, all in one place.
From a dozen stars to 95: Vibe Coding lowers the bar but flattens the moat, cold start, the Day 2 problem, and a few lessons from shipping skill-base.
When many tools and many Skills coexist, source-of-truth conflicts, trigger ranking, and frontmatter dialects become unavoidable: why sharing one folder is not the same as sharing one contract.
A practical companion to Best Practices: how to narrow descriptions, layer SKILL.md vs references, and use checklists plus a versioning strategy to keep quality stable over time.
A real refactor walkthrough: freezing pagination mapping, date-range checks, query fold behavior, org permissions, and export handling as a project Skill so the model’s first pass needs fewer rework rounds.
This post only answers “what deserves a Skill”: the repeat / stable / executable bar; a scenario checklist with counterexamples; a crosswalk to the DeepLearning.AI short course and Anthropic’s official notes. Series context is in parts 1–3.
Use skill-base / skb to publish, search, install, and update team Skills like npm—so you stop copy-pasting rules and fighting version drift.
How Skills load in layers at runtime, what a skill directory looks like, and a copy-paste minimal `SKILL.md`; team distribution and versioning are in part 3.
From “I’ve heard of it / installed a few but can’t explain it” to writing clearly and splitting concerns: what a Skill is, what problems it fits, how to pick topics and author them, plus fragmentation and team rollout.