All Flashcards

A skill whose persona access is narrowed so only owners (or another designated group) can see or invoke it. Other users never see it offered.

A named, reusable instruction package stored in SharePoint. A trigger phrase loads the skill's Markdown file into the agent's context so it follows those instructions for the run.

A meta-skill that improves other skills by running baseline evals, mutating the target skill, rerunning evals, and keeping the version that scores best.

The eval score of a skill before any optimization. Every mutation is judged against this number — improvement is the lift over baseline.

The fixed-size memory the model uses for a single run. Everything loaded — system prompt, skill file, references, chat history — competes for the same finite space.

A measurable test that runs a skill against fixed inputs and scores each output against defined criteria. Turns subjective quality into a number you can compare.

A short, specific yes/no question used to grade one dimension of a skill's output — hook quality, hallucination, tone, structure, and so on.

The discipline of pulling rules, templates, or data into the context window only when the current run actually requires them — the foundation of clean skill design.

Per-skill setting that controls which SharePoint personas — owners, members, visitors, or custom groups — can see and run the skill.

A side file the skill loads only when needed. Templates, schemas, and long examples live here so they don't sit in every run's context window.

A single proposed change to a skill's instructions — usually a reworded section or new guardrail — generated by the auto-research loop in response to failing eval criteria.

Saving an improved skill under a new name (V2, V3 …) instead of overwriting the original. Preserves rollback and lets you A/B the versions on live work.

The per-site catalogue of installed skills. Open it to inspect, edit, or change persona access for any skill on the SharePoint site.

The main Markdown file that defines a skill. Keep it small — list the trigger, the high-level behaviour, and pointers to reference files instead of inlining every template.

By default, visitors can leverage skills built by site owners but cannot edit them. Owners can override either direction on a per-skill basis.