cafleet-research

# Research Skill (CAFleet Edition) This skill is the umbrella for research and presentation media: two CAFleet-native **orchestration workflows** (research report, presentation) plus two load-on-demand utility **reference pages** (matplotlib visualization, the custom Slidev theme). It is a dispatcher — route to the matching workflow body to run a team, or read a reference page for a standalone utility. **Teammates in member teams** that need this skill load it by its name `cafleet-research` via their backend's skill-loader — never by reading the skill files directly. ## Required reading Before routing into a workflow or consulting a reference page, Read your overlay — it is row #1 below. Identify your coding agent first: your spawn prompt's `CODING AGENT:` line names it; a standalone / main-session reader uses its own identity. **Load-bearing — Read before acting:** | # | Read | What you lose if you skip it | |---|------|------------------------------| | 1 | your overlay [`../cafleet/reference/coding-agent/<name>-overlay.md`](../cafleet/reference/coding-agent/) — read **and resolve** it (see *Resolve your overlay* in the cafleet `SKILL.md`) | you skip resolution — you emit a literal `{monitor_model}` / `{task_coord}` / `{decision_surface}` in the workflow you route into, **or** guess a wrong/default value, **or** ignore a backend note (codex has no harness task list) | **On-demand — consult directly (no team), only when the task needs it:** | Read | When | |------|---...