From cafleet
Orchestrates CAFleet teams for multi-source research reports, presentation decks, data visualizations, and Slidev-themed slides.
How this skill is triggered — by the user, by Claude, or both
Slash command
/cafleet:cafleet-researchThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
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.
presentation/presentation.mdpresentation/roles/director.mdpresentation/roles/presentation.mdpresentation/roles/transcript.mdpresentation/roles/visual-reviewer.mdreference/slidev.mdreference/slidev/techniques/formatting.mdreference/slidev/techniques/math-formulas.mdreference/slidev/techniques/two-column-layouts.mdreference/slidev/theme/components/Admonition.vuereference/slidev/theme/components/Highlight.vuereference/slidev/theme/layouts/blank.vuereference/slidev/theme/layouts/bullets-sm.vuereference/slidev/theme/layouts/bullets.vuereference/slidev/theme/layouts/cover.vuereference/slidev/theme/layouts/end.vuereference/slidev/theme/layouts/section-divider.vuereference/slidev/theme/layouts/stats-grid.vuereference/slidev/theme/layouts/two-cols.vuereference/slidev/theme/styles/index.cssThis 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 agent 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.
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>.md — 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 |
|---|---|
| reference/visualization.md | you are creating a chart / plot / graph / figure or visualizing data |
| reference/slidev.md | you are authoring slides with the custom Slidev theme (layouts, components, techniques) |
Each workflow body (report / presentation) carries its own Required-reading block for the team it runs — base-dir and supervision are gated there, not on this dispatch surface.
Before acting, resolve every {token} you will use to its overlay value (or the documented default); a literal {token} in any command or message is a defect.
When the user's request matches a scenario below, invoke this skill and run the linked workflow as a full CAFleet team — proactively, the moment the request matches, without waiting for the user to say "use cafleet".
Routing into the report or presentation workflow means executing its entire orchestration. The dedicated monitoring member is spawned first-in (cafleet member create --role monitor, gating the team behind its ready: monitor live handshake), then the role team, then the workflow body's review and revision rounds run through to approval. The linked workflow body is the authoritative procedure.
| When the user wants to… | Invoke this skill and run |
|---|---|
| Research a topic / create a multi-source research report | the report workflow (report/report.md) — Director/Manager/Researcher team → researches/<topic>/ |
| Build a presentation / slide deck / reading transcript from a report | the presentation workflow (presentation/presentation.md) |
For a chart/figure or the Slidev theme — consult the On-demand reference pages in § Required reading above (no team needed).
The report workflow chains into the presentation workflow after user approval. The two reference pages are standalone utilities the presentation workflow also reads. Always route research work through the workflow bodies above — each runs the full CAFleet team.
npx claudepluginhub himkt/cafleet --plugin cafleetCreates slide presentations from topics, URLs, PDFs, git repos, or vault notes. Handles research, synthesis, outlining, and editing existing decks. Default output is reveal.js HTML; pptx available on request.
Writes structured survey/assessment reports (literature review, technology assessment, SOTA) from a populated knowledge base. Final stage of the survey pipeline.
Generates slide deck presentations from briefs with optional research, outline approval, and PPTX export.