daddia Deck Outline
When to use
For consultants building a storyline-first, action-titled deck outline before slide design. Markdown outline only — hand off to presentation tools after approval.
What this skill does not do
- Does not build slides — outline only; pptx or design tools after approval.
- Does not invent narrative without governing thought — route to
narrative-builderif needed. - Does not rewrite source analysis — maps pyramid to slides.
Preconditions
| Input | If missing |
|---|---|
| Practice profile (slide title style, exhibits) | Proceed with action titles default; flag practice-setup |
| Governing thought / narrative | Ask to run narrative-builder first |
Provisional mode
Thin narrative: label structured first pass; flag slides that don't trace to key line.
Trust spine
- Confidence bands (
narrative-synthesis): High = every slide traces to key line; Medium = some exhibit TBD; Low = topic list without governing thought — flag. - Analytical Rigor: Every slide supports a key line point; cut or flag non-load-bearing slides.
- Escalation: Slide without key-line parent → flag or cut; board-final → gate + reviewer note.
Full rules: ../../references/trust-conventions.md.
Workflow
- Read practice profile for slide title style and exhibit conventions.
- Use
narrative-builderoutput if available; else ask to build narrative first. - Map pyramid: governing thought slide → key line slides → supporting evidence (one exhibit per slide).
- Action titles unless profile says descriptive.
- Note exhibit per slide without building it.
- So-what test per
minto-pyramid.md— cut non-load-bearing slides.
Output format
GOVERNING THOUGHT: [headline]
Slide 1 — [Action title]
Exhibit: [...]
Slide 2 — [Action title for key line point 1]
Exhibit: [...]
...
Flag slides that don't trace to a key line point.
Worked example
Input: Governing thought: "Mid-tier price increase destroyed volume — revert pricing." Three MECE key lines.
Excerpt: Slide 1 action title states governing thought; Slides 2–4 map one key line each with exhibit notes (cohort chart, elasticity model, competitor scan).
Quality checks before delivering
- Governing thought on slide 1, not "Overview"
- Action titles (unless profile overrides)
- Every slide traces to key line
- Trust spine applied to exhibit claims
Propose profile update
When a stable convention surfaces during this run (thresholds, naming, tone, output format, or recurring corrections), propose a profile update: show the exact diff against ~/.claude/plugins/config/claude-for-strategy/consulting/CLAUDE.md (org-wide facts go to org-profile.md), ask for confirmation, and write only on yes. Only /consulting:practice-setup auto-applies a full profile write.
Outputs
Follows plugin CLAUDE.md § Outputs. Next: approve outline → build slides, or /consulting:so-what-sharpener on weak titles.