Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Generate slide deck presentations from briefs — use when you need slides, pitch decks, or visual summaries
.claude/skills/hashgraph-online-skill-deck/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-08 | ✗→✓ | ▲ Improved | 37% | 0% |
| case-16 | ✓→✗ | ▼ Worse | -53% | 0% |
| case-04 | ✓→✓ | = Same ✓ | 64% | 0% |
| case-05 | ✓→✓ | = Same ✓ | 31% | 0% |
| case-06 | ✓→✓ | = Same ✓ | 45% | 0% |
> Host: Codex CLI — This skill was designed for Claude Code and adapted for Codex. > Cross-reference commands use installed skill names in Codex rather than /octo:* slash commands. > Use the active Codex shell and subagent tools. Do not claim a provider, model, or host subagent is available until the current session exposes it. > For host tool equivalents, see skills/blocks/codex-host-adapter.md.
Generate professional slide decks from briefs with optional research, outline approval, and PPTX export.
The document-skills plugin MUST be installed for PPTX rendering:
/plugin list | grep document-skillsIf not installed, tell the user:
The document-skills plugin is required for PPTX generation.
Install it with: /plugin install document-skills@anthropic-agent-skillsParse the user's topic and description. Use AskUserQuestion to clarify:
Question 1 - Audience:
Question 2 - Slide count target:
Question 3 - Tone:
If the user already provided clear context (e.g., "10-slide investor pitch deck about our Series A"), skip questions where the answer is obvious.
If the topic needs external research or context gathering:
Explore or general-purpose subagent to gather relevant information/octo:discover [topic] first, then /octo:deck to build slides from the results"This step is OPTIONAL. Many decks are built from the user's own knowledge or existing documents.
Build a slide-by-slide outline in markdown format. Structure:
markdown## Slide 1: [Title Slide] - Presentation title - Subtitle / Date / Author ## Slide 2: [Agenda / Overview] - Key topics to cover ## Slide 3: [First Content Section] - Bullet point 1 - Bullet point 2 - Bullet point 3 ## Slide N: [Summary / Next Steps] - Key takeaways - Call to action
IMPORTANT: Present the outline to the user for approval using AskUserQuestion:
This is the wireframe gate — the user MUST approve the outline structure before PPTX generation.
Once the outline is approved:
document-skills:pptx skill to convert the approved markdown outline to PowerPoint## heading becomes a slideExample filename: Series-A-Pitch-Deck-2026-02-14.pptx
Apply these when generating outlines:
Executives / Board:
Engineers / Technical:
Investors / Fundraising:
General / Mixed:
This skill works well in combination with:
/octo:discover [topic] — Research first, then build deck from findings/octo:docs — For converting existing markdown to other formats/octo:prd — Generate a PRD, then create a presentation summarizing it/octo:brainstorm — Brainstorm ideas, then structure into a deckUser: "Create a 10-slide deck about our Q1 results"
→ Step 1: Clarify audience (executives)
→ Step 2: Skip (user has the data)
→ Step 3: Generate outline, get approval
→ Step 4: Render PPTXUser: "Build a presentation about AI trends in healthcare"
→ Step 1: Clarify audience and scope
→ Step 2: Research using Task agents
→ Step 3: Generate outline from research, get approval
→ Step 4: Render PPTXUser: "I need a comprehensive investor deck about the autonomous vehicles market"
→ Suggest: "/octo:discover autonomous vehicles market" first
→ Then: "/octo:deck" using the research synthesisSlide deck skill for claude-octopus v8.12.0+
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-04 | pass→pass | 14,497 | 19,845 | +37% | 1 | 1 | 0% | 2,739 | 4,483 | +64% | 0 | 0 | — |
case-01 | fail→fail | 29,271 | 18,545 | -37% | 1 | 1 | 0% | 5,814 | 1,778 | -69% | 0 | 0 | — |
case-02 | fail→fail | 9,795 | 20,255 | +107% | 1 | 1 | 0% | 1,615 | 1,937 | +20% | 0 | 0 | — |
case-03 | fail→fail | 12,281 | 20,668 | +68% | 1 | 1 | 0% | 1,208 | 2,408 | +99% | 0 | 0 | — |
case-05 | pass→pass | 46,529 | 36,358 | -22% | 1 | 1 | 0% | 6,640 | 8,669 | +31% | 0 | 0 | — |
case-06 | pass→pass | 21,679 | 20,297 | -6% | 1 | 1 | 0% | 3,102 | 4,510 | +45% | 0 | 0 | — |
case-07 | fail→fail | 42,697 | 7,446 | -83% | 1 | 1 | 0% | 8,221 | 1,745 | -79% | 0 | 0 | — |
case-08 | fail→pass | 17,475 | 31,278 | +79% | 1 | 1 | 0% | 2,887 | 3,941 | +37% | 0 | 0 | — |
case-09 | pass→pass | 18,274 | 16,380 | -10% | 1 | 1 | 0% | 3,106 | 3,236 | +4% | 0 | 0 | — |
case-10 | fail→fail | 37,704 | 12,398 | -67% | 1 | 1 | 0% | 8,213 | 1,806 | -78% | 0 | 0 | — |
case-11 | fail→fail | 44,500 | 47,180 | +6% | 1 | 1 | 0% | 8,226 | 9,056 | +10% | 0 | 0 | — |
case-12 | fail→fail | 9,507 | 15,961 | +68% | 1 | 1 | 0% | 1,663 | 4,254 | +156% | 0 | 0 | — |
case-13 | fail→fail | 12,177 | 11,972 | -2% | 1 | 1 | 0% | 2,138 | 2,608 | +22% | 0 | 0 | — |
case-18 | pass→pass | 15,689 | 7,744 | -51% | 1 | 1 | 0% | 2,584 | 2,579 | -0% | 0 | 0 | — |
case-14 | fail→fail | 47,023 | 14,442 | -69% | 1 | 1 | 0% | 6,819 | 3,033 | -56% | 0 | 0 | — |
case-15 | pass→pass | 26,177 | 16,755 | -36% | 1 | 1 | 0% | 3,462 | 4,203 | +21% | 0 | 0 | — |
case-16 | pass→fail | 22,134 | 11,491 | -48% | 1 | 1 | 0% | 3,766 | 1,764 | -53% | 0 | 0 | — |
case-17 | fail→fail | 20,689 | 9,091 | -56% | 1 | 1 | 0% | 2,755 | 1,736 | -37% | 0 | 0 | — |
case-19 | pass→pass | 16,176 | 22,639 | +40% | 1 | 1 | 0% | 2,869 | 4,020 | +40% | 0 | 0 | — |
case-20 | pass→pass | 9,021 | 21,805 | +142% | 1 | 1 | 0% | 1,497 | 2,644 | +77% | 0 | 0 | — |
case-21 | pass→pass | 16,234 | 10,699 | -34% | 1 | 1 | 0% | 1,940 | 2,309 | +19% | 0 | 0 | — |
case-22 | pass→pass | 12,845 | 6,758 | -47% | 1 | 1 | 0% | 2,131 | 2,649 | +24% | 0 | 0 | — |
case-23 | pass→pass | 9,702 | 12,417 | +28% | 1 | 1 | 0% | 1,491 | 2,511 | +68% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 23 cases were attempted, and 16 counted toward the lift figure. The other 7 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of 0 percentage points is the difference between those two pass rates over the 16 comparable cases. 2 cases got worse with the skill loaded, and they are included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.