presentation-blueprint
Skill6 starsChanged 9 days agoMITView on GitHub
Use when the user needs to create a presentation, pitch deck, slide deck, or visual summary about a project, codebase, website, or topic. Triggers on requests like 'build a deck', 'create a presentation', 'make slides about', or 'pitch deck for'.
In this repository22 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- adding-an-add-to-claude-buttonSkill
- bd-to-br-migrationSkill
- codex-plan-reviewSkill
- codex-reviewSkill
- debugging-kubernetes-rolloutsSkill
- debugging-nodejs-appsSkill
- de-sloppingSkill
- detect-overengineeringSkill
- evaluating-third-party-toolsSkill
- finding-latest-versionsSkill
- git-reconSkill
- humanizerSkill
- hyprland-luaSkill
- mining-claude-sessionsSkill
- minto-pyramidSkill
- nonstopSkill
- operating-frappe-on-kubernetesSkill
- pr-fixSkill
- pr-landSkill
- prSkill
- watching-pr-bot-reviewsSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 7
If you were dispatched as a subagent to execute a specific delegated task, do NOT follow this skill — skip it and return to the task you …
- Very specific: line 16
Verify document-skills:pptx is available.
- Distinctive: line 61
No fabricated data. Flag secrets to user.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
<SUBAGENT-STOP>
If you were dispatched as a subagent to execute a specific delegated task, do NOT follow this skill — skip it and return to the task you were given.
</SUBAGENT-STOP>Presentation Blueprint
Fortune 500 presentation consultant. Pipeline: analyze, strategize, outline, style, render.
Prerequisites
Verify document-skills:pptx is available. If missing, instruct user to install it and stop.
Presentation Types
| Type | Triggers | Slides |
| Pitch | fundraise, investors, startup | 10-12 |
| Technical | architecture, system design, API | 15-20 |
| Update | status, quarterly, progress | 5-8 |
| General | summarize, overview, "about" | 10-12 |
Pipeline
digraph { rankdir=LR; Analysis->Strategy->Outline->Style->Render; Outline->Strategy [label="reject\nmax 3"]; Outline [label="Outline\n(approval gate)"]; Style [label="Style\n(approval gate)"]; }Phase 1: Source Analysis
Per ./source-analysis.md. Sources: codebase (README, docs, package.json, CLAUDE.md, git log), website (WebFetch: landing, about, pricing, features), user interview (3-5 questions). If a source fails, note and continue. Interview alone is minimum viable path.
Phase 2: Strategic Blueprint
Per ./narrative-frameworks.md. Define: objective, audience, key message, ask, narrative arc. Present Presentation Strategy to user for confirmation before proceeding.
Phase 3: Slide Outline
Format: Slide N: [Type] — "Key message". Approval gate: user must approve. Max 3 revision loops, then offer "start over" or "abort". Warn at 25+ slides.
Phase 4: Style Confirmation
| Type | Default |
| Pitch | Dark, bold, high-contrast |
| Technical | Clean, structured, diagram-heavy |
| Update | Data-heavy, minimal decoration |
Approval gate. Pass style label + parameters to pptx skill. No intermediate document.
Phase 5: Render & Review
Delegate to document-skills:pptx html2pptx workflow. Reference ./slide-archetypes.md for layouts. No speaker notes (async-first). No incremental updates — each invocation produces one complete deck. Rendering errors surfaced by pptx skill.
Guardrails
- No fabricated data. Flag secrets to user.
- Phase 3 + Phase 4 approval mandatory.
- Max 25 slides. One deck per invocation.
Red Flags
| Never | Why |
| Fabricate metrics | Destroys credibility |
| Skip approval gates | User loses control |
| Generate filler slides | Wastes attention |
| Include secrets/API keys | Security breach |
| Render before approval | Wrong output |
| Assume style without confirmation | Style mismatch |
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.