⏳ This skill is pending AI review.
Scores will appear once the review pipeline completes.
strategy-consulting-visualization
Use when turning any content into clear, professional visualizations - board slides, reports, proposals, research summaries, training materials, technical diagrams, infographics, process flows, timelines, benchmarks, waterfall charts, or data-backed visual specs for any audience.
Choose how to use this skill
You do not need every option. Choose the path your AI client supports. The stable page stays the same; versioned files are immutable.
1. Native installer
This listing has no registered native installer command. Use the complete package or source fallback below, depending on what your client supports.
Do not guess an installer command or replace an existing version without reviewing the diff.
2. Complete package recommended
Download the ZIP when available. It includes SKILL.md plus the references, security notes and version metadata.
No complete ProSkills package is published for this listing yet.3. Prompt-only
Copy the prompt above when the agent can read the stable page or when you want to adopt the workflow without installing a skill.
Need only the instruction file?
Download SKILL.md only if your client requires a single file. The complete ZIP is safer for a full installation because it preserves the references and release context.
No path installs or executes anything by itself. Your agent still needs access to the project files. Before updating, compare the installed version and review the diff.
// RATINGS
Not yet listed on ClawHub or SkillsMP
// README
Strategy Consulting Visualization Skill
Messy notes in. Board-ready slides out.
One skill for your AI agent: turn notes, metrics, and prose into consulting-grade visuals — as real SVG slides, as an animated HTML deck, or as a spec any designer or tool can execute.
Rendering existing JSON specs into SVG/HTML uses the Python 3 standard library only, with no API key or network access required. Generating slides from notes in the browser requires your own Anthropic API key. The sample trial needs no key. Automated PDF export has optional browser dependencies.
English | 日本語
Watch the full demo with playback controls →
Actual browser recording. Preview at 2.5× speed; full video at normal speed, without audio.
Actual v3 output: motion manifest (JSON) → interactive story + static reading edition.
v3.0.0-rc.1 — Interactive decision stories
Open the English live demo → · Static reading version · Japanese demo
Change an assumption. See the decision change. Six connected pages take readers from the priority to investigate, through route comparisons and a live value model, to readiness and a conditional rollout. The English decision design uses large body text, assertion-led headlines and whitespace instead of decorative dividers. Press D for the guided demo, or explore the charts and controls yourself. All example data is illustrative, not a client result.
This is a prerelease, not a fully device-certified stable release. v2.4.0 remains the latest stable release. Download the self-contained HTML files from the release assets.
A click-through motion presentation is now available. The six-page English story starts with an overview you can enter, lets readers press exhibits and prominent numbers for evidence, and connects changed assumptions to the conditional rollout. Sorting, retained differences, live equations, gap-filling actions and timeline steps are included in a cursor-led demo. A static reading version comes from the same source. See the motion story guide. The Japanese version is also retained.
python3 scripts/build_motion_deck.py --manifest examples/interactive-deck/motion.en.json -o deck.motion.en.html
python3 scripts/build_motion_deck.py --manifest examples/interactive-deck/motion.en.json --static -o deck.motion.en.static.html
The separately supported contract-backed runtime is described below.
The skill now has an optional stateful interactive companion for decision work: clickable evidence, bounded scenario switches, exact what-if sliders, readiness scoring, drill-downs, accordions, and a deterministic presenter demo. It keeps the restrained, assertion-led slide system and always preserves a static/print conclusion.
“Animated deck” still means the existing quiet reveal. Ask explicitly for an
interactive deck, dynamic deck, what-if, clickable evidence, scenario slider, drill-down, or auto-demo to build both audience artifacts:
python3 scripts/build_html_deck.py --manifest examples/interactive-deck/deck.json -o deck.html
python3 scripts/build_interactive_deck.py --manifest examples/interactive-deck/deck.json -o deck.interactive.html
Try the original, entirely illustrative eight-page example: Project Relay —
classic HTML, interactive
HTML, and static
PDF. The public /try/ route remains the
classic builder. Core HTML generation uses the Python standard library and
writes only the explicit output path; browser/PDF/audit checks use the pinned
optional test tools. See interaction selection,
scene authoring, accessibility,
and presenter operation.
Known verification limits: Safari, physical iPhone/touch, real browser-toolbar 200% zoom, AirPlay/HDMI/projector, VoiceOver/NVDA, real high contrast, and hosted response headers remain manual gates. See the verification record. The English decision layer is tailored to Project Relay, not a universal business-model generator. Public inspiration and independent design choices are recorded in design provenance; this package is not affiliated with or endorsed by McKinsey or any other consulting firm.
What’s new — September 9, 2026
Try a presentation on your phone before setting up an API key. Open the browser trial, choose Explore a sample deck, then Start presentation.
- Present directly in the browser. Swipe or use Previous / Next to move through slides; rotate your phone for a larger landscape view. Desktop keyboard navigation is also supported.
- Share or save HTML. Use the device share sheet where supported, with a download fallback. Present from the browser; reopening interactive HTML from iOS Files is not yet verified.
- Save a PDF. Choose PDF / Print, select landscape in the native print dialog, then use its share/save options. iOS may initially select A4 portrait.
- See the outcome before trying it. The homepage pairs a clearly labeled AI-generated hero concept with actual renderer output and a path from examples to the trial or installation.
- iOS fixes verified in Simulator. Japanese text and controls use an explicit Hiragino fallback; HTML sharing no longer creates an extra text file.
Tested with iPhone 17 / iOS 26.3 Simulator Safari: sample loading, presentation, swipe navigation, rotation, nine-page print preview, and PDF/HTML saving to Files. Existing 335 tests pass. Physical iPhone hardware, live API generation and AirPlay/projector output remain unverified. See the test record.
What’s new — September 8, 2026
- Refined business slides and diagrams. Updated the executive summary, growth waterfall, priority matrix, process flow and roadmap layouts, with clearer hierarchy, labels and decision cues. Regenerated the English and Japanese landing decks and site previews from the current renderer.
- Real deliverables on the site. The homepage now shows actual slide previews alongside a complete A4 brief, with links to the finished PDFs. Examples use illustrative business data.
- **HTML first, PDF for sharing
// HOW IT'S BUILT
// FILES
2 files shipped with this skill. Inline text is the catalog copy. The upstream link is the source repository.
SKILL.md7.8 KBupstream ↗
--- name: strategy-consulting-visualization description: Use when turning any content into clear, professional visualizations - board slides, reports, proposals, research summaries, training materials, technical diagrams, infographics, process flows, timelines, benchmarks, waterfall charts, or data-backed visual specs for any audience. --- # Strategy Consulting Visualization ## Purpose Use this skill to turn any content into professional visualization specs with strategy-consulting clarity: insight-led headlines, disciplined layout, accurate data, restrained design, and explicit implications. It covers board slides first, and generalizes to reports, proposals, training materials, technical diagrams, infographics, and any input that benefits from visual structure. ## Fast Path Skip the pattern-by-pattern build when the user just wants a complete, real deck or document immediately. **Full deck** — scaffold a ready-made archetype from `templates/decks/`, then fill in the illustrative placeholders with real data: ```bash python3 scripts/scaffold_deck.py --list # 6 archetypes with slide counts python3 scripts/scaffold_deck.py board-update -o my-deck # copies deck.json + specs/ # edit my-deck/specs/*.json with real data, keeping the pattern shapes intact python3 scripts/build_html_deck.py --manifest my-deck/deck.json -o my-deck/deck.html ``` **Document** — write Markdown (with `spec:`/`svg:` exhibit references where a chart belongs) and build it straight to a browser-ready, print-to-A4 HTML report: ```bash python3 scripts/build_html_report.py my-report.md -o my-report.html --lang en ``` `templates/reports/` has three starting points (board pre-read, one-pager, proposal memo). **Speaker script** — the podium version of any deck: add a top-level `"notes"` field (a string, or a list of paragraph strings) to the slides that need narration, then build a print-first, one-slide-per-page HTML script with the narration set below each slide. The renderer ignores `notes` entirely, so adding it never changes the rendered slide, and a slide with no notes still gets its own page with a muted "no script" marker. ```bash python3 scripts/build_speaker_script.py --manifest my-deck/deck.json -o my-deck/script.html --lang en ``` **Deck as an article** — the same deck read top-to-bottom on a single 680px reading column instead of click-through slides or a side-nav document: a paper-first hero (kicker/lead from the manifest's optional `series`/`lead` keys), then each slide's SVG followed by its `notes` as reading prose, with optional per-slide `label`/`refs` fields adding a section tag and a "Links" aside that rolls up into an end-of-article links section. ```bash python3 scripts/build_html_article.py --manifest my-deck/deck.json -o my-deck/article.html --lang en ``` All four fast paths still obey the style system and quality rubric below — they only skip writing specs from a blank page. Fall back to the full workflow for anything the templates don't already cover. ## Use When - The user needs a board slide, executive memo visual, market map, competitor benchmark, investment view, performance bridge, or strategic timeline. - The user needs visuals for any other document: internal reports, research summaries, sales proposals, project status updates, training or education materials, technical documentation, one-pagers, infographics, or study notes. - The user has raw data, prose, notes, a process description, or a question and needs a visual direction — even if they only say "visualize this". - The user asks for McKinsey-style, BCG-style, Bain-style, consulting-style, boardroom-ready, executive-ready, or strategy-deck visuals. - The output should feel like a top-tier professional deliverable without implying affiliation with any consulting firm. ## Do Not Use When - The user wants decorative art with no informational content, brand campaigns, or low-density inspirational visuals. - The user needs regulated financial, medical, or legal conclusions without source verification. - The user asks for a final rendered chart but has not provided enough data to check labels, scales, and claims. ## Workflow 1. Identify the decision, question, or job the visual should support for its reader. 2. If the input is not an obvious chart request, triage it with `references/input-triage.md` to map any input type to a pattern family. 3. Pick the document profile from `references/document-type-profiles.md` to set canvas, density, and tone. 4. Convert the request into an insight-led headline that answers the reader's question. The headline must be a single proposition — one answer or one tension, never several claims joined by "and". 5. Select the visualization pattern from `references/visualization-patterns.md`, starting from the comparison-type gate at the top of that file. Structural patterns (`section_divider`, `agenda`, `bullet_list`, `closing`, `quote`, `end_cover`, `cover`) are deck furniture, not the argument — use them for connective tissue between slides (opening, orienting, transitioning, closing) and spend the insight-headline discipline on the content slides they connect. 6. Apply the visual system in `references/style-system.md`, using the canvas from the document profile. Write copy to its Word Budget: when text does not fit, cut words or split the slide — never shrink type. 7. Produce a structured spec, diagram-as-code source, or image-generation prompt using `references/prompt-templates.md`. When the environment allows running scripts, render supported patterns to SVG with `python3 scripts/render_slide_spec.py <spec.json>`. Twenty-two patterns render (cover, section_divider, end_cover, agenda, bullet_list, closing, quote, waterfall, gap, before_after, time_series, benchmark_table, summary_strip, process_flow, funnel, heatmap, gantt, kpi_scorecard, two_by_two, scatter, distribution, small_multiples), on a 16:9 canvas only; every other pattern and canvas is spec-only. `cover`, `section_divider`, and `end_cover` are full-bleed navy and skip the header/footer chrome; every other renderable pattern uses the standard white content chrome. Tell the user which they are getting — never imply a spec-only pattern will render. Spec examples are in `examples/render-specs/`. 8. Score the output against `references/quality-rubric.md`. For decks, also run its deck-level headline check. 9. Flag missing data, unverifiable claims, source-sensitive assumptions, or trademark-sensitive wording. 10. For public, high-stakes, cross-functional, or broad-audience work, run `references/expert-review-loop.md` to remove blind spots, overclaims, jargon, accessibility issues, and cultural assumptions. 11. For polished executive work, run the draft through `references/iterative-review-loop.md` until the output reaches the stopping criteria. ## Output Contract Return a concise deliverable with: - `Strategic question` (or the reader's key question for non-strategy documents) - `Insight headline` - `Recommended visualization` - `Slide spec` (or figure, page, or diagram spec matching the document profile) - `Data and assumptions` - `Quality check` - `Expert review notes` when the output is public, high-stakes, cross-functional, or broad-audience When the user requests a batch, deck, or multi-figure document, repeat the contract per visual and add a brief flow summary explaining how the visuals build the argument. ## Reference-led reproduction When the user requests a particular firm's style or supplies a reference, read `references/reference-reproduction.md` before selecting a theme. Consult `references/consulting-reference-evidence.json` and inspect the specific source page. Record geometry, hierarchy, chart encoding, notes and deviations. Choose presentation, analytical pre-read, or reading document explicitly. Do not claim exact fidelity from a colour preset alone. The worked examples are in `templates/reference-layouts/`. ## Default Visual Standards - ForREADME.mdupstream ↗
Contents are not inlined in the catalog. Open the upstream file.
Plain-text copy, no login: /skill-bundles/kgraph57-mckinsey-style-visualization-skill.md
