A source-grounded consulting delivery workflow that transforms scattered client inputs into validated storylines, executive presentations, strategy documents, and speaker scripts.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install mckinsey-library
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
Copy this prompt to OpenClaw to install it automatically.
Help me install mckinsey-library using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
McKinsey Library Consultant is one of the Openclaw Skills designed for structured, evidence-backed consulting work. It analyzes uploaded documents, datasets, notes, and meeting records using a methodology library derived from 44 user-provided McKinsey materials, then converts the inputs into a focused decision question, MECE logic tree, research plan, and persuasive storyline.
The skill supports the full delivery lifecycle: it identifies evidence gaps, conducts external research, validates sources, creates a storyline Markdown file, and—after client confirmation—generates a PPT deck and complete presentation script. Its layout-selection library, reusable Python-PPTX primitives, source footnotes, and mandatory Critic visual quality gate help produce consulting deliverables that are clear, traceable, and ready for review.
references/rulebook.md, references/materials_index.md, references/methodology.md, references/intake_questions.md, references/storyline_template.md, references/external_research.md, references/layout_selection.md, references/visualization_layouts.md, references/critic_checklist.md, and assets/pptx_primitives.py.# Verify the expected reference and asset directories
find references -maxdepth 1 -type f | sort
ls -l assets/pptx_primitives.py
# Optional: verify commonly required local tools
python --version
libreoffice --version
The skill organizes work around phases, source provenance, analysis branches, and deliverable status.
| Data area | Organization and purpose |
|---|---|
| Methodology library | The 44 user-provided source materials are routed through materials_index.md, rulebook.md, methodology.md, and functional playbooks. The index tracks applicable materials, deduplication, usage, and unavailable or failed items. |
| Intake record | Captures the core problem or hypothesis, decision-maker, audience, timeline, success criteria, precision requirement, and desired action. |
| Logic tree | Stores MECE branches, hypotheses, questions, analyses, prioritization decisions, and the rationale for removing non-key issues. |
| Evidence-gap register | Maps each branch to missing evidence, the affected conclusion, proposed search approach, source status, and validation needs. |
| Research source map | Records source URL or reference, source tier, publication date, metric definition, statistical scope, claim supported, and whether independent triangulation is complete. |
| Storyline artifact | Generates 故事线_<主题>.md, containing the problem definition, logic tree, workplan, analysis, evidence plan, storyline, source notes, presentation structure, and speaker-script sections. |
| Layout plan | Documents each page’s intended message, candidate visualization, selected layout, selection rationale, chart type, and relationship to the Critic checklist. |
| Presentation artifact | Produces a PPT deck using reusable colors, fonts, cards, native charts, Treemap, Mekko, waterfall, funnel, matrix, and dashboard-style primitives. |
| Speaker script | Generates 演讲稿_<主题>.md with a 30-second opening, page-by-page narration, transitions, emphasis and pause cues, closing actions, and three to five anticipated Q&A responses. |
| Quality metadata | Labels outputs as “ready to use” or “requires confirmation,” records source footnotes, tracks Critic findings, and identifies corrected pages after re-rendering. |
Core governance rules include one idea per page, action-oriented titles, explicit source footnotes, transparent estimates, correct visualization selection, and a hard storyline-confirmation gate before final PPT delivery.
pptx_primitives.py rendering engine with native charts and area-based visuals such as Treemap, Mekko, waterfall, funnel, matrix, and gauge layouts.Loading
Toolbelt gives AI agents a shared, queryable workspace for documents, structured data, entities, relationships, and persistent findings.

Turn historical battles and military conflicts into rigorously researched, single-screen mobile PNG briefings with tactical analysis and source citations.

An evidence-first Openclaw Skills workflow that transforms arXiv literature into validated field intelligence, technical options, maturity assessments, and actionable decisions.

AI Tech Insight Compass turns daily AI trend research into source-backed, publication-ready technical articles.

An implementation workflow that isolates code changes, validates them, commits and pushes the result, and opens a draft GitHub pull request.

A guided co-creation skill that transforms imaginative dialogue into vivid surreal scenes and production-ready image prompts.








































