McKinsey Library Consultant for Openclaw

A source-grounded consulting delivery workflow that transforms scattered client inputs into validated storylines, executive presentations, strategy documents, and speaker scripts.

forrestneo
v0.1.0
Aug 11, 2026
0
1.8k
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install mckinsey-library

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

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).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is McKinsey Library Consultant?

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.

McKinsey Library Consultant Use Cases

  • Turn unstructured client documents, spreadsheets, notes, or meeting records into a structured consulting proposal.
  • Define a single decision-oriented problem statement and clarify the decision-maker, timeline, success criteria, and expected action.
  • Build MECE issue trees, hypothesis-driven analyses, 80/20 prioritization, and executive-ready storylines.
  • Identify missing industry benchmarks, competitor comparisons, market data, policy evidence, customer proof, or expert judgment.
  • Research external evidence through WebSearch and WebFetch, then triangulate important claims across independent sources.
  • Create a McKinsey-style PPT presentation with action titles, charts, process diagrams, maps, organizational views, and source footnotes.
  • Generate a complete speaker script with opening remarks, page-by-page narration, transitions, closing recommendations, and anticipated Q&A.
  • Use Openclaw Skills for an end-to-end consulting workflow when authorized, while preserving the storyline-first and approval-gate discipline.

How McKinsey Library Consultant Works

  1. Route the request through the methodology library: The skill consults the rulebook, materials index, methodology references, intake questions, storyline template, external research guidance, strategy playbooks, and functional playbooks.
  2. Lock the problem: It asks five to seven focused intake questions covering the core problem or hypothesis, decision-maker, timing, success metrics, required precision, and desired audience action.
  3. Map the analysis: It selects an appropriate MECE structure, such as a hypothesis tree, issue tree, or argument tree, and decomposes the central question into testable branches.
  4. Prioritize the work: It applies 80/20 filtering and repeated “so what?” checks to remove low-value branches and retain the analyses most relevant to the decision.
  5. Find evidence gaps: Each retained branch is checked for missing benchmarks, market figures, competitor data, policy sources, customer validation, or expert input.
  6. Research and validate externally: When internal materials are insufficient, the skill searches across relevant keyword groups and topics, fetches authoritative sources, ranks source quality, records dates and definitions, and triangulates key claims with at least two independent sources when possible.
  7. Build the storyline Markdown file: It records the problem, hypotheses, logic tree, workplan, analysis, source map, evidence gaps, recommendations, and presentation narrative using introduction, body, and conclusion logic.
  8. Pause at the approval gate: PPT and final speaker-script generation remains blocked until the client confirms the storyline, unless the user explicitly authorizes autonomous end-to-end orchestration.
  9. Select visual layouts: For each page, the skill maps the intended message to a suitable layout from a 50+ pattern library, documents the selection rationale, and produces a layout plan.
  10. Generate presentation deliverables: It creates the PPT with reusable chart and design primitives, produces full speaker notes, and labels outputs as ready to use or requiring confirmation.
  11. Run the Critic quality gate: The deck is rendered to PDF and page images, inspected against a 12-point visual checklist, corrected where necessary, and rechecked before delivery.

McKinsey Library Consultant Setup

  1. Install or enable the McKinsey Library Consultant skill in the target OpenClaw-compatible agent environment.
  2. Place the complete reference library and asset directories alongside the skill. The workflow expects paths such as 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.
  3. Provide the source materials for the engagement, including documents, data, notes, meeting records, or other client inputs. If the archived McKinsey library is available locally, preserve its original terminology and source mapping.
  4. Ensure the runtime can access the research and presentation tools used by the workflow, including WebSearch, WebFetch, Python/Python-PPTX, LibreOffice for PDF conversion, and PyMuPDF for page rendering and inspection.
  5. Start the workflow with a consulting request such as “help me create a consulting proposal,” “create a PPT from these materials,” or “organize this storyline using McKinsey methods.”
# 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
  1. Review and confirm the generated storyline before allowing Phase 3 presentation generation. In autonomous orchestration mode, explicitly authorize end-to-end execution; the Critic quality gate still cannot be skipped.

McKinsey Library Consultant Data Schema & Taxonomy

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.

McKinsey Library Consultant Advanced Features

  • Full 44-document methodology routing with a materials index, rulebook, source archive, and 33-item application ledger.
  • Seven-step problem-solving discipline covering problem definition, logic-tree decomposition, prioritization, work planning, analysis, storyline synthesis, and delivery.
  • Five external research approaches, including full-potential scanning, sequential analysis, objective-value analysis, value assessment, and evidence-gap-driven search.
  • Source hierarchy and triangulation controls that distinguish primary government, regulatory, financial, research, media, and self-published sources.
  • Autonomous orchestration from intake through research, storyline, PPT, and speaker script when the user explicitly authorizes it.
  • Mandatory storyline-first approval gate that prevents premature presentation generation.
  • 50+ visualization layouts with explainable AX Labs-style layout selection and a generated layout planning table.
  • Reusable pptx_primitives.py rendering engine with native charts and area-based visuals such as Treemap, Mekko, waterfall, funnel, matrix, and gauge layouts.
  • Presentation storytelling rules that separate Treemap hierarchy views from Mekko comparison views and preserve source footnotes and rounding disclosures.
  • Complete speaker-script generation with conversational narration, transitions, delivery cues, closing recommendations, and Q&A preparation.
  • Critic visual quality gate that renders slides through LibreOffice and PyMuPDF, checks 12 defect categories, fixes high-severity issues, and rechecks affected pages.
  • Clear delivery-status metadata distinguishing outputs that are directly usable from those awaiting client confirmation or minor refinement.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*