Phase 3 deep diligence: NTB quality check, driver tree, boundability assessment, financial model, GTM metrics, and KPI tree. Requires data room for financial/GTM skills.
Decomposes investment theses into driver trees with T1–T4 evidence tiers, then converts load-bearing drivers and material diligence findings into underwriting decisions through a 6-module assessment. Use when Ian asks to "assess boundability," "bound this risk," "build a driver tree," "decompose this thesis," "score the drivers," "run underwriting analysis on [issue]," "what does this mean for our underwrite," "convert diligence to underwriting," "score this for IC," "price this risk," "what's the perimeter on X," "can we underwrite this?" "how confidently can we bound this driver," "what's load-bearing in this thesis," or "run a cascade scenario." Produces a driver tree, structured issue objects, deal summary, and final deal view (proceed / proceed with protections / reprice / pass). Single-asset analysis only — does not perform portfolio construction or position sizing. Distinct from pre-mortem (which enumerates failure pathways) and claim-scrutinizer (which tests bull-case logic). Boundability decomposes the thesis, isolates what is load-bearing, and converts identified risk into specific underwriting action.
Decomposes investment theses into MECE driver trees, assigns evidence tiers (T1–T4) to each leaf node, and surfaces what a thesis is actually built on. Use when Ian asks to "build a driver tree," "decompose this thesis," "score the drivers," "map the revenue tree," "what's load-bearing in this thesis," "tier the drivers," "run a base-rate overlay," "check the vintage on this evidence," "run a cascade scenario," "what's the variance-dominant driver," or "do a structural assessment of [company]." Single-asset methodology only. Produces a driver tree with tiers and directionality, segment driver tables with historical/today/path/tier/impact/boundability columns, base-rate overlay for load-bearing drivers, vintage check on supporting evidence, variance amplification analysis, downside and upside cascade scenarios, and a framework self-audit. Output is a methodology document — does not produce underwriting actions, deal verdicts, or position sizing. Distinct from boundability (which converts driver work into underwriting structure), pre-mortem (which enumerates failure pathways), and claim-scrutinizer (which tests bull-case logic). Driver-tree is the structural decomposition step that those other skills build on.
**SaaS / Operating Model Financial Template Builder**: Reads a source Excel operating model (P&L, Balance Sheet) and generates a standardized 3-tab financial model with Input Page, Financial Model Template, and Output Tab. - MANDATORY TRIGGERS: "build financial model", "run the template", "create financial model template", "3-tab model", "generate financial model", "financial model from P&L" - Use this skill whenever a user uploads an Excel file containing a P&L or income statement and wants a structured financial model built from it - Also triggers for: "Input Page + FMT + Output Tab", "6+6 analysis", "go-forward analysis", "SaaS model template", "turn this P&L into a model", "build a model from this", "model this out", "create a financial template", "build the pattern template model"
calculate, interpret, and package b2b saas go-to-market metrics into a diagnostic excel workbook using the bundled metric catalog, formulas, and input requirements. use when a user uploads gtm tables, exports, board files, forecasts, or operating spreadsheets and wants a clean excel-based diagnostic analysis of growth drivers, arr funnel, pipeline, retention, efficiency, productivity, or forecast metrics. ask for missing uploaded inputs, distinguish provided values from derived calculations, and populate the bundled workbook tabs for inputs, metric calculations, and diagnostic output.
build, audit, and maintain company-specific kpi trees that decompose a budget, forecast, or operating target into causal drivers and atomic inputs. use when a user wants to break revenue, margin, opex, headcount, cash flow, or other plan lines into measurable drivers; create a diligence-ready budget framework; translate a model into operating inputs; or define what should be tracked weekly and monthly post-close. especially useful in late diligence, annual planning, monthly business reviews, and post-acquisition operating cadence design.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Pattern's modular skill architecture for Claude. Each skill is a folder containing a SKILL.md file that instructs Claude on methodology, output format, and quality standards for a specific domain. Skills are loaded on-demand — Claude reads the relevant SKILL.md before executing any task in its domain.
31 skills across 8 groups and 4 functional layers, plus 2 multi-agent pipelines. Every formal output runs through at least two layers — usually three or four. Layers are not optional — skipping a layer produces a draft, not a deliverable.
Source of truth: This README reflects the folders in
ian-lawrence423/Claude-skills. Update this file whenever skills are added or removed from the repo.
The skill library has four functional layers. The mandatory sequence for any formal output:
Critical: Never trigger a document production skill without running the quality layer first. A file produced without
writing-styleandclaim-scrutinizerwill fail thedoc-quality-checkerpass and require a full rebuild.
| Layer | Skills | What It Owns | When It Runs |
|---|---|---|---|
| 1 — Analytical OS | mckinsey-consultant | Problem structuring, MECE trees, frameworks, claim labeling (F/E/H), Six Screening Questions | Always active for strategy or investment work |
| 2 — Research | market-research, ntb-diligence, ic-memo, competitive-moat-assessment, executive-summary-writer, driver-tree, tam-sam-som-calculator, statistics-fundamentals, finance-metrics-quickref, gtm-metrics-analyzer | Evidence gathering, research workflow, deliverable architecture, metrics analysis | When research or a specific deliverable type is needed |
| 3 — Quality | writing-style ⚙️, claim-scrutinizer, red-team, pre-mortem, boundability | Prose standards, claim testing, adversarial stress-testing, failure mode enumeration | During drafting (writing-style) and after draft (all others) |
| 4 — Production | pattern-docx, pattern-investment-pptx, diligence-ddr, financial-model-builder, executive-briefing, written-communication, giving-presentations | Branded file output in correct format with header/footer/logo | Final step — after analytical and quality layers complete |
| 4b — QA | doc-quality-checker ⚙️ | Brand compliance, formatting, internal consistency, draft artifact language check | Auto-runs after every Layer 4 file output |
These two skills execute on every relevant output without being explicitly invoked:
| Skill | Auto-Runs When... |
|---|---|
writing-style | Any final or near-final formal output — memos, reports, investment theses, PPTX narrative text |
doc-quality-checker | After any pattern-docx or pattern-investment-pptx file is produced |
All other skills are invoked by name when the task matches their trigger criteria.
All 31 skills organized by group. Invoke the most specific skill first; fall back to broader skills if needed.
npx claudepluginhub ian-lawrence423/claude-skills --plugin deal-diligenceProvision direct cloud access (Vertex AI, Bedrock, or LLM gateway) for the Claude Office add-in. Generates the customized add-in manifest, walks through Azure admin consent, and writes per-user config via Microsoft Graph extension attributes.
Investment banking productivity tools: client and market insights, deck creation, financial analysis, and transaction management
Equity research tools: earnings analysis, initiating coverage reports, and research workflows
Core financial modeling and analysis tools: DCF, comps, LBO, 3-statement models, competitive analysis, and deck QC
S&P Global - Financial data and analytics skills including company tearsheets, earnings previews, and transaction summaries
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
UI/UX design intelligence. 67 styles, 161 palettes, 57 font pairings, 25 charts, 15 stacks (React, Next.js, Vue, Svelte, Astro, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, Nuxt, Jetpack Compose). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient.