Deep dive into capital deployment, buybacks, dividends, and shareholder yield
npx skills add https://github.com/openai/plugins --skill capital-allocation
Perform a deep dive into capital allocation for the company named in the user's request. If no ticker or company is provided, ask for one before proceeding.
Before starting, read ../data-access.md for data access methods and ../design-system.md for formatting conventions. Follow the data access detection logic and design system throughout this skill.
Follow these steps:
Look up the company by ticker using discover_companies. Capture:
company_idlatest_calendar_quarter — anchor for all period calculations below (see ../data-access.md Section 1.5)latest_fiscal_quarter../data-access.md Section 4.5Get the current stock price, market cap, and shares outstanding for {TICKER} (see ../data-access.md Section 2 for how to source market data in your environment).
If market data is unavailable, note that market-derived metrics (yields, etc.) cannot be computed and proceed with Daloopa data only.
Calculate 8 quarters backward from latest_calendar_quarter. Pull:
Share Count & Buybacks:
Dividends:
Cash Flow:
Balance Sheet:
M&A / Investments:
Calculate for each quarter where data is available:
Shareholder Returns:
FCF Deployment:
Leverage:
Share Count Dynamics:
Search SEC filings for capital allocation strategy and context. Try multiple searches:
Extract:
Analyze the 8-quarter trend:
Honestly assess whether capital allocation is creating or destroying value:
Assess whether the company is adequately reinvesting in its business or funding returns at the expense of long-term competitiveness.
Pull reinvestment metrics (8 quarters):
Assess reinvestment adequacy:
Value creation vs extraction verdict:
Save to reports/{TICKER}_capital_allocation.html using the HTML report template from ../design-system.md. Write the full analysis as styled HTML with the design system CSS inlined. This is the final deliverable — no intermediate markdown step needed.
Structure the report with these sections:
<h1>{Company Name} ({TICKER}) — Capital Allocation Analysis</h1>
<p>Generated: {date}</p>
<h2>Summary</h2>
{2-3 sentences: How does this company deploy its capital? Key takeaways.}
<h2>Current Snapshot</h2>
<table>
| Metric | Value |
| Market Cap | $XXX |
| Trailing 4Q FCF | $XXX |
| FCF Yield | X.X% |
| Shareholder Yield | X.X% |
| Net Debt / EBITDA | X.Xx |
| Remaining Buyback Authorization | $XXX |
</table>
<h2>Cash Flow & FCF (8 Quarters)</h2>
<table>
| Metric | Q1 | Q2 | ... | Q8 |
{OCF, CapEx, FCF, FCF Margin % — with Daloopa citations}
</table>
<h2>Share Repurchases & Dividends (8 Quarters)</h2>
<table>
| Metric | Q1 | Q2 | ... | Q8 |
{Buyback $, Dividends $, Total Return, Share Count — with Daloopa citations}
</table>
<h2>Shareholder Yield Analysis</h2>
<table>
| Metric | Q1 | Q2 | ... | Q8 |
{Buyback Yield, Div Yield, Total Yield, FCF Payout Ratio}
</table>
<h2>Leverage & Balance Sheet (8 Quarters)</h2>
<table>
| Metric | Q1 | Q2 | ... | Q8 |
{Cash, Debt, Net Debt, Net Debt/EBITDA — with Daloopa citations}
</table>
<h2>Capital Allocation Framework</h2>
{Management's stated priorities from filings, with document citations}
<h2>Reinvestment Assessment</h2>
<table>
| Metric | Q1 | Q2 | ... | Q8 |
{R&D, R&D % Rev, CapEx, CapEx % Rev, key growth KPIs — with Daloopa citations}
</table>
{Analysis: Is the company adequately reinvesting? R&D/CapEx trends vs growth KPI trends. Value creation vs extraction verdict.}
<h2>Buyback Discipline Analysis</h2>
{Analysis of buyback timing vs price, share count reduction trend, authorization remaining}
<h2>M&A Activity</h2>
{Any acquisitions from filings, deal sizes, strategic rationale}
<h2>Key Observations</h2>
<ul>{3-5 bullet points on capital allocation quality, trends, and implications}</ul>
All financial figures must use Daloopa citation format: <a href="https://daloopa.com/src/{fundamental_id}">$X.XX million</a>
Tell the user where the HTML report was saved.
Highlight the key capital allocation story (e.g., "AAPL returned $XX billion to shareholders over the last year, a X.X% shareholder yield, with buybacks accelerating").
Assess Kubernetes workloads and cluster configuration for AKS Automatic compatibility. Identifies incompatibilities, generates fixes, and guides migration from AKS Standard to AKS Automatic. WHEN: migrate to AKS Automatic, check AKS Automatic readiness, validate manifests for Automatic, assess cluster for Automatic compatibility, fix deployment for Automatic compatibility, identify AKS Automatic migration blockers, is my cluster ready for AKS Automatic.
Discovers available Azure OpenAI model capacity across regions and projects. Analyzes quota limits, compares availability, and recommends optimal deployment locations based on capacity requirements. USE FOR: find capacity, check quota, where can I deploy, capacity discovery, best region for capacity, multi-project capacity search, quota analysis, model availability, region comparison, check TPM availability. DO NOT USE FOR: actual deployment (hand off to preset or customize after discovery), quota increase requests (direct user to Azure Portal), listing existing deployments.
Interactive guided deployment flow for Azure OpenAI models with full customization control. Step-by-step selection of model version, SKU (GlobalStandard/Standard/ProvisionedManaged), capacity, RAI policy (content filter), and advanced options (dynamic quota, priority processing, spillover). USE FOR: custom deployment, customize model deployment, choose version, select SKU, set capacity, configure content filter, RAI policy, deployment options, detailed deployment, advanced deployment, PTU deployment, provisioned throughput. DO NOT USE FOR: quick deployment to optimal region (use preset).
Unified Azure OpenAI model deployment skill with intelligent intent-based routing. Handles quick preset deployments, fully customized deployments (version/SKU/capacity/RAI policy), and capacity discovery across regions and projects. USE FOR: deploy model, deploy gpt, create deployment, model deployment, deploy openai model, set up model, provision model, find capacity, check model availability, where can I deploy, best region for model, capacity analysis. DO NOT USE FOR: listing existing deployments (use foundry_models_deployments_list MCP tool), deleting deployments, agent creation (use agent/create), project creation (use project/create).
Intelligently deploys Azure OpenAI models to optimal regions by analyzing capacity across all available regions. Automatically checks current region first and shows alternatives if needed. USE FOR: quick deployment, optimal region, best region, automatic region selection, fast setup, multi-region capacity check, high availability deployment, deploy to best location. DO NOT USE FOR: custom SKU selection (use customize), specific version selection (use customize), custom capacity configuration (use customize), PTU deployments (use customize).
This skill should be used when working with LaminDB, an open-source data framework for biology that makes data queryable, traceable, reproducible, and FAIR. Use when managing biological datasets (scRNA-seq, spatial, flow cytometry, etc.), tracking computational workflows, curating and validating data with biological ontologies, building data lakehouses, or ensuring data lineage and reproducibility in biological research. Covers data management, annotation, ontologies (genes, cell types, diseases, tissues), schema validation, integrations with workflow managers (Nextflow, Snakemake) and MLOps platforms (W&B, MLflow), and deployment strategies.
Latch platform for bioinformatics workflows. Build pipelines with Latch SDK, @workflow/@task decorators, deploy serverless workflows, LatchFile/LatchDir, Nextflow/Snakemake integration.
Run Python code in the cloud with serverless containers, GPUs, and autoscaling. Use when deploying ML models, running batch processing jobs, scheduling compute-intensive tasks, or serving APIs that require GPU acceleration or dynamic scaling.
Take openai/capital-allocation from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.