skills/dividend-buyback-analyzer/SKILL.md
Determines how much cash a company can return to shareholders and whether to use dividends, buybacks, or retained earnings. Compares actual cash returns to FCFE capacity, identifies excess cash on the balance sheet, and recommends an optimal return policy. Use when analyzing dividend policy, evaluating share buybacks, assessing cash return capacity, or when user mentions dividend policy, buyback, share repurchase, FCFE, payout ratio, cash return, or excess cash.
npx skillsauth add lyndonkl/claude dividend-buyback-analyzerInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Scenario: Mature tech company -- assess whether it is returning enough cash to shareholders and in what form.
Inputs:
Step 1 -- Compute FCFE:
FCFE = Net Income - (CapEx - Depreciation) - Change in WC + (Debt Issued - Debt Repaid)
FCFE = $2.0B - ($600M - $400M) - $50M + ($300M - $200M)
FCFE = $2.0B - $200M - $50M + $100M = $1.85B
Step 2 -- Compare to actual returns:
Total cash returned = Dividends + Buybacks = $400M + $600M = $1.0B
FCFE gap = $1.85B - $1.0B = $850M (under-returning)
Cash return ratio = $1.0B / $1.85B = 54% (returning only ~half of capacity)
Step 3 -- Assess excess cash:
Operating cash needs = Revenue x 3% = $15B x 0.03 = $450M
Excess cash = $8.0B - $450M = $7.55B
Step 4 -- Evaluate reinvestment quality:
ROC (12%) > WACC (10%) -- still earning above cost of capital
But gap is narrowing and reinvestment opportunities are declining
Step 5 -- Determine dividend vs buyback split:
Step 6 -- Recommendation:
Copy this checklist and track your progress:
Dividend & Buyback Analysis Progress:
- [ ] Step 1: Compute FCFE (what the company can afford to return)
- [ ] Step 2: Compare to actual cash returned (dividends + buybacks)
- [ ] Step 3: Assess excess cash on balance sheet
- [ ] Step 4: Evaluate reinvestment quality (ROC vs WACC)
- [ ] Step 5: Determine optimal split (dividends vs buybacks)
- [ ] Step 6: Make recommendation
Step 1: Compute FCFE
Calculate free cash flow to equity -- the maximum sustainable cash return to shareholders. See resources/template.md for the computation worksheet and resources/methodology.md for the conceptual framework.
FCFE = Net Income - (CapEx - Depreciation) - Change in WC + (Debt Issued - Debt Repaid)
If FCFE is negative, the company cannot sustainably return cash and should be retaining or raising capital instead. Use multi-year average FCFE for cyclical companies.
Step 2: Compare to actual cash returned
Compute total cash returned (dividends + buybacks) and compare to FCFE. See resources/template.md for the comparison table.
Three outcomes:
Step 3: Assess excess cash on balance sheet
Determine how much cash exceeds operating needs. See resources/methodology.md for industry norms on operating cash requirements.
Excess Cash = Cash on Hand - Operating Cash Needs
Operating Cash Needs typically = 2-5% of Revenue (varies by industry)
Large excess cash indicates accumulated under-returning. This is a stock of past under-distribution, separate from the flow (FCFE vs returns).
Step 4: Evaluate reinvestment quality
Assess whether the company has profitable uses for retained cash. See resources/methodology.md for the ROC vs WACC framework.
Step 5: Determine optimal split (dividends vs buybacks)
Choose the return mechanism based on cash flow predictability, tax regime, and investor base. See resources/methodology.md for the full decision framework.
Key considerations:
Step 6: Make recommendation
Synthesize findings into a concrete policy recommendation. See resources/template.md for the recommendation template. Validate using resources/evaluators/rubric_dividend_buyback_analyzer.json. Minimum standard: average score of 3.5 or higher.
Pattern 1: Cash Hoarder
Pattern 2: Dividend Stretcher
Pattern 3: High-Growth Retainer
Pattern 4: Mature Returner
FCFE sets the ceiling on sustainable cash returns. Dividends plus buybacks cannot exceed FCFE indefinitely without depleting cash or increasing debt. Short-term over-distribution is acceptable if FCFE is temporarily depressed, but multi-year over-distribution is unsustainable.
Dividends create expectations; buybacks are flexible. Match the return mechanism to cash flow predictability. Stable, predictable cash flows support dividends. Variable or cyclical cash flows favor buybacks as the primary return vehicle.
Tax regime affects the optimal split. If capital gains are taxed at a lower rate than ordinary income (dividends), buybacks are more tax-efficient for shareholders. Consider the investor base: tax-exempt institutions are indifferent; taxable individuals prefer the lower-taxed form.
Excess cash calculation requires estimating operating cash needs. Operating cash needs typically range from 2% of revenue (stable, predictable businesses) to 5% of revenue (cyclical or seasonal businesses). Cash beyond this threshold is excess and should be evaluated for return to shareholders.
If ROC exceeds WACC and the company has good projects, retention is appropriate. A high FCFE does not automatically mean the company should return it all. The quality of reinvestment opportunities matters -- but hold management accountable for delivering returns above cost of capital.
Compare payout policy to peers. Check the company's payout ratio, dividend yield, and total yield against industry norms. Significant deviations should be explained by differences in growth, risk, or reinvestment opportunity.
Common pitfalls:
Key formulas:
FCFE = Net Income - (CapEx - Depreciation) - Change in WC + (Debt Issued - Debt Repaid)
Cash Returned = Dividends + Share Buybacks
Cash Return Ratio = Cash Returned / FCFE
Payout Ratio = Dividends / Net Income
Excess Cash = Cash on Hand - Operating Cash Needs
Dividend Yield = Dividends per Share / Price per Share
Buyback Yield = Value of Shares Repurchased / Market Cap
Total Shareholder Yield = Dividend Yield + Buyback Yield
Operating Cash Needs = Revenue x Operating Cash % (typically 2-5%)
Decision framework:
| Cash Return Ratio | ROC vs WACC | Excess Cash | Recommendation | |-------------------|-------------|-------------|----------------| | < 50% of FCFE | ROC < WACC | Large | Increase returns substantially; return excess cash | | < 50% of FCFE | ROC > WACC | Moderate | Retain for reinvestment if projects are strong | | 50-80% of FCFE | ROC > WACC | Low | Reasonable balance; fine-tune split | | 80-100% of FCFE | ROC near WACC | Low | Optimal range for mature companies | | > 100% of FCFE | Any | Declining | Unsustainable; reduce returns to FCFE level |
Dividend vs buyback selection:
| Factor | Favors Dividends | Favors Buybacks | |--------|-----------------|-----------------| | Cash flow stability | Stable, predictable | Variable, cyclical | | Tax regime | Dividends taxed same or lower | Capital gains taxed lower | | Investor base | Income-seeking (retirees, funds) | Growth-oriented, tax-sensitive | | Stock valuation | N/A | Undervalued (accretive) | | Signaling intent | Commitment to ongoing returns | Flexibility, opportunistic | | Management confidence | High confidence in sustainability | Uncertainty about future cash flows |
Key resources:
Inputs required:
Outputs produced:
dividend-buyback-analysis.md: Complete analysis with FCFE computation, cash return comparison, excess cash assessment, reinvestment quality evaluation, dividend vs buyback recommendation, peer comparison, projected cash accumulation under current vs recommended policytesting
Cluster a conference's event records into a small set of coarse themes with finer sub-clusters, an explicit outlier bucket, and soft (multi-membership) affinities — using the hybrid embed-then-label pipeline (embed abstracts, reduce, density-cluster, then LLM-label the clusters) when embedding libraries are available, and an LLM-reasoned hierarchical fallback when they are not. Embeddings do the grouping; the LLM only names the groups. Conference-agnostic. Use when turning structured event records into a navigable theme map for preference elicitation and scheduling, when you need 6-8 reasonable themes rather than 20 muddy ones, or when overlapping talks must belong to more than one theme. Trigger keywords - theme clustering, cluster talks, embed then label, soft membership, outlier talks, conference themes, topic map.
development
Build a personal conference schedule as a constraint-optimization problem — hard constraints (no time overlap, room-to-room travel time, capacity/registration, the attendee's own must-attends and blackouts) plus a user-owned weighted objective trading interest against breadth, pacing (maximize contiguous free time), and serendipity. Surfaces unbreakable conflicts (two high-value overlapping talks the model cannot rank) as decisions for the human rather than silently picking, and reports what each choice traded away. Conference-agnostic. Use to turn a preference profile plus a theme map into a day-by-day plan, to resolve overlapping sessions, or to balance a packed vs paced schedule. Trigger keywords - schedule optimization, conference schedule, constraint optimization, overlapping talks, contiguous free time, conflict surfacing, packed vs paced.
development
Parse a heterogeneous conference program (markdown, HTML, PDF-derived text, or JSON) into normalized event records with per-field confidence scores and independent classification axes (topic, depth, format, prerequisites, recorded, capacity). Detects the program's format before extracting, treats every inferred field as uncertain (present vs inferred vs missing), and flags thin or missing abstracts so downstream enrichment can target them. Conference-agnostic. Use when ingesting a conference or event schedule into a structured store, normalizing a talk/session list, or extracting per-session metadata with calibrated confidence. Trigger keywords - program ingestion, parse schedule, session extraction, event records, conference program, talk metadata, per-field confidence.
development
Build a personalized preference profile from a small number of well-chosen, cluster-grounded questions instead of a long survey. Represents the person's interests as an uncertainty region over the theme map, picks the single highest-information-gain choice-based question (contrasting real talks from different clusters), balances exploiting known interests against exploring uncertain ones, deliberately injects outlier probes to fight selection bias, and stops as soon as the schedule would be stable. Also elicits the user-owned objective weights and hard constraints. Interactive — runs where it can actually ask the person. Conference-agnostic. Use to turn a theme map into a preference profile, to decide what to ask a conference attendee, or to elicit scheduling priorities. Trigger keywords - preference elicitation, ask few questions, information gain, choice-based questions, selection bias probe, objective weights, attendee preferences.