stock-management-review
Skill30 starsChanged 4 months agoMITView on GitHub
Review a US-listed company's management quality and capital-allocation track record for an equity-research workup. Covers 5-year capital-allocation history (buybacks vs dividends vs M&A vs capex vs debt), buyback timing, M&A return-on-investment, guidance-vs-actuals track record, comp-structure alignment, insider ownership and trading activity, earnings-call communication style, and strategic-thesis stability. Trigger when analyzing the human-judgment layer (L5 of the seven-layer X-ray) — the most under-rated and longest-impact dimension. Dispatched by stock-analysis-lead.
In this repository52 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- api-designSkill
- api-integration-testSkill
- constructive-thinkingSkill
- create-prSkill
- deep-researchSkill
- e2e-testSkill
- fuzzing-testSkill
- git-commitSkill
- go-benchmarkSkill
- go-ci-workflowSkill
- go-code-reviewerSkill
- go-concurrency-reviewSkill
- go-dependency-auditSkill
- go-error-reviewSkill
- go-logic-reviewSkill
- go-makefile-writerSkill
- go-observability-reviewSkill
- google-searchSkill
- go-performance-reviewSkill
- go-quality-reviewSkill
- go-review-leadSkill
- go-security-reviewSkill
- go-test-reviewSkill
- incident-postmortemSkill
- kafka-event-driven-designSkill
- load-testSkill
- local-transcriptSkill
- log-analyzerSkill
- mongo-migrationSkill
- monitoring-alertingSkill
- mysql-migrationSkill
- oceanbase-table-designSkill
- oracle-migrationSkill
- pg-migrationSkill
- readme-generatorSkill
- redis-cache-strategySkill
- security-reviewSkill
- stock-analysis-leadSkill
- stock-balance-sheet-reviewSkill
- stock-business-reviewSkill
- stock-earnings-quality-reviewSkill
- stock-industry-reviewSkill
- stock-peer-comparison-reviewSkill
- systematic-debuggingSkill
- tdd-workflowSkill
- tech-doc-writerSkill
- thirdparty-api-integration-testSkill
- unit-testSkill
- update-docSkill
- writing-plansSkill
- yt-dlp-downloaderSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 44
Read the most recent earnings call for tone.
- Very specific: line 152
Every finding ID must start with MGT — the prefix is the whole segment before the first hyphen.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Stock Management Review
Purpose
Read DEF 14A (proxy), Letter to Shareholders, last 4 earnings-call transcripts, and 5-year capital-allocation history with a single question in mind: would I trust this CEO with my money for the next decade? Identify capital allocation skill (buyback timing, M&A discipline), credibility (guidance-vs-actuals), incentive alignment (comp structure), skin-in-the-game (insider ownership and trading), and communication honesty (call transcript style). Output structured Findings on management quality — orchestrator weights this heavily in long-horizon scenarios.
When To Use
- Orchestrator dispatches management review — a Tier-1 conditional worker: always at Standard / Strict depth, and at Lite depth when DEF 14A + a transcript are both present, when the question targets capital allocation / M&A / buybacks / insiders / guidance credibility, or when the archetype is Mature Cash Cow / Capital-Intensive / Financials / REIT (capital allocation is the thesis for those). See
stock-analysis-lead/references/dispatch-protocol.mdPart 1. - User asks "is the management good", "what's the CEO's track record", "are they good capital allocators".
When NOT To Use
- Financial statement analysis →
stock-earnings-quality-revieworstock-balance-sheet-review - Business strategy details →
stock-business-review - Industry positioning →
stock-industry-review
Mandatory Gates
1) Execution Integrity Gate
You must read at least 2 of: latest proxy (DEF 14A), latest annual letter to shareholders, last 4 earnings call transcripts. If fewer than 2 available, return SKIPPED (insufficient management-disclosure data).
2) 5-Year-Window Gate
Capital allocation is a multi-year discipline. Look at 5 years of cash-flow allocation choices (buybacks, dividends, M&A, capex, debt). A single year is noise.
3) Insider-Activity Recency Gate
Insider transactions older than 12 months are weak signals. Pull the most recent 12 months of Form 4 filings.
4) Communication Bias Gate
Earnings call transcripts have an inherent positivity bias (CEOs sell). Look for absence of defense, willingness to name failures, and specific (not vague) forward statements.
Workflow
- Locate proxy, annual letter, recent earnings call transcripts.
- Build the 5-year capital-allocation table from cash flow statements.
- Sample 1–2 named acquisitions; estimate ROI (revenue contribution vs purchase price + integration cost).
- Build the 8–12 quarter guidance-vs-actuals scorecard.
- Read the most recent earnings call for tone; flag defensive patterns or vague guidance.
- Emit Findings.
Filing-Pattern-Gated Execution Protocol
Execution Order
- Identify filings: DEF 14A (comp + ownership), annual letter, transcripts.
- For each checklist item, locate the specific section/keyword.
- HIT → semantic + quantitative analysis.
- MISS → mark NOT FOUND.
- Report only confirmed Findings.
- Include
Filing pre-scan: X/Y items hit, Z confirmed.
Management Checklist (10 Items)
| ID | Item | Filing Section | Trigger |
| MGT-01 | 5-year capital-allocation pattern | Cash flow statements ×5 | Profile: where did cash go (buybacks / div / M&A / capex / debt). Flag if M&A-heavy + low ROI. |
| MGT-02 | Buyback timing quality | Share repurchase history vs price history | Flag if buybacks concentrated at price-peak quarters (poor timing) |
| MGT-03 | M&A ROI (sample 2–3 named deals) | 10-K M&A footnote + segment results | Flag if acquired-segment revenue growth < industry growth, or write-down occurred |
| MGT-04 | Guidance-vs-actuals (8–12 quarters) | Earnings releases + actuals | Flag if missed > 2 of last 8 quarters; flag if "raise-then-miss" pattern |
| MGT-05 | Frequency of guidance revisions (down) | Earnings releases | Flag if guidance lowered > 2× in trailing 4 quarters |
| MGT-06 | Comp structure: LTI alignment | DEF 14A "Executive Compensation" section | Flag if LTI tied to revenue-growth or non-GAAP earnings without TSR component |
| MGT-07 | Insider ownership level | DEF 14A "Security Ownership" table | Flag if CEO/CFO ownership < 0.1% AND founder no longer with company (low skin-in-the-game) |
| MGT-08 | Insider net buying/selling (12 months) | Form 4 filings | Flag if cluster of selling at price highs OR no buying despite low price |
| MGT-09 | Earnings call communication style | Last earnings call transcript | Flag defensive patterns: blames macro for misses; vague forward statements; refuses analyst pushback |
| MGT-10 | Strategic-thesis stability | Annual letters (3 years) | Flag if strategy pivots every year (no compounding) OR same strategy persists despite repeated failure (stubborn) |
Severity Rubric
- High: A Finding that should cap Bull-scenario probability. E.g., 3 consecutive guidance misses; M&A returns < 5%; insider selling cluster at highs.
- Medium: A Finding warranting watch. E.g., comp not tied to TSR; one missed guidance; modest founder dilution.
- Low: Context. E.g., capital allocation tilted to buybacks (informational unless timing is bad).
Evidence Rules
- Cite proxy section, earnings release date, or Form 4 filing.
- For capital allocation, show the 5-year table summarized.
- For guidance vs actuals, show the scorecard or quote specific quarters.
- Direct quotes from earnings calls capped at 60 words.
Output Format
Findings
[High|Medium|Low] Short Title
- ID:
MGT-NN - Citation: proxy section / earnings release date / transcript date
- Evidence: data series or direct quote
- Implication: what this means for long-horizon trust
Suppressed Items
Execution Status
Filings reviewed: DEF 14A (FY2024), Annual Letter (FY2024), Q3/Q4 FY24 + Q1/Q2 FY25 earnings transcripts
Filing pre-scan: 9/10 items hit, 3 confirmed as findings
Skipped items: MGT-07 (founder still major holder — alignment evident, no flag)Summary
One line: N High / M Medium / K Low — most material: <MGT-NN short title>.
Machine-Readable Findings Block (mandatory)
End the reply with exactly one fenced block tagged findings-json, carrying
Worker Findings Contract v1 (full schema and error codes:
stock-analysis-lead/references/worker-contract.md). The orchestrator synthesizes
the verdict from this block only — anything stated in the Markdown above but
omitted here does not reach the report. Everything above the fence is for the
human reader.
{
"contract_version": "1",
"worker": "stock-management-reviewer",
"prefix": "MGT",
"status": "OK",
"depth_mode": "<echo the dispatched depth>",
"archetype_applied": "<echo the dispatched archetype>",
"archetype_challenge": null,
"findings": [
{
"id": "MGT-NN",
"severity": "High|Medium|Low",
"title": "<= 80 chars",
"citation": {"source": "10-K", "locator": "<item/page/note>", "fiscal_period": "FY2025"},
"evidence": "direct quote <= 60 words, or a computed figure with its inputs",
"implication": "one sentence on what this means for the thesis",
"confidence": "first-hand|second-hand"
}
],
"positives": [],
"data_gaps": [],
"checklist_coverage": {"items_total": 10, "items_checked": 0, "items_not_found": 0, "ids_not_checked": []},
"mandatory_checks_run": []
}Contract rules that fail validation if broken:
statusis one ofOK/DEGRADED/SKIPPED/REFUSED; any value other thanOKrequires astatus_reason. The gate returnsSKIPPED (...)in prose and"status": "SKIPPED"here.- Every finding ID must start with
MGT— the prefix is the whole segment before the first hyphen. citationis an object, never a bare string;locatorandfiscal_periodmust be non-empty. A finding with no real citation is suppressed, not emitted.source: "aggregator"forcesconfidence: "second-hand"— this is what makes the first-hand data rule checkable rather than aspirational.checklist_coverage:items_checked + items_not_foundmust reachitems_total(10), so "the checklist ran to completion" is verifiable.archetype_challenge:nullwhen the dispatched archetype fits. When the evidence says it does not, file{"proposed", "reason", "evidence"}instead of silently analyzing against thresholds you believe are wrong — this is the only sanctioned way to disagree with the orchestrator's classification.mandatory_checks_run: list the archetype-specific check IDs the dispatch marked REQUIRED. Omitting one that was required fails validation.
Self-check before replying:
python3 <path-to>/stock-analysis-lead/scripts/finlib/worker_contract.py \
validate --reply <this-reply>.md --expect-worker stock-management-reviewerNo-Finding Case
No management-quality findings — track record clean, capital allocation thoughtful, communication direct.
Notable positives: Guidance beat 7/8 last quarters; CEO ownership 4%; buybacks well-timed (avg buyback 18% below current).Load References Selectively
references/capital-allocation-patterns.md— load when classifying capital allocation history or evaluating M&A track record; contains buyback-timing analysis methodology, M&A-ROI estimation framework, and worked examples (e.g., Apple's playbook vs AT&T's historical disasters).
Review Discipline
Management quality is the highest-impact / longest-horizon dimension. A great business with bad management compounds bad capital allocation; a mediocre business with great management often outperforms. Be selective with High severity — reserve it for clear pattern evidence over multiple years.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

