agentleFS
johnqtcgjohnqtcg/awesome-skills/skills/stock-industry-review/SKILL.md

stock-industry-review

Skill30 starsChanged 4 months agoMITView on GitHub

Review a US-listed company's industry position and competitive moat for an equity-research workup. Covers Porter Five Forces scan, market-share trend (absolute and relative to industry growth), TAM size and trajectory, unit economics where disclosed (LTV/CAC, unit gross margin), moat classification (network / brand / scale-cost / switching-cost / patent / regulatory / proprietary-data), substitute threats, new-entrant threats, pricing-power evidence, supplier/channel concentration risk, and regulatory exposure. Trigger when analyzing competitive position at L6 of the seven-layer X-ray framework. Dispatched by stock-analysis-lead; at Lite depth runs in Lite-Industry mode (moat type + share trend only, no full Porter scan).

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read 10-K Item 1 "Competition" section AND at least one external source (analyst report, industry association, or comparable peer's 10-K) …

    line 27
  2. Distinctive:

    Read 10-K "Competition" subsection + Risk Factors related to competition.

    line 40
  3. Very specific:

    Do NOT assign P(success) or a dollar value — that is the orchestrator's synthesis.

    line 119
  4. Very specific:

    Every finding ID must start with IND — the prefix is the whole segment before the first hyphen.

    line 166

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Stock Industry Review

Purpose

Read 10-K "Competition" sections, MD&A market commentary, and external industry-size data with the eye of a strategy analyst. The financial statements tell you what the company did; this skill tells you what the industry will let it keep doing. Surface moat type and durability, market-share trajectory relative to industry, pricing power evidence, and structural threats. Output Findings that the orchestrator uses to model Bull/Base/Bear scenarios — moat strength caps the multiple expansion, and competitive pressure determines margin sustainability.

When To Use

  • Orchestrator dispatches industry review — a Tier-0 core worker, always-on at all depths; Lite runs the lighter moat-type + share-trend pass only, no full Porter scan. See stock-analysis-lead/references/dispatch-protocol.md Part 1.
  • User asks "what's the moat", "is <ticker> losing share", "who are the competitors", "what's the TAM".

When NOT To Use

  • Business model classification → stock-business-review
  • Margin trends → stock-earnings-quality-review
  • Management quality → stock-management-review

Mandatory Gates

1) Execution Integrity Gate

Read 10-K Item 1 "Competition" section AND at least one external source (analyst report, industry association, or comparable peer's 10-K) for triangulation. The company's own description of competition is self-serving.

2) Quantification Gate

"Strong competitive position" is not a Finding. Quantify: market share %, share trend, TAM $, growth rate. If you cannot quantify, suppress.

3) Moat-Type Gate

Generic "competitive advantages" is not a moat. Classify into one of seven types: network effects, brand, scale-cost advantage, switching cost, patent/IP, regulatory, proprietary data. If you cannot fit it into a named type, flag "no identifiable moat".

4) Cyclicality Gate

Pricing-power evidence in a bull market is not pricing power. Look for margin stability across a downturn (2020 or 2022 depending on sector).

Workflow

  1. Read 10-K "Competition" subsection + Risk Factors related to competition.
  2. Pull at least one peer 10-K for triangulation (peer list from manifest).
  3. Estimate market-share trend using revenue YoY vs industry growth (from external source).
  4. Classify moat into named type(s); test moat durability.
  5. Emit Findings.

Filing-Pattern-Gated Execution Protocol

Execution Order

  1. Locate the 10-K Competition section, Risk Factors, segment-level revenue, and peer 10-K for context.
  2. For each checklist item, locate evidence.
  3. HIT → quantify + classify.
  4. MISS → mark NOT FOUND.
  5. Report only Findings with named, quantified evidence.
  6. Include Filing pre-scan: X/Y items hit, Z confirmed.

Industry Checklist (10 Items)

IDItemSourceTrigger
IND-01Porter Five Forces quick scan10-K Competition + Risk FactorsFlag if any one force is "high" without compensating moat
IND-02Market-share trend (relative growth)Company revenue YoY vs industry growthFlag if company growth < industry growth (losing share)
IND-03TAM size + 5-year growth trajectoryInvestor presentation / industry researchFlag if TAM growth < 5% (mature market — multiple compression risk)
IND-04Unit economics (LTV/CAC, unit GM)Investor presentations + 10-K segmentFlag if LTV/CAC < 3 in subscription business
IND-05Moat classification (named type)Multi-source synthesisFlag "no clear moat" if no named type applies
IND-06Substitute threat (named adjacent products)10-K Risk Factors + external scanFlag if substitute growing > 20% annually
IND-07New-entrant threat (capital + regulatory barriers)10-K Risk FactorsFlag if barriers low AND TAM attractive
IND-08Pricing-power evidence (cross-cycle margin stability)5-year gross margin through last downturnFlag if gross margin compressed > 5pp in last downturn
IND-09Supplier/channel concentration risk10-K Risk FactorsFlag if > 30% of supply from single vendor (e.g., TSMC dependency)
IND-10Regulatory exposure (sector-specific)10-K Item 1 "Regulation" + Risk FactorsFlag if pending regulation could compress margin or restrict TAM

Severity Rubric

  • High: Threatens the long-term thesis. E.g., losing share for 3 consecutive years; no identifiable moat in a competitive market; key regulatory action pending.
  • Medium: Caps Bull-scenario probability. E.g., moat is real but narrow (switching cost ~6 months only); supplier concentration material but second-sourcing in progress.
  • Low: Context for valuation. E.g., TAM growing 8% (not great, not terrible); regulatory exposure passive.

Evidence Rules

  • Market share must cite a number AND the source (whose definition of the market?).
  • Moat classification must name the type explicitly; don't write "they have a strong moat".
  • TAM citations must include the source (research firm + year) since TAM estimates vary widely.
  • Pricing power must reference a specific downturn period.

Output Format

Findings

[High|Medium|Low] Short Title

  • ID: IND-NN
  • Citation: 10-K section + peer or external source
  • Evidence: quantified data + named moat type
  • Implication: what this means for the multiple / margin sustainability

Suppressed Items

Execution Status

Filings reviewed: 10-K (FY2024) Item 1 + Item 1A, peer 10-K (<peer ticker>)
External sources: <industry research firm / analyst report>
Filing pre-scan: 10/10 items hit, 4 confirmed as findings

Venture Priors (option-dominated names only — when the orchestrator's dispatch says Optionality Overlay)

When the company is option-dominated (Tesla, pre-profit narrative names), the orchestrator values the unproven engines with a sum-of-the-parts whose option legs need priors you are best placed to supply. For each value-driving venture (e.g. robotaxi, humanoid robots, an AI/software stream), emit a structured prior — and express every uncertain field as a range with a source tag, never a point (a point would be false precision the orchestrator's SOTP engine rejects):

Venture: <name>
- TAM at maturity: $<low>–$<high>B (<target year>) — source: <research firm + year> [estimate]
- Company addressable share: <low>–<high>% — basis: <vs named competitor / structural argument> [estimate]
- Take-rate / revenue capture: <low>–<high>% [assumption — state the network/pricing logic]
- Plausible steady-state operating margin: <%> — analog: <named comparable business> [assumption]
- Independent of the company's other ventures? <yes/no — shared tech stack?>  ← feeds the venture probability tree

Do NOT assign P(success) or a dollar value — that is the orchestrator's synthesis. Your job is the falsifiable, sourced, ranged inputs. If you cannot source even a range for a field, say so; a missing prior is better than a fabricated one.

Summary

One line: N High / M Medium / K Low — most material: <IND-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-industry-reviewer",
  "prefix": "IND",
  "status": "OK",
  "depth_mode": "<echo the dispatched depth>",
  "archetype_applied": "<echo the dispatched archetype>",
  "archetype_challenge": null,
  "findings": [
    {
      "id": "IND-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:

  • status is one of OK / DEGRADED / SKIPPED / REFUSED; any value other than OK requires a status_reason. The gate returns SKIPPED (...) in prose and "status": "SKIPPED" here.
  • Every finding ID must start with IND — the prefix is the whole segment before the first hyphen.
  • citation is an object, never a bare string; locator and fiscal_period must be non-empty. A finding with no real citation is suppressed, not emitted.
  • source: "aggregator" forces confidence: "second-hand" — this is what makes the first-hand data rule checkable rather than aspirational.
  • checklist_coverage: items_checked + items_not_found must reach items_total (10), so "the checklist ran to completion" is verifiable.
  • archetype_challenge: null when 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-industry-reviewer

No-Finding Case

No industry-position findings — moat real and named, gaining share, pricing power demonstrated through last cycle.
Notable positives: Network-effect moat; share grew from 24% to 31% in 5 years.

Load References Selectively

  • references/moat-typology.md — load when classifying moat type or stress-testing moat durability; contains the 7-type taxonomy with named exemplars (Visa network, Costco scale, SAP switching, etc.), and the cyclicality test for pricing power.

Review Discipline

Industry analysis is where retail investors most often hand-wave ("they have AI, they'll win"). Discipline: name the moat type. Quantify the share trend. Cite the TAM source. If you can't, suppress — orchestrator handles a missing IND finding better than a hand-wavy one.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.