AI Skills Catalog
Skills pack Tools

Stock Analysis

Prepare filing-based company research with sector-aware ratios, peer comparisons, valuation scenarios, and an auditable report and scorecard.
SKILL SCORE79How it is scored
VerifiedFreeMIT

Works with

Packaged from the source skill for Claude, Codex and 4 more.

About this skill

Stock Analysis is Alireza Rezvani's workflow for preparing documented fundamental research on a company. It combines primary filings, sector-specific analysis, peer comparisons, financial calculations, and explicit uncertainty. The standard deliverables are a Markdown research report and a weighted scorecard showing the underlying inputs.

The package includes reference guides, sector playbooks, illustrative reports, benchmark configuration, and Python tools for intake checks, ratios, scoring, valuation calculations, and report checks. It offers short screening, standard, deeper research, forensic accounting, and pre-listing IPO modes.

Use this skill when

  • You need a structured company-research report grounded in annual reports, quarterly filings, and supporting disclosures.
  • You want to compare a business with appropriate peers and its own history instead of ranking it on a single ratio.
  • Your question concerns the reliability of reported earnings or the disclosures in an IPO prospectus and needs a different workflow from a conventional listed-company review.

Start with the company and security identity, exchange, reporting currency, accounting basis, analysis date, and desired depth. Supply or obtain primary filings, recent results, ownership disclosures, call transcripts, and relevant sector data. Financial inputs need source and period labels; missing documents and unverifiable figures are explicit gaps.

What it can do

  • Check reporting basis, units, periods, provenance, and whether newer releases or material events supersede the gathered data.
  • Route research through the relevant sector and company-situation guides, suppressing generic ratios that do not apply.
  • Examine earnings quality, cash conversion, capital returns, debt, governance, and non-financial disclosures alongside the financial statements.
  • Build a stated peer set and compare key measures with both peers and the company's historical record.
  • Calculate ratios and scenario-based valuation outputs from supplied assumptions, including enterprise-value bridges and reverse-DCF questions.
  • Present weighted scores with benchmark assumptions and disqualifying findings, then document the bear case, uncertainty, and evidence that would invalidate the thesis.

The tools depend on correctly sourced inputs and a usable Python environment; they do not obtain filings or make unsupported numbers reliable. Default benchmark bands are editable starting points, not universal standards. The report linter checks structure and nearby sourcing cues heuristically, so passing it does not establish factual accuracy. Scores are research summaries, not predicted returns or personalized trading instructions. Fictional worked examples demonstrate format and must not supply figures for a real company.

Typical workflows

Choose the research mode, resolve the security identity, and gather the official record before computing ratios. Validate the intake, classify the sector, examine accounting and governance concerns, then develop the business analysis, peer comparison, and valuation scenarios. Standard and deeper reviews also consider the narrative and notes surrounding the statements.

Assemble a report with recency and data-quality disclosures, visible assumptions, risks, and supporting calculations. A challenge pass tests the claims carrying the conclusion; a final report check flags omissions for correction. If the core issue is accounting reliability, use the forensic route; for a company that has not begun trading, use the prospectus-based IPO route and its different information limits.

What is inside the skill

Section headings from the original SKILL.md (about 4,731 words of instructions). Read the full text in the source repository before installing.

  1. The principle that governs everything here
  2. Non-negotiables
  3. Never invent a number
  4. Official records are the source — and they hold far more than the financial statements
  5. Analysis, not advice
  6. Show the reasoning and the uncertainty
  7. Choose a depth mode
  8. The workflow
  9. Stage 0 — Establish identity
  10. Stage 1 — Acquire data
  11. Stage 2 — Classify sector and situation
  12. Stage 3 — Kill-criteria and red-flag screen
  13. Stage 4 — Core analysis
  14. Stage 5 — Build the peer set and benchmark
  15. Stage 6 — Value it
  16. Stage 7 — Risk, bear case, invalidation
  17. Stage 8 — Score and write
  18. Stage 9 — Challenge the draft before delivering it
  19. Stage 10 — Lint before delivering
  20. Sector router
  21. Bundled scripts
  22. Output contract
  23. Reference index
  24. Anti-Patterns

Bundled files

  • evals/evals.json
  • examples/README.md
  • examples/forensic-analysis-example.md
  • examples/standard-analysis-example.md
  • references/01-data-sourcing.md
  • references/02-core-factors.md
  • references/03-earnings-quality.md
  • references/04-balance-sheet-and-cashflow.md
  • references/05-returns-and-dupont.md
  • references/06-valuation.md
  • references/07-forensic-red-flags.md
  • references/08-governance.md
  • references/09-risk-and-macro.md
  • references/10-peer-set.md
  • references/11-scoring-rubric.md
  • references/12-report-template.md
  • references/13-situations.md
  • references/14-accounting-comparability.md
  • references/15-document-diligence.md
  • references/16-market-mechanics-and-tax.md
  • references/17-process-and-epistemics.md
  • references/18-forensic-mode.md
  • references/19-ipo-mode.md
  • references/20-challenge-pass.md
  • references/21-data-integrity-tools.md
  • references/sectors/_index.md
  • references/sectors/auto.md
  • references/sectors/aviation-hotels.md
  • references/sectors/banks.md
  • references/sectors/biotech-clinical.md
  • references/sectors/chemicals-cement.md
  • references/sectors/exchanges-payments.md
  • references/sectors/fmcg-consumer.md
  • references/sectors/holdco-assetmgr.md
  • references/sectors/infra-capitalgoods.md
  • references/sectors/insurance-brokers-services.md
  • references/sectors/insurance.md
  • references/sectors/it-saas.md
  • references/sectors/metals-mining.md
  • references/sectors/mortgage-reit-specialty-finance.md

Example prompts

  • Prepare a Standard-mode report for the listed company identified in the attached filings. Establish reporting basis, units, and recency first, then build an appropriate peer set and a scorecard with visible weights and data gaps.
  • Use Forensic mode on these annual reports and cash-flow schedules. Investigate the profit-to-cash gap and related-party disclosures, distinguish anomalies from supported findings, and list the evidence needed to resolve them.
  • Review this pre-listing prospectus using IPO mode. Identify the offer structure, compare the stated assumptions with suitable listed peers, and document missing disclosures and scenario sensitivities without giving subscription advice.

How to install Stock Analysis

Claude Packaged
  1. Download the Claude package from the skill page. The ZIP contains one folder named after the skill, with SKILL.md and any bundled reference files.
  2. For Claude Code, unpack the folder into ~/.claude/skills/ to use it in every project, or into .claude/skills/ inside a repository to share it with your team.
  3. For Claude apps, upload the ZIP in the Skills section of the capabilities settings.
  4. Start a new session and describe the task in your own words. Claude picks the skill when the request matches its description.
More about skills for Claude
Codex Packaged
  1. Download the Codex package. The ZIP contains one folder named after the skill, with SKILL.md and bundled resources.
  2. Unpack the complete folder into .agents/skills/ inside your repository, or into ~/.agents/skills/ for personal use. Preserve its relative reference-file paths.
  3. Start a new Codex session and invoke the skill by name or with $skill-name, or describe a matching task.
  4. AGENTS.md is separate project guidance. The ZIP does not generate or modify that file.
More about skills for Codex
GPT Packaged
  1. Download the GPT package from the skill page.
  2. Create or edit a custom GPT (or a ChatGPT project) and paste the contents of SKILL.md into the instructions field.
  3. Upload the bundled reference files as knowledge so the GPT can consult them.
  4. Test with one of the example prompts from the skill page and adjust the instructions if your use case differs.
More about skills for GPT
Gemini Packaged
  1. Download the Gemini package from the skill page.
  2. For a project, unpack the complete folder into .gemini/skills/ or .agents/skills/. For personal use, use ~/.gemini/skills/ or ~/.agents/skills/.
  3. Run /skills reload in Gemini CLI, then /skills list to check discovery. There is no need to paste the skill into GEMINI.md.
  4. Test a matching task and verify the referenced tools and files are available.
More about skills for Gemini
Cursor Packaged
  1. Download the Cursor package from the skill page.
  2. Unpack the complete skill folder into .cursor/skills/ or .agents/skills/ in your project. For personal local use, ~/.cursor/skills/ and ~/.agents/skills/ are also supported.
  3. Start a new Cursor session. Type / in Agent chat and select the skill name, or describe a matching task.
  4. Commit the skill folder and resources for team use. Personal local skills are not automatically available to remote agents or automation runs.
More about skills for Cursor
OpenCode Packaged
  1. Download the OpenCode package from the skill page.
  2. Unpack the complete folder into .opencode/skills/ in your project, or ~/.config/opencode/skills/ for personal use. OpenCode also supports .agents/skills/ and .claude/skills/ compatibility locations.
  3. Keep supporting files at their original relative paths. AGENTS.md is separate project-wide guidance and is not generated by this ZIP.
  4. Start OpenCode in the project and test a matching task with the model and permissions you use.
More about skills for OpenCode

Permissions & security

Low risk

Inspect the source, license and declared permissions before use. Read the scripts before running them. Review method

Read project files
Write generated skill files

Stock Analysis FAQ

What does the Stock Analysis skill do?

Prepare filing-based company research with sector-aware ratios, peer comparisons, valuation scenarios, and an auditable report and scorecard.

Which AI agents can use Stock Analysis?

Packages for Claude, Codex and 4 more are built from the same source instructions.

How do I install Stock Analysis in Claude?

Download the Claude package from the skill page. The ZIP contains one folder named after the skill, with SKILL.md and any bundled reference files. For Claude Code, unpack the folder into ~/.claude/skills/ to use it in every project, or into .claude/skills/ inside a repository to share it with your team.

Who made Stock Analysis and what is the license?

Stock Analysis is published by Alireza Rezvani under the MIT license. The source is https://github.com/alirezarezvani/claude-skills/tree/main/finance/skills/stock-analysis. The catalog keeps the original attribution.

What permissions does Stock Analysis need?

Declared permissions: read project files, write generated skill files. Risk level: low. Check the scripts in the source before running them.

Stock Analysis Skill — Alireza Rezvani | AI Skills Catalog