public-equity-research: Skill for Claude Code

.claude/skills/data-validator/SKILL.md

data-validator is a skill for Claude Code from lowtidebuild/public-equity-research. It costs 0 tokens per session (4,600 once invoked), scanned A, original, Apache-2.0.

A validation workflow step that fact-checks collected stock data in three layers, assigns confidence grades, and builds an evidence pack for the analyst.

In plain words
What is it for?
Use it after web research to validate raw data, record exclusions, create validated-data.json and evidence-pack.json, and measure the analyst’s context budget.
Why use it?
It prevents unverified figures from entering the analysis: data below the required confidence level is left blank rather than estimated or guessed.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; mentions CLAUDE.md.

This is lowtidebuild/public-equity-research's own configuration. It tells Claude Code how to work on public-equity-research itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything public-equity-research configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python tools/evidence_pack.py \.

Reuse

Borrowing it

Nothing to install: this file belongs to lowtidebuild/public-equity-research. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/lowtidebuild/public-equity-research/main/.claude/skills/data-validator/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/lowtidebuild/public-equity-research

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for data-validator

README.md
[![agentmods](https://agentmods.dev/badge/skills/lowtidebuild/public-equity-research/data-validator/github.svg)](https://agentmods.dev/skills/lowtidebuild/public-equity-research/data-validator)
Your own site
<a href="https://agentmods.dev/skills/lowtidebuild/public-equity-research/data-validator"><img src="https://agentmods.dev/badge/skills/lowtidebuild/public-equity-research/data-validator/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for data-validator

Your own site · 80×15
<a href="https://agentmods.dev/skills/lowtidebuild/public-equity-research/data-validator"><img src="https://agentmods.dev/badge/skills/lowtidebuild/public-equity-research/data-validator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,600 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.04600
Opus 5.5 $0.00000 $0.01840
Sonnet 5.5 $0.00000 $0.00920
Haiku 4.5 $0.00000 $0.00460

Measured 1mo ago against content hash 6deaf6a01e70, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

data-validator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/normalize-metadata.py, scripts/ratio-calculator.py, scripts/validate-artifacts.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/data-validator/SKILL.md · 448 lines

How it starts

The opening of the file, as written. The whole thing — 448 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Data Validator — SKILL.md

Role: Step 5 — Validate all collected data through 3-layer fact-checking, assign confidence grades, build the evidence pack, measure Analyst context budget, and enforce the Blank-Over-Wrong principle. Triggered by: CLAUDE.md after Step 4 (web researcher) Reads: output/runs/{run_id}/{ticker}/tier1-raw.json (Enhanced), output/runs/{run_id}/{ticker}/tier2-raw.json, references/validation-rules.md, references/confidence-grading.md, references/source-metadata-contract.md Writes: output/runs/{run_id}/{ticker}/validated-data.json, output/runs/{run_id}/{ticker}/evidence-pack.json, output/runs/{run_id}/{ticker}/context-budget.json References: validation-rules.md, confidence-grading.md, source-metadata-contract.md


THE BLANK-OVER-WRONG PRINCIPLE

빈칸 > 틀린 숫자 (An empty cell is better than a wrong number)

If a data point cannot be verified to Grade C or above, it is:

  1. Set to null in validated output
  2. Listed in exclusions with reason
  3. Displayed as "—" in all output modes
  4. NEVER filled with an estimate, approximation, or best guess

This principle is ABSOLUTE. No exceptions. Grade D = excluded.


Instructions

Step 5.1 — Load Data Sources

Enhanced Mode:

Load: output/runs/{run_id}/{ticker}/tier1-raw.json    (API data)
Load: output/runs/{run_id}/{ticker}/tier2-raw.json    (web data)
Primary source: tier1 (API)
Cross-check source: tier2 (web)

Standard Mode (US stocks):

Load: output/runs/{run_id}/{ticker}/tier2-raw.json    (web data only)
Primary source: tier2 extracted_metric_candidates
Cross-check source: tier2 extracted_metric_candidates from independent source_domain values

Korean stocks:

Load: output/runs/{run_id}/{ticker}/dart-api-raw.json    (DART OpenAPI — Grade A financials, always attempted)
Load: output/runs/{run_id}/{ticker}/tier2-raw.json       (web — price from 네이버금융, consensus, qualitative)
Primary financial source: run-local dart-api-raw.json (if exists)
Primary market data source: tier2 (네이버금융)
Fallback: if dart-api-raw.json missing → tier2-raw.json only (aggregator-only, max Grade B)

Read the full file on GitHub · 448 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 1mo ago First seen · 448 lines · 0 tokens per session scan A 6deaf6a01e70

Subscribe to this mod's changes

data-validator is a skill published in the GitHub repository lowtidebuild/public-equity-research (47 stars, last pushed 3mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 4,600 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

tradingagents-analysis

A multi-agent analysis tool for stocks listed on China's Shanghai and Shenzhen exchanges, known as A-shares. It combines technical, company, market-sentiment, money-flow, economic, and game-theory analysis into a structured trading view.

KylinMountain/TradingAgents-AShare · 138 tokens

interactive-dashboard

Interactive web dashboards: stock trackers, sector heatmaps, portfolio monitors, served via preview URL.

ginlix-ai/LangAlpha · 21 tokens

dcf-model

Build a DCF valuation in Excel: FCF projections, WACC, terminal value, scenarios, sensitivity grids, reverse DCF. Triggers on build a DCF, what is it worth, intrinsic value, fair value, price target from cash flows.

ginlix-ai/LangAlpha · 56 tokens

comps-analysis

Comparable company analysis: peer set, operating metrics, valuation multiples, statistics and an implied value. Triggers on comps, trading comparables, how does it trade against peers, peer benchmarking, what multiple should it get.

ginlix-ai/LangAlpha · 48 tokens

company-profile

One-page company profile slide, four quadrants of overview, financial summary, share price chart and key facts. Also the compact profile paragraph when it has to sit inside a memo, a deck or a chat reply. Triggers on one-page profile, tear sheet, company snapshot, profile slide, quick profile of [company].

ginlix-ai/LangAlpha · 68 tokens

html-report

Self-contained styled HTML reports written to the task directory: PDF-exportable research documents with inline data, charts, and theme-aware CSS.

ginlix-ai/LangAlpha · 29 tokens