public-equity-research: Skill for Claude Code

.claude/skills/dashboard-generator/SKILL.md

dashboard-generator is a skill for Claude Code from lowtidebuild/public-equity-research. It costs 0 tokens per session (3,442 once invoked), scanned A, original, Apache-2.0.

A workflow step that turns an analysis-result.json file into an HTML dashboard for a stock analysis. It uses a predefined HTML layout and colour system, including charts and 11 sections.

In plain words
What is it for?
Use it after the analyst step when output mode C is selected, to create a dated HTML report for a stock ticker.
Why use it?
It removes the need to assemble the dashboard by hand after the analysis is complete. It also calculates an overall data-confidence grade from the metric grades.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: 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 →

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/dashboard-generator/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 dashboard-generator

README.md
[![agentmods](https://agentmods.dev/badge/skills/lowtidebuild/public-equity-research/dashboard-generator/github.svg)](https://agentmods.dev/skills/lowtidebuild/public-equity-research/dashboard-generator)
Your own site
<a href="https://agentmods.dev/skills/lowtidebuild/public-equity-research/dashboard-generator"><img src="https://agentmods.dev/badge/skills/lowtidebuild/public-equity-research/dashboard-generator/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 dashboard-generator

Your own site · 80×15
<a href="https://agentmods.dev/skills/lowtidebuild/public-equity-research/dashboard-generator"><img src="https://agentmods.dev/badge/skills/lowtidebuild/public-equity-research/dashboard-generator.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 3,442 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 $0.03442
Opus 5 $0.00000 $0.01721
Sonnet 5 $0.00000 $0.00688
Haiku 4.5 $0.00000 $0.00344

Measured 10d ago against content hash cbdde499cf79, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

dashboard-generator 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 10d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/render-dashboard.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/dashboard-generator/SKILL.md · 304 lines

How it starts

The opening of the file, as written. The whole thing — 304 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dashboard Generator — SKILL.md

Role: Step 8 — Generate the Mode C HTML dashboard from analysis-result.json. Triggered by: CLAUDE.md when output_mode = "C" after Step 7 (Analyst Agent completes analysis) Reads: run-local analysis-result.json, references/html-template.md, references/color-system.md Writes: output/reports/{ticker}_C_{lang}_{YYYY-MM-DD}.html References: html-template.md, color-system.md, docs/adr/0001-mode-c-rendering-strategy.ko.md


Instructions

Step 8.1 — Load Inputs

Load in this order:

  1. Read references/html-template.md — complete HTML skeleton with all 11 sections
  2. Read references/color-system.md — Tailwind CSS classes and Chart.js color configs
  3. Read run-local analysis-result.json — analysis output from Analyst Agent
  4. Verify all required sections are present in run-local analysis-result.json

Step 8.2 — Compute Data Confidence Indicator

From run-local analysis-result.json, count the data_quality_used grade distribution:

Grade A count: {N}
Grade B count: {N}
Grade C count: {N}
Grade D count: {N}

Overall:
- All critical metrics (price, revenue, net_income) Grade A → Overall A
- ≥6 of 10 key metrics Grade A or B → Overall B
- ≥4 of 10 key metrics Grade A, B, or C → Overall C
- Otherwise → Overall D (add warning banner)

Translate to Data Confidence Indicator text:

  • Grade A: Data Confidence: A — All key metrics independently verified
  • Grade B: Data Confidence: B — {N} of 10 key metrics cross-referenced
  • Grade C: Data Confidence: C — Limited source verification. Review with caution.
  • Grade D: Data Confidence: D — ⚠️ Insufficient verified data

Step 8.3 — Section-by-Section Population

Populate each section of html-template.md with data from analysis-result.json.

JSON field → HTML placeholder mapping:

analysis-result.json field HTML Section Placeholder
ticker Section 1 {TICKER}
company_name Section 1 {COMPANY_NAME}
exchange Section 1 {EXCHANGE}
price_at_analysis Section 1, 3 {CURRENT_PRICE}
price_day_change Section 1 {DAY_CHANGE}
price_day_change_pct Section 1 {DAY_CHANGE_PCT}
data_mode Section 1 badge class
analysis_date Section 1 {ANALYSIS_DATE}
key_metrics.market_cap Section 3 {MARKET_CAP}
key_metrics.pe_ratio Section 3 {PE_RATIO}
key_metrics.ev_ebitda Section 3 {EV_EBITDA}
key_metrics.fcf_yield Section 3 {FCF_YIELD}
key_metrics.revenue_growth_yoy Section 3 {REV_GROWTH}
key_metrics.operating_margin Section 3 {OP_MARGIN}
scenarios.bull.* Section 2 bull card values
scenarios.base.* Section 2 base card values
scenarios.bear.* Section 2 bear card values
rr_score Section 2 R/R badge
verdict Section 2 verdict badge
sections.variant_view_q1 Section 4 Q1 text
sections.variant_view_q2 Section 4 Q2 text
sections.variant_view_q3 Section 4 Q3 text
sections.precision_risks Section 4 risk table rows
sections.valuation_metrics Section 5 valuation table
sections.sotp Section 5 SOTP section
sections.dcf_analysis Section 5 DCF subsection (after SOTP)
valuation_bridge (top-level) Section 5b {VALUATION_BRIDGE_SECTION} (4 anchors + weighted fair value + reconciliation paragraph)
sections.macro_context Section 4/6 Macro Environment section
sections.peer_comparison Section 6 peer table rows
output/runs/{run_id}/peers/*.json minimum collection_timestamp Section 6 {PEER_COLLECTED_AT_MIN}
output/runs/{run_id}/peers/*.json maximum collection_timestamp Section 6 {PEER_COLLECTED_AT_MAX}
sections.analyst_coverage Section 7 analyst data
historical_prices Section 8 Chart 1 data array
income_statements Section 8, 9 Charts 2/3, quarterly table
sections.qoe_summary Section 9 QoE section
sections.portfolio_strategy Section 10 strategy text
sections.what_would_make_me_wrong Section 10 WWMMW list
upcoming_catalysts Section 10 catalyst table

Read the full file on GitHub · 304 lines

Files

What ships with it

3 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. 10d ago First seen · 304 lines · 0 tokens per session scan A cbdde499cf79

Subscribe to this mod's changes

dashboard-generator is a skill published in the GitHub repository lowtidebuild/public-equity-research (46 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 3,442 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.