Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Ruinius/financial-analyst-skills --skill qualitative_assessmentgit clone --depth 1 https://github.com/Ruinius/financial-analyst-skillsWrote 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.
[](https://agentmods.dev/skills/ruinius/financial-analyst-skills/qualitative_assessment)<a href="https://agentmods.dev/skills/ruinius/financial-analyst-skills/qualitative_assessment"><img src="https://agentmods.dev/badge/skills/ruinius/financial-analyst-skills/qualitative_assessment/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.
<a href="https://agentmods.dev/skills/ruinius/financial-analyst-skills/qualitative_assessment"><img src="https://agentmods.dev/badge/skills/ruinius/financial-analyst-skills/qualitative_assessment.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00047 | $0.02121 |
| Opus 5 | $0.00023 | $0.01060 |
| Sonnet 5 | $0.00009 | $0.00424 |
| Haiku 4.5 | $0.00005 | $0.00212 |
Grade A, and why
Qualitative Assessment 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 11d ago.
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.
How it starts
The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Qualitative Assessment Skill
Purpose
This skill reads qualitative source documents (analyst reports, earnings call transcripts, press articles) and produces a structured assessment of three dimensions that directly feed into the DCF model assumptions:
- Economic Moat — determines terminal growth rate and margin sustainability
- EBITA Margin Outlook — adjusts Stage 2 margin assumptions (+/- pp)
- Organic Growth Outlook — adjusts Stage 2 growth assumptions (+/- pp)
Without this skill, the Financial Modeling skill falls back to pure historical trend continuation, which misses forward-looking information.
Prerequisites
- The document must already be classified (Skill 1) — ticker, company name, and document type known
- The company's
output_data/TICKER/directory must already exist (i.e., at least one financial report has been processed) TICKER_metadata.mdshould exist with a Financial History table for context
Inputs
- Classified document in
processing_data/(analyst report, transcript, or article) output_data/TICKER/TICKER_metadata.md— for existing assessments to compare/harmonize
Outputs
- Updated
TICKER_metadata.mdwith Qualitative Assessment section (new or harmonized with existing)
Step-by-Step Instructions
Step 1: Read the Source Document
Read the classified document from processing_data/. Identify:
- Source type: Analyst report, earnings transcript, press article, etc.
- Source date: Publication or earnings call date
- Author/firm: e.g., "Morningstar (Dan Romanoff, CPA)"
Also read the company's TICKER_metadata.md to check for any existing Qualitative Assessment.
Step 2: Assess Economic Moat
Determine the company's economic moat rating: Wide, Narrow, or None.
| Rating | Definition | Terminal Growth Implication |
|---|---|---|
| Wide | Structural advantages expected to sustain excess ROIC for 20+ years. Dominant network effects, high switching costs, or irreplaceable intangible assets. | Terminal growth = 4.0% |
| Narrow | Clear competitive advantage, but likely to face erosion within 10-20 years. Currently outperforming cost of capital but not deep enough for long-term protection. | Terminal growth = 3.0% |
| None | Highly commoditized or intensely competitive. No sustainable advantage. Short-term excess profits are quickly competed away. | Terminal growth = 2.5% |
What ships with it
2 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.
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.
- 11d ago First seen · 208 lines · 47 tokens per session scan A 937b14a794cd
Qualitative Assessment is a skill published in the GitHub repository Ruinius/financial-analyst-skills (5 stars, last pushed 3mo ago), licensed MIT. It adds 47 tokens to every session and 2,121 once invoked, about $0.0002 per session on Opus 5. 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 2026-08-31.
Other skills, from other repositories
xiaohongshu-finance
A writing and chart-making guide for creating finance and investing posts for Xiaohongshu, a Chinese social platform. It covers topics such as stocks, funds, property, gold, crypto, and economic data.
openclaw-cost-auditor
Parse logs, query API metrics, forecast bills, optimize spend with reports & alerts.
scenario-analysis
A financial planning method that compares baseline, optimistic, and pessimistic assumptions to estimate their effects on returns, cash flow, or valuation.
payment-scheduling-cm
A payment-scheduling process orders approved payments according to due dates, urgency and available cash.
cost-center-performance
A cost-centre performance review compares each department’s budget and actual costs with its output, efficiency, capacity use and quality.
expense-ratio-analysis
A process for comparing sales, administrative, and research-and-development spending with revenue, budgets, targets, and earlier periods. It breaks down spending by type and department.