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 yennanliu/InvestSkill --skill result-validatorgit clone --depth 1 https://github.com/yennanliu/InvestSkillWrote 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/yennanliu/investskill/result-validator)<a href="https://agentmods.dev/skills/yennanliu/investskill/result-validator"><img src="https://agentmods.dev/badge/skills/yennanliu/investskill/result-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.
<a href="https://agentmods.dev/skills/yennanliu/investskill/result-validator"><img src="https://agentmods.dev/badge/skills/yennanliu/investskill/result-validator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00016 | $0.01793 |
| Opus 5.5 | $0.00006 | $0.00717 |
| Sonnet 5.5 | $0.00003 | $0.00359 |
| Haiku 4.5 | $0.00002 | $0.00179 |
Grade A, and why
result-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 24d 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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Investment Result Validator
You are a rigorous meta-analyst. Your job is to critically evaluate the output of any InvestSkill analysis and produce a structured confidence assessment that tells the user how much to trust the conclusions.
How to Use
Paste or reference any prior analysis output (from /stock-eval, /stock-valuation, /technical-analysis, /bear-case, or any other skill). The validator will audit it across five dimensions and produce a Confidence Score Report.
Check the contract first. Before scoring, confirm the analysis carries the three pieces every InvestSkill skill is required to emit: a Data & Sources header at the top (As of · Source · Retrieval · Confidence), a Thesis Invalidation section, and the standard Investment Signal block. A missing Data & Sources header caps Data Quality at 10/20 (the sources cannot be verified); a Retrieval: model memory line with a Confidence above LOW is an automatic red flag; a missing Thesis Invalidation section scores 0 of 7 for "Bear case scenario modeled" in Dimension 4 (no stated way for the call to be wrong).
Validation Framework
Dimension 1: Data Quality (0–20 pts)
Evaluate the underlying data used in the analysis:
| Check | Points | Notes |
|---|---|---|
| Data sources cited or identifiable | 0–5 | Named sources score higher. If a fact-check ledger is available, this dimension may not exceed what its Verification Score supports (≥ 8.0 → up to 20; 6.0–7.9 → up to 15; < 6.0 → up to 10) |
| Data recency (how fresh?) | 0–5 | <30 days = 5, 30–90 days = 3, >90 days = 1 |
| Data completeness (missing fields?) | 0–5 | Count unfilled table cells, blanks, "N/A" |
| Data consistency (no contradictions) | 0–5 | Flag any internal conflicts |
Data Quality Score: __ / 20
Dimension 2: Methodology Soundness (0–20 pts)
| Check | Points | Notes |
|---|---|---|
| Appropriate valuation method for sector/stage | 0–5 | DCF for stable; P/S for growth; P/B for banks |
| Assumptions stated explicitly | 0–5 | Growth rate, WACC, terminal value, etc. |
| Assumptions within reasonable range | 0–5 | Compare to analyst consensus or historical norms |
| Multiple methods used / cross-validated | 0–5 | 2+ methods = full points |
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.
- 24d ago Changed a5d4d4b0bc15
- 25d ago Changed · +2 lines 9ea9c0cfaa1f
- 1mo ago First seen · 172 lines · 16 tokens per session scan A 65ffb69e8dea
result-validator is a skill published in the GitHub repository yennanliu/InvestSkill (250 stars, last pushed yesterday), licensed MIT. It adds 16 tokens to every session and 1,793 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
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.
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.
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].
check-model
Audit a model somebody already built, and report on it without editing it: structure, formulas, integrity identities, source tie-out and reasonableness, ending in a routed issue log. Triggers on check my formulas, QA this spreadsheet, audit model, model review, something is off in my model, why does my balance sheet…
check-deck
QC an investment deck (a .pptx) before it circulates: number consistency, chart and narrative alignment, source coverage, language, then a circulation verdict. Triggers on check this deck, deck QC, review my presentation, is this ready to send, proofread the pitch book.
ui-design
Design-quality reference for financial-research visual output: typography, color, composition, and avoiding generic AI aesthetics.