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 skindhu/skind-skills --skill us-stock-researchergit clone --depth 1 https://github.com/skindhu/skind-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/skindhu/skind-skills/us-stock-researcher)<a href="https://agentmods.dev/skills/skindhu/skind-skills/us-stock-researcher"><img src="https://agentmods.dev/badge/skills/skindhu/skind-skills/us-stock-researcher/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/skindhu/skind-skills/us-stock-researcher"><img src="https://agentmods.dev/badge/skills/skindhu/skind-skills/us-stock-researcher.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 | $0.00045 | $0.01773 |
| Opus 5 | $0.00023 | $0.00886 |
| Sonnet 5 | $0.00009 | $0.00355 |
| Haiku 4.5 | $0.00005 | $0.00177 |
Grade A, and why
us-stock-researcher 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 12d 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
US Stock Researcher
Institutional-grade deep analysis of US stock SEC filings, outputting professional investment reports.
Research Mode Selection
| Mode | When to Use | Requirements |
|---|---|---|
| Gemini Mode | Default when GEMINI_API_KEY is configured | GEMINI_API_KEY environment variable |
| Claude Native Mode | When no Gemini API or user requests | WebSearch tool access |
Quick Start Workflow
Path Variables
Before starting, determine these two paths:
<project_root>: The user's current working directory (where the agent session started). All output files go here.<skill_dir>: The directory containing this SKILL.md file. Use its absolute path to reference scripts.
IMPORTANT: Always use absolute paths when running scripts. Never cd into the skill directory.
Step 1: Determine Filing Period
If user did NOT specify a period, use WebSearch to find the latest filing:
WebSearch: "{company_name} latest 10-K 10-Q SEC filing"
IMPORTANT: Always analyze the MOST RECENT filing by date, regardless of type (10-K or 10-Q).
Example decision logic:
- If latest 10-K is 2024-12-31 and latest 10-Q is 2025-09-30 → Use 10-Q (more recent)
- If latest 10-K is 2025-01-15 and latest 10-Q is 2024-09-30 → Use 10-K (more recent)
Inform user: "根据搜索，{TICKER} 最新的财报是 {10-K/10-Q}（截至 {period}），将分析该期财报"
Step 2: Download Filing
python3.11 <skill_dir>/scripts/download_sec_filings.py --ticker <TICKER> --type <10-K|10-Q|6-K> --limit 1 --project-root <project_root>
Output: <project_root>/investment-research/{TICKER}/tmp/sec_filings/cleaned.txt
Step 3: Dynamic Framework Generation
- Read first 5000 characters of filing
- Identify company industry
- Select modules from
<skill_dir>/industry-analysis-modules.md - Merge with
<skill_dir>/financial-analysis-framework.md - Save to
<project_root>/investment-research/<TICKER>/tmp/analysis-framework-YYYY-MM-DD.md
Step 4: Execute Deep Research
What ships with it
14 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.
- financial-analysis-framework.md 7.5 KB
- industry-analysis-modules.md 8.1 KB
- markdown-formatter-rules.md 5.4 KB
- prompts/claude-deep-research-protocol.md 10 KB
- prompts/got-research-templates.md 11 KB
- prompts/phase1-filesearch-template.md 639 B
- prompts/phase1-inline-template.md 717 B
- prompts/phase2-web-research-template.md 2.5 KB
- prompts/report-merge-prompt.md 4.3 KB
- README.md 7.2 KB
- scripts/clean_sec_filing.py 11 KB runs code
- scripts/download_sec_filings.py 5.0 KB runs code
- scripts/gemini_deep_research.py 24 KB runs code
- scripts/requirements.txt 199 B
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.
- 12d ago First seen · 184 lines · 45 tokens per session scan A 0e97f97d663f
us-stock-researcher is a skill published in the GitHub repository skindhu/skind-skills (54 stars, last pushed 6mo ago), licensed MIT. It adds 45 tokens to every session and 1,773 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 2026-08-30.
Other skills, from other repositories
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.
furusato
A Japanese hometown-tax donation manager for furusato nozei, a system where donations to municipalities can qualify for an income-tax or local-tax deduction. It reads donation receipts, stores donation records, and calculates deduction limits.
reading-receipt
An image-reading workflow for extracting structured information from receipts, invoices, and hometown-tax donation certificates. It can first extract text from PDFs and otherwise read their images.