yaojingang/yao-open-skills is a public collection of reusable AI skills for research, decision-making, business analysis, learning, and document creation. It serves people who want repeatable, maintainable AI workflows instead of isolated prompts, and catalogued add-ons are published skills from this collection.
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 yaojingang/yao-open-skills --skill yao-kelly-skillgit clone --depth 1 https://github.com/yaojingang/yao-open-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/yaojingang/yao-open-skills/yao-kelly-skill)<a href="https://agentmods.dev/skills/yaojingang/yao-open-skills/yao-kelly-skill"><img src="https://agentmods.dev/badge/skills/yaojingang/yao-open-skills/yao-kelly-skill/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/yaojingang/yao-open-skills/yao-kelly-skill"><img src="https://agentmods.dev/badge/skills/yaojingang/yao-open-skills/yao-kelly-skill.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 | $0.00093 | $0.00979 |
| Opus 5 | $0.00046 | $0.00490 |
| Sonnet 5 | $0.00019 | $0.00196 |
| Haiku 4.5 | $0.00009 | $0.00098 |
Grade A, and why
yao-kelly-skill 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 13d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Yao Kelly Skill
Use This Skill For
- turn "should I invest, bet, or allocate, and how much?" into a practical resource allocation plan
- decide whether the user's problem is actually suitable for Kelly-style sizing
- translate a percentage into a minimum action package with owner, metric, review window, add condition, and stop condition
- start with incomplete input, give a provisional view early, then ask only the minimum high-impact follow-up questions
- size a single bet or opportunity, or conservatively split a pool across several opportunities
- keep a round-by-round log for the current case and an append-only change log for future edits to this skill
Do Not Route Here
- pure formula tutoring, homework solving, or generic finance education
- requests for guaranteed returns, sure-win systems, or martingale-style escalation
- final licensed investment, legal, or tax advice
- leverage sizing with no bounded downside model
Default Workflow
- Use
references/intake-contract.mdto identify the user's real resource pool, decision question, minimum action unit, review window, and opportunity candidates. - If the input is incomplete, read
references/multi-turn-kelly-loop.md:- ask only
1-3questions that can materially change the result - recalculate
decision_readinessafter every round - stop asking when the threshold is met or the action class is already stable
- ask only
- Decide whether Kelly is suitable:
- use it when downside is bounded, the opportunity can be tested or repeated, and probabilities can be approximated
- switch to a test-first or risk-review answer when the decision is irreversible, one-off, or has unbounded downside
- Use
references/kelly-sizing-playbook.mdto choose the formula path:- binary opportunity: standard Kelly closed form
- scenario-based opportunity: maximize
E[log(1 + f * r)] - multiple opportunities: compute standalone Kelly first, then apply fractional Kelly, dependence haircuts, and total exposure scaling
- Run
scripts/kelly_allocation_report.pyfor canonical JSON sizing output. - Run
scripts/generate_html_report.pywhen the user wants a polished standalone HTML report or PDF-ready artifact. - Use
references/output-contract.mdto produce a practical allocation report:- resource snapshot
- fit assessment
- minimum action packages
- Kelly sizing cap
- add, stop, and review conditions
- Use
references/logging-contract.mdto maintain:- the case round log for the current user request
- the append-only iteration log in
history/CHANGELOG.mdwhenever this skill package changes
- Apply
references/safety-and-scope.mdbefore finalizing.
What ships with it
27 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.
- agents/interface.yaml 962 B
- history/CHANGELOG.md 9.6 KB
- logs/README.md 266 B
- manifest.json 628 B
- README.md 2.4 KB
- references/intake-contract.md 4.7 KB
- references/kelly-sizing-playbook.md 2.8 KB
- references/logging-contract.md 2.2 KB
- references/multi-turn-kelly-loop.md 3.0 KB
- references/output-contract.md 4.1 KB
- references/safety-and-scope.md 1.1 KB
- reports/design-summary.md 1.2 KB
- reports/engineering-hours-brief.json 2.9 KB
- reports/engineering-hours-output.json 7.8 KB
- reports/engineering-hours-report.html 27 KB
- reports/example-brief.json 1.6 KB
- reports/example-html-report.html 26 KB
- reports/example-output.json 4.3 KB
- reports/internet-product-sprint-brief.json 4.3 KB
- reports/internet-product-sprint-output.json 7.9 KB
- reports/internet-product-sprint-report.html 27 KB
- reports/marketing-budget-brief.json 2.9 KB
- reports/marketing-budget-output.json 7.8 KB
- reports/marketing-budget-report.html 27 KB
- scripts/append_iteration_log.py 2.6 KB runs code
- scripts/generate_html_report.py 31 KB runs code
- scripts/kelly_allocation_report.py 25 KB runs code
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.
- 13d ago First seen · 77 lines · 93 tokens per session scan A 596eda52f25d
yao-kelly-skill is a skill published in the GitHub repository yaojingang/yao-open-skills (1,314 stars, last pushed 15d ago), licensed MIT. It adds 93 tokens to every session and 979 once invoked, about $0.0005 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.