ticker-briefing
Skill0 starsChanged 3 months agoMITView on GitHub
Structured market briefing for any ticker using live data tools when available. Use when the user asks about a stock, ticker, or "what's happening with X", wants a market summary, or mentions price moves, options, or earnings context.
In this repository4 other files it gives its agents.
- backtest-reviewSkill
- data-quality-auditSkill
- paper-reproSkill
- stats-test-pickerSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 29
Every number gets a timestamp qualifier ("as of the last quote I pulled")
- Distinctive: line 30
No price targets, no buy/sell recommendations, ever.
- Distinctive: line 31
If data tools error out, degrade gracefully to qualitative framing and say so explicitly
- Distinctive: line 36
Use short sections with the headers above.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Ticker Briefing
Produce a structured briefing, not a data dump. If an MCP market-data tool (e.g. yfinance-mcp) is available, use it for live numbers; otherwise say clearly that figures are from training data and may be stale.
Briefing structure
1. Snapshot
Last price, day change %, 52-week range position ("at 78% of its 52w range"), volume vs typical if available.
2. Trend context
Return over 1 month / 6 months / 1 year. One sentence characterizing the trend (making higher highs, range-bound, drawing down). Max drawdown over the period if computable.
3. Options surface (if listed)
Nearest monthly expiration: ATM call IV, put/call OI skew direction. Translate: high IV percentile means the market prices big movement; heavy put OI can signal hedging demand, not necessarily bearishness. Never present options flow as a directional prediction.
4. News scan
Top 3-5 headlines with dates and links. Separate facts (earnings date, product launch) from narratives ("analysts bullish"). Attribute every claim.
5. What to watch
Two or three concrete upcoming catalysts: earnings date, macro prints relevant to the sector, known lockup/index events.
Rules
- Every number gets a timestamp qualifier ("as of the last quote I pulled")
- No price targets, no buy/sell recommendations, ever; end with what to watch, not what to do
- If data tools error out, degrade gracefully to qualitative framing and say so explicitly
- Currency and exchange suffixes matter: clarify ambiguous tickers before pulling data
Format
Use short sections with the headers above. Total length: scannable in 30 seconds. Tables over prose for numbers.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.