aipa-research
Broad, multi-ticker or sector research using the aipa CLI. Use for deep dives, market overviews, sector comparisons, or detailed reports. For one ticker use aipa-analyze; for raw data use aipa-data.
How do I install this agent skill?
npx skills add https://github.com/quanhua92/aipriceaction --skill aipa-researchIs this agent skill safe to install?
- Gen Agent Trust Hubfail
The skill provides a comprehensive framework for financial market research using the aipa CLI. It includes standard installation procedures for well-known developer tools and uses Python for precise data calculations. It features a typical attack surface for indirect prompt injection common in research-oriented agents that process external data feeds.
- Socketpass
No alerts
- Snykwarn
Risk: MEDIUM · 1 issue
What does this agent skill do?
Deep research
The CLI has two modes: a market snapshot and a full multi-agent research run. The snapshot needs no LLM key. The full run requires a configured API key and takes longer.
Choose a mode first
Before running an aipa command, ask whether the user wants:
- Fast research: fetch a snapshot, then investigate relevant tickers and sectors with the available tools or parallel agents.
- Full pipeline: run
aipa deep-research --run, which executes the CLI's supervisor, worker, aggregator, and review stages.
Skip the question only when the user explicitly names a mode. Do not start the full pipeline without the user's choice.
Commands
aipa deep-research [QUESTION] --source vn|crypto|global|sjc
aipa deep-research --run [QUESTION] --source vn|crypto|global|sjc
aipa deep-research --run --resume SESSION_ID
aipa deep-research --run --output report.md
Check aipa deep-research --help for current options. Use aipa config get use_sma before discussing moving-average signals.
Fast research workflow
- Fetch a snapshot for the requested market.
- Select a small set of relevant sectors and tickers. Use
aipa performersfor more than one perspective when ranking market leaders or laggards. - Assign separate sector or ticker groups to parallel workers when available. Give every worker the same data range and questions.
- Compare results using the same dates and definitions. Remove unsupported claims, resolve conflicting data, and produce one combined report.
For Vietnamese stocks, fundamental analysis is optional and should only be run when requested. Rank or screen peers before fetching detailed ratios. See the fundamentals skill.
Quality rules
- Use command output for all numeric claims. Verify ticker, date, and reporting period; mark missing data as unavailable.
- Compare volume with its 20-day average. Do not treat a day-over-day change as the 20-day comparison.
- Present both bullish and bearish evidence. State the data range and key limits.
- Before proposing an entry, inspect daily 60 bars, weekly 52 bars, and a volume profile covering at least 30 days. Check for Buying Climax, Upthrust After Distribution, and weekly trend conflict.
- Calculate reward-to-risk. Block setups below 1:1; flag below 2:1. Anchor targets to observed resistance or another stated structure.
- For Vietnamese shares, check T+2 settlement before recommending a sale.
- Keep the final report concise and separate observed data from interpretation.
How can the creator link this skill?
Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.
<a href="https://skillzs.dev/skills/quanhua92/aipriceaction/aipa-research">View aipa-research on skillZs</a>