stock-research-executor — Claude Code skill: what it does and setup
Runs structured 8-phase investment due diligence on stocks using parallel sub-agents. Helps produce cited research reports covering company fundamentals, industry cycles, and risks.
npx skills add liangdabiao/Claude-Code-Stock-Deep-Research-Agent --skill stock-research-executor -a claude-codeWhat stock-research-executor does
The skill executes fundamental equity due diligence following an 8-phase research framework. It takes a structured brief and lays out a plan under RESEARCH/STOCK_[ticker]_[company]/. To gather evidence, it launches parallel research agents using the Task tool. These workers pull data through WebSearch, WebFetch, and the mcp__web_reader__webReader tool.
The workflow examines business drivers and governance. It also inspects financial anomalies and moat strength. Sub-agents grade citations on an A-E scale while separating verified facts from market opinion. A final synthesis provides traffic-light signal ratings alongside tracking checklists for future reviews.
Research hinges entirely on strict inputs. The executor will halt and ask questions if you skip the structured brief from stock-question-refiner. You need ticker and holding period upfront. Because reports write directly to disk, the agent requires local file permissions.
What it helps with
- Run structured fundamental due diligence across 8 research phases
- Deploy parallel sub-agents to gather and cross-check financial data
- Audit earnings quality, share ownership, and capital allocation
- Compile a cited report with source confidence grades and tracking checklists
Example prompts for the agent
- Execute the 8-phase stock research plan using the structured prompt for NVDA in the US market.
- Run stock-research-executor on the brief from stock-question-refiner for BABA with a long-term value focus.
- Plan and run parallel due diligence agents for AAPL covering financial quality and competitive moats.
How to install stock-research-executor
1Skills CLI (Vercel)
npx skills add liangdabiao/Claude-Code-Stock-Deep-Research-Agent --skill stock-research-executor -a claude-code2Manually: put the files in place
~/.claude/skills/stock-research-executor/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/stock-research-executor/
1Skills CLI (Vercel)
npx skills add liangdabiao/Claude-Code-Stock-Deep-Research-Agent --skill stock-research-executor -a codex2Manually: put the files in place
.agents/skills/stock-research-executor/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add liangdabiao/Claude-Code-Stock-Deep-Research-Agent --skill stock-research-executor -a cursor2Manually: put the files in place
.cursor/skills/stock-research-executor/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install liangdabiao/Claude-Code-Stock-Deep-Research-Agent stock-research-executor2Manually: put the files in place
.github/skills/stock-research-executor/SKILL.md1Skills CLI (Vercel)
npx skills add liangdabiao/Claude-Code-Stock-Deep-Research-Agent --skill stock-research-executor -a gemini-cli2Platform CLI
gemini skills install https://github.com/liangdabiao/Claude-Code-Stock-Deep-Research-Agent --path 1.claude/skills/stock-research-executorManually: put the files in place
.devin/skills/stock-research-executor/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add liangdabiao/Claude-Code-Stock-Deep-Research-Agent --skill stock-research-executor -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about stock-research-executor
How to install stock-research-executor in Claude Code?
Run npx skills add liangdabiao/Claude-Code-Stock-Deep-Research-Agent --skill stock-research-executor -a claude-code. This registers the skill for Claude Code.
What does stock-research-executor do?
It executes an eight-phase investment due diligence workflow, analyzing business models, industry dynamics, governance, valuation, and risks using parallel search agents.
What inputs are required before running research?
The executor expects a structured brief, typically generated by stock-question-refiner. It must include the ticker, market, investment style, time horizon, and data source constraints.
