earnings-preview · openai — Codex skill: what it does, how to install
Builds a full pre-earnings report with market expectations, KPI tracking, scenarios, and call questions. Use it before results are released.
npx skills add openai/plugins --skill earnings-preview -a codexWhat earnings-preview does
This skill builds a complete pre-earnings report. It starts with an executive view, then lays out the market’s expectation bar, possible stock-reaction drivers, supporting evidence, and questions for the earnings call. It can add guidance-credibility work, KPI views, bull/base/bear cases, and gaps in the evidence when the sources support them.
The workflow draws on company filings and IR material, earnings transcripts and events, market estimates, and internal research. A standalone HTML report is the default surface for a full preview, while an interactive run can resolve remaining choices about depth, audience, or focus. Connected workflows handle source resolution and related analysis.
This is a pre-print workflow, not a post-results review tool. The report should keep company facts, consensus, whisper data, analyst inference, and user assumptions separate, while recording the freeze time and timestamps for time-sensitive inputs.
What it helps with
- assemble a full pre-earnings report
- compare market expectations with company guidance
- map possible stock reactions to bull, base, and bear cases
- prepare KPI views and earnings-call questions
- flag evidence gaps before the results release
Example prompts for the agent
- Prepare a full pre-earnings report with an executive summary, expectation bar, and scenarios.
- Compare company guidance with consensus and identify what could move the stock after the results.
- Build a KPI dashboard and call-question list, separating missing evidence from sourced findings.
How to install earnings-preview
1Skills CLI (Vercel)
npx skills add openai/plugins --skill earnings-preview -a codex2Manually: put the files in place
.agents/skills/earnings-preview/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add openai/plugins --skill earnings-preview -a claude-code2Manually: put the files in place
~/.claude/skills/earnings-preview/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/earnings-preview/
Manually: put the files in place
.cursor/skills/earnings-preview/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install openai/plugins earnings-preview2Manually: put the files in place
.github/skills/earnings-preview/SKILL.mdPlatform CLI
gemini skills install https://github.com/openai/plugins --path plugins/public-equity-investing/skills/earnings-previewManually: put the files in place
.devin/skills/earnings-preview/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: Codex skills: how to install, where they live, how to call them
Questions about earnings-preview
How do I install earnings-preview in Codex?
Run npx skills add openai/plugins --skill earnings-preview -a codex, then check .agents/skills/earnings-preview/SKILL.md.
What does earnings-preview do?
It produces a full pre-earnings report covering the expectation bar, guidance credibility, KPI signals, scenarios, stock-reaction drivers, and call questions.
Can I use earnings-preview after results are released?
No. The workflow is for preparation before the print; it handles a short summary only when the user explicitly requests that format.
Similar skills
All skills for Finance and business →earnings-preview by other authors comes first.