What does this skill do, and when should you use it?
This skill defines a workflow to construct and maintain a calendar of upcoming catalysts—earnings dates, economic releases, conferences, product launches, regulatory decisions, and macro events—for a user-defined coverage universe. It helps prioritize attention and positioning by collecting events via platform tools, organizing them in a table, and outputting an Excel workbook and weekly preview. The skill is part of the LangAlpha financial research skill set, following the Agent Skills spec, and is derived from Anthropic's financial-services-plugins.
The skill guides the user through defining a coverage universe (e.g., tickers or sectors), then uses MCP tools like get_earnings_calendar and get_economic_calendar to gather earnings and macro events, complemented by WebSearch/WebFetch for news-driven catalysts. It compiles events into a structured table with date, event, type, impact level, and positioning notes. It generates a weekly forward-looking summary and saves outputs as an Excel workbook and a markdown note to a designated work directory.
- A portfolio manager who wants to see upcoming earnings dates and macro data for holdings in the next two weeks to adjust positions.
- A quant researcher needing to track CPI, jobs reports, and Fed meetings to time trades or rebalance models.
- An equity analyst covering a sector who wants to build an event calendar to prioritize research before busy earnings season.
- A trader looking for catalysts like product launches or FDA approvals to spot short-term opportunities.
- An investment team that conducts weekly reviews of market events and records outcomes to refine future predictions.
How do you install this skill?
- The skill relies on external services (macro MCP, Web search) that may be unavailable in certain environments; verify availability before use.
- Trigger terms are broad and may cause false positives; users should specify task type clearly.
- No Chinese language support or mainland-China network reachability noted; test if intended for those environments.
- Shell / CLI
- Network access
- Local filesystem
- MCP Server
Python 3.12+MCP servers
This skill ships as part of the LangAlpha repository. Follow the repo README to clone and start LangAlpha (Docker or make config); the skill is included. Alternatively, place the SKILL.md file into a workspace's skills directory. It activates via slash command or auto-detection.
tmp="$(mktemp -d)"
git clone --depth 1 https://github.com/ginlix-ai/LangAlpha.git "$tmp"
mkdir -p ~/.claude/skills
cp -R "$tmp/skills/catalyst-calendar" ~/.claude/skills/
rm -rf "$tmp"Generated from the source repository and skill path; it copies only this skill's folder. If the author's install steps above differ, follow those first. To scope it to one project, replace ~/.claude/skills with that project's .claude/skills.
How do you use this skill?
Once installed, send your agent any of these to trigger it:
- Build a catalyst calendar for the next month
In LangAlpha, trigger the skill with natural language like 'Build a catalyst calendar for the next month' or 'What's coming up this week?' The skill will guide you to define the coverage universe, then automatically collect events and generate an Excel calendar and weekly preview. Ensure required MCP servers (e.g., macro economics) and network access are configured.
What are this skill's strengths and limitations?
- Provides a clear, step-by-step workflow from defining the universe to producing deliverables.
- Covers a wide range of catalyst types: earnings, corporate, industry, and macro events.
- Outputs a sortable Excel calendar useful for team collaboration.
- Emphasizes archiving past catalysts to build pattern recognition.
- Depends on external MCP servers and web search; functionality is limited without them.
- Event dates can shift; manual verification is required, and the skill doesn't guarantee accuracy.
- No automated tests or validation are mentioned, so output quality relies on user diligence.
- As part of a monorepo, extracting the skill for standalone use may require adapting file paths and tools.
How does this skill compare with similar options?
Side by side with related skills; every score comes from the same FSRS standard.
| Skill | FS score | Stars | Last updated | License |
|---|---|---|---|---|
| Catalyst Calendar Skill this page | 48 · Use with care | ★ 1.8k | 3d ago | Apache-2.0 |
| Equity Catalyst Calendar ✓ Anthropic · Official | 44 · Not recommended | ★ 39k | 20d ago | Apache-2.0 |
| Financial Statement Ratio Analyst ✓ Anthropic · Official | 40 · Not recommended | ★ 53k | 13d ago | MIT |
| Nine-Chapter Equity Research Skill | 63 · Recommended | ★ 453 | 1mo ago | MIT |
| Earnings Update Researcher ✓ Anthropic · Official | 54 · Use with care | ★ 39k | 20d ago | Apache-2.0 |
This skill is adapted from anthropics/financial-services-plugins, but modified for LangAlpha with MCP server integration and a specific workspace directory structure.
How did FollowSkills review this skill?
The skill file defines only a workflow, no permissions or sensitive data handling, pure documentation, limited risk, but lacks explicit disclosure and verification of data sources (e.g., macro MCP and web search). Deduct for incomplete security information.
Workflow steps are clear but no tests or specific execution details provided, dependency on external tools (macro MCP) unverified, failure handling unspecified. Static assessment gives moderate-low score.
Clear target scenario (catalyst calendar), but trigger terms are broad causing potential false positives; boundaries (e.g., uncovered asset types, data freshness) not declared. Environment fit lacks Chinese and mainland network considerations.
Clear structure and output format, but missing installation/dependency notes, versioning, changelog, maintenance responsibility, FAQ and troubleshooting.
Expected outputs (Excel and markdown) have some value, but implementation details insufficient to confirm outputs are directly usable or need only light review.
CI workflows exist but are for code review, not covering skill key paths; no test suite or independent verification for this skill.
Open a dimension to read why it scored that way
Evidence confidence：Low — Mostly static review, author material or a limited demo; useful for discovery, not high-risk decisions.
See the full review method →