A collection of Agent Skills for Altertable AI agents. Skills are portable, version-controlled packages of instructions, scripts, and references that give agents new capabilities.
Agent Skills are an open standard for giving AI agents specialized capabilities. Each skill is a self-contained folder with a SKILL.md file containing instructions that agents load on demand. Build once, use across any compatible platform.
Don't know which skill to use? Just type:
/altertable:ask <your question>
The /altertable:ask command routes your query to the best skill automatically. Examples:
/altertable:ask show me my web traffic->analyzing-web-traffic/altertable:ask what tables do I have?->exploring-data/altertable:ask analyze my signup funnel->analyzing-funnels/altertable:ask what is Altertable?->understanding-platform
| Skill | Description |
|---|---|
| analyzing-funnels | Creates and analyzes conversion funnels to understand user journeys |
| analyzing-insights | Interprets chart data to identify patterns, anomalies, and trends |
| analyzing-web-traffic | Analyzes web analytics data to identify traffic patterns |
| building-segments | Creates user segments and cohorts using filters and dimensions |
| configuring-watchers | Configures monitoring agents with intervals and targets |
| creating-insights | Creates discoveries with insights through the approval workflow |
| deciding-actions | Decision matrices for choosing insight types and discovery actions |
| evaluating-skills | Evaluates and creates agent skills following best practices |
| exploring-data | Explores data connections and schemas |
| forecasting-timeseries | Analyzes time series data for trends, anomalies, and forecasts |
| managing-discoveries | Manages the discovery approval workflow and user feedback |
| querying-lakehouse | Writes and executes SQL queries against the DuckDB Lakehouse |
| tracking-events | Works with product analytics events and user identification |
| understanding-platform | Explains platform concepts and architecture |
| using-memory | Stores and retrieves agent memories for learning and context |
git clone https://github.com/altertable-ai/skills.git
cd skills
uv sync
uv run pre-commit installuv run skills validate ./skills/skill-nameEvery skill is scored by an LLM judge against the Agent Skills spec (threshold: 70/100):
uv run python scripts/score-skills.py ./skills/skill-name --verboseuv run pytest scripts/tests/ -vcp -r skills/SKILL_TEMPLATE skills/my-new-skillEach skill follows the Agent Skills Specification:
skills/
skill-name/
SKILL.md # Required: metadata + instructions
references/ # Optional: detailed documentation
scripts/ # Optional: executable code
assets/ # Optional: templates, resources
See CONTRIBUTING.md for full guidelines.
Skills follow the open Agent Skills standard and work across 30+ compatible platforms:
Claude Code | Cursor | VS Code | Gemini CLI | OpenAI Codex | GitHub Copilot | Goose | Roo Code | OpenHands | and more
This project is licensed under the MIT License. See LICENSE for details.