{
  "markdown": "# Altertable Skills\n\n[![CI](https://github.com/altertable-ai/skills/actions/workflows/ci.yml/badge.svg)](https://github.com/altertable-ai/skills/actions/workflows/ci.yml)\n[![Score Skills](https://github.com/altertable-ai/skills/actions/workflows/score-skills.yml/badge.svg)](https://github.com/altertable-ai/skills/actions/workflows/score-skills.yml)\n[![Agent Skills](https://img.shields.io/badge/Agent%20Skills-compatible-8A2BE2)](https://agentskills.io)\n[![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE)\n[![Skills](https://img.shields.io/badge/skills-17-green)](https://github.com/altertable-ai/skills)\n[![Python 3.12+](https://img.shields.io/badge/python-3.12+-3776AB.svg)](https://www.python.org)\n\nA collection of [Agent Skills](https://agentskills.io) for [Altertable](https://altertable.ai) AI agents. Skills are portable, version-controlled packages of instructions, scripts, and references that give agents new capabilities.\n\n## What are Agent Skills?\n\nAgent Skills are an [open standard](https://agentskills.io/specification) 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.\n\n## Quick Start with `/altertable:ask`\n\nDon't know which skill to use? Just type:\n\n```\n/altertable:ask <your question>\n```\n\nThe `/altertable:ask` command routes your query to the best skill automatically. Examples:\n\n- `/altertable:ask show me my web traffic` -> `analyze-web-traffic`\n- `/altertable:ask what tables do I have?` -> `explore-data`\n- `/altertable:ask analyze my signup funnel` -> `analyze-funnels`\n- `/altertable:ask what is Altertable?` -> `understand-platform`\n\n## Available Skills\n\n| Skill | Description |\n| ----- | ----------- |\n| [analyze-funnels](skills/analyze-funnels/) | Builds conversion funnels over ordered steps |\n| [analyze-insights](skills/analyze-insights/) | Explains what an existing insight or chart shows |\n| [analyze-web-traffic](skills/analyze-web-traffic/) | Analyzes website traffic (pageviews, sessions, referrers, landing pages) |\n| [ask](skills/ask/) | Routes user queries to the best-fit Altertable skill |\n| [build-segments](skills/build-segments/) | Compares event metrics across cohorts using filters, breakdowns, and dimensions |\n| [configure-tasks](skills/configure-tasks/) | Schedules recurring AI tasks over insights and dashboards |\n| [create-discoveries](skills/create-discoveries/) | Reports a change, anomaly, root cause, recommendation, or warning to users |\n| [create-insights](skills/create-insights/) | Drafts, renders, and saves insights of every type (SQL, semantic, segmentation, funnel, retention) |\n| [decide-actions](skills/decide-actions/) | Decision matrices for picking insight types (funnel, retention, semantic, segmentation, SQL), task types, and discovery actions |\n| [evaluate-skills](skills/evaluate-skills/) | Evaluates and authors agent skills against the Agent Skills spec |\n| [explore-data](skills/explore-data/) | Inspects catalogs, schemas, tables, columns, semantic models, measures, and dimensions |\n| [forecast-timeseries](skills/forecast-timeseries/) | Runs on-demand statistics over a time series to spot outliers and project values |\n| [instrument-product-analytics](skills/instrument-product-analytics/) | Adds Altertable product analytics to an application (event tracking, user identification, traits, consent, session reset, aliasing) |\n| [manage-discoveries](skills/manage-discoveries/) | Reviews, approves, and rejects existing discoveries |\n| [query-lakehouse](skills/query-lakehouse/) | Writes, validates, optimizes, and runs DuckDB SQL against the Altertable lakehouse |\n| [query-product-events](skills/query-product-events/) | Queries product events and identities with SQL (event counts, properties, user activity, traits) |\n| [understand-platform](skills/understand-platform/) | Explains Altertable concepts and architecture |\n| [use-memory](skills/use-memory/) | Stores and recalls agent memories and org knowledge between sessions |\n\n## Getting Started\n\n```bash\ngit clone https://github.com/altertable-ai/skills.git\ncd skills\nuv sync\nuv run pre-commit install\n```\n\n### Validate a skill\n\n```bash\nuv run skills validate ./skills/skill-name\n```\n\n### Score a skill\n\nEvery skill is scored by an LLM judge against the Agent Skills spec (threshold: 70/100):\n\n```bash\nuv run python scripts/score-skills.py ./skills/skill-name --verbose\n```\n\n### Run tests\n\n```bash\nuv run pytest scripts/tests/ -v\n```\n\n## Creating a New Skill\n\n```bash\ncp -r templates/SKILL_TEMPLATE skills/my-new-skill\n```\n\nEach skill follows the [Agent Skills Specification](https://agentskills.io/specification):\n\n```\nskills/\n  skill-name/\n    SKILL.md          # Required: metadata + instructions\n    references/       # Optional: detailed documentation\n    scripts/          # Optional: executable code\n    assets/           # Optional: templates, resources\n```\n\nSee [CONTRIBUTING.md](CONTRIBUTING.md) for full guidelines.\n\n## Compatibility\n\nSkills follow the open [Agent Skills](https://agentskills.io) standard and work across 30+ compatible platforms:\n\n**Claude Code** | **Cursor** | **VS Code** | **Gemini CLI** | **OpenAI Codex** | **GitHub Copilot** | **Goose** | **Roo Code** | **OpenHands** | **and more**\n\n## Resources\n\n- [Agent Skills Specification](https://agentskills.io/specification)\n- [Altertable](https://altertable.ai)\n- [Anthropic Skills Examples](https://github.com/anthropics/skills)\n\n## License\n\nThis project is licensed under the MIT License. See [LICENSE](LICENSE) for details.\n",
  "bytes": 5631,
  "sha": "3993e019d7dd338d0e14963c07f9e88ca6c5eec982b640de0fe5b30849cb885e",
  "repo_slug": "altertable-ai/skills",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/plg_altertable_ai_skills_altertable_734d4a79/readme"
}