# Alterlab Skill Name

> <Verb-led statement of what the skill does, naming the real tools/libraries/databases/methods>. Use when <concrete trigger conditions and keywords a user's request would contain>. Part of the AlterLab Academic Skills suite.

- Skill: `alterlab-ieu/alterlab-skill-name` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add alterlab-ieu/alterlab-skill-name`
- Raw SKILL.md: https://api.skillmd.com/api/skills/alterlab-ieu/alterlab-skill-name/raw
- Safety review: PASS (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- License: MIT
- Author: AlterLab-IEU (https://skillmd.com/u/alterlab-ieu)
- Updated: 2026-08-19
- Page: https://skillmd.com/skills/alterlab-ieu/alterlab-skill-name

---


# Skill Title

One-paragraph overview: what this skill does and the value it adds. Keep the whole
SKILL.md body under ~500 lines — move long detail into `references/` (loaded on demand).

## When to Use This Skill

Use this skill when the user wants to:
- <concrete task 1>
- <concrete task 2>

### Does NOT Trigger

| Scenario | Use Instead |
|----------|-------------|
| <adjacent task> | `alterlab-other-skill` |

## Core Capabilities

### 1. <Capability>

Concrete, correct guidance with real APIs/commands. Cite real sources; never fabricate
citations, benchmarks, or DOIs.

## Resources

- `references/<topic>.md` — detailed reference loaded on demand
- `scripts/<tool>.py` — runnable helper (invoke as `python scripts/<tool>.py`)

<!--
AUTHORING CHECKLIST (see CONTRIBUTING.md → Skill Quality Standards):
- name == this directory's name, lowercase-hyphen, no 'claude'/'anthropic'
- description: third person, leads with what + "Use when", suite label LAST, <=1024 chars
- body <500 lines; reference files exist; tools scoped in allowed-tools
- add evals/evals.json on the docs/evals.schema.json shape
  (>=3 should_trigger + >=1 should_not_trigger assertion — see docs/evals.md)
- validate: python scripts/audit_skills.py  &&  uv run pytest tests/
-->