skills/langextract-usage/README.md
This directory is an Agent Skill source that teaches
AI coding assistants how to use LangExtract correctly. It follows the open
Agent Skills format (SKILL.md with YAML frontmatter, optional
references/, examples/).
This directory is not auto-discovered by any tool from the skills/
path it lives in here. To use it, copy or symlink the directory into
whichever path your Agent-Skills-compatible tool reads from.
Pick your tool, then install at either project scope (this repo only) or user scope (all your projects). Paths below are canonical examples per each tool's 2026 docs — some tools (Copilot, Codex) scan several paths, so any of the documented locations works. Check the linked docs for the full list if your tool has moved.
Project-scope paths are relative to your workspace/repo root. Run the copy or symlink command from there.
| Tool | Project-scope path (example) | User-scope path (example) |
|---|---|---|
| Google Antigravity | .agents/skills/langextract-usage/ | ~/.gemini/antigravity/skills/langextract-usage/ |
| Anthropic Claude Code | .claude/skills/langextract-usage/ | ~/.claude/skills/langextract-usage/ |
| OpenAI Codex | .agents/skills/langextract-usage/ | ~/.agents/skills/langextract-usage/ |
| GitHub Copilot | .github/skills/langextract-usage/ | ~/.copilot/skills/langextract-usage/ |
Notes:
.agent/skills/ (singular) for
backward compatibility; new installs should use .agents/skills/
(plural)..claude/skills/ or .agents/skills/ at project
scope, and ~/.claude/skills/ or ~/.agents/skills/ at user scope..agents/skills/ from the current directory up through
the repo root, so a project-scope install works from any subdirectory..agents/skills/langextract-usage/ therefore activates
the skill in Antigravity, Codex, and Copilot simultaneously.cp -R skills/langextract-usage <tool-skill-path>
ln -s "$(pwd)/skills/langextract-usage" <tool-skill-path>
.cursor/rules/, Windsurf .windsurf/rules/, Aider CONVENTIONS.md) —
copy the relevant sections of SKILL.md / references/*.md into that
tool's convention. The content is portable; only the activation
mechanism differs.After activating, restart your agent session if the tool does not auto-detect changes.
SKILL.md — entry point; install, basic usage, key parameters, working with
results, common issuesreferences/providers.md — Gemini, OpenAI, Ollama, ModelConfig, custom
provider pluginsreferences/resolver-params.md — fuzzy alignment tuningreferences/prompt-validation.md — PromptValidationLevel detailsexamples/ — runnable scripts (basic_extraction.py,
relationship_extraction.py, multiple_documents.py)When changing user-facing LangExtract APIs (imports, lx.extract() kwargs,
resolver or validation behavior), please update the affected files in this
subtree in the same PR. If you spot drift, open an issue or PR.