How do I install the Libdoc Search skill?

Run npx skillmds@latest add manykarim/libdoc-search in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Libdoc Search safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Libdoc Search?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Libdoc Search free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Libdoc Search?

manykarim (@manykarim) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Libdoc Search by manykarim — Agent Skill

Name: Libdoc Search
Rating: 4.2 (5 reviews)
Author: manykarim

Libdoc Search

Search Robot Framework library/resource/suite documentation to find matching keywords for a use case. Use when asked to find keywords, search libdoc, match a use case to keywords, or scan multiple libraries/resources for relevant keywords.

manykarim Updated Sep 10, 2026

File contents

Robot Framework Libdoc Search

Use this skill to search Robot Framework libraries/resources/suites for keywords that match a use case. Output JSON only.

Command

Search in standard libraries:

python3 "${CLAUDE_PLUGIN_ROOT}/scripts/rf_libdoc.py" --library BuiltIn --library OperatingSystem --search "create temp file" --pretty

Search multiple sources with custom weights:

python3 "${CLAUDE_PLUGIN_ROOT}/scripts/rf_libdoc.py" --library SeleniumLibrary --resource resources/common.resource --search "upload file" --weights name=0.5,short_doc=0.3,doc=0.2 --limit 10 --pretty

Notes

Use --library, --resource, --suite, or --spec (repeatable). Inputs are aggregated.
Search considers keyword name, short_doc, and full doc.
Output contract (stable): returns {schema_version, mode, libraries, results, query, ...} with mode="search". results is a single array of {library, keyword, usage, score, reasons} (search items carry score/reasons; usage is null). Read results without branching on top-level keys.
Payload is bounded: library prose doc is not included by default — only {name, type, version, scope, doc_format, short_doc} per library. Pass --include-library-doc to add the full doc.
Use --tag to filter keywords by tag.
Use --include-private to include private keywords.
Use --exclude-deprecated to drop deprecated keywords.

Frequently asked questions