Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Download and normalize official documentation pages into local .mdx files at user-specified paths using markdown.new. Use when user asks to fetch docs from a...
Download and normalize official documentation pages into local .mdx files at user-specified paths using markdown.new. Use when user asks to fetch docs from a...
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
Convert a docs URL into a cleaned local .mdx file at a path the user specifies. Use this skill when the user wants reproducible, file-based docs snapshots for local knowledge bases, RAG prep, or project docs folders.
Run: scripts/mdnew_to_mdx.sh <source_url> <output_mdx_path> Example: scripts/mdnew_to_mdx.sh \ https://docs.convex.dev/agents/agent-usage \ docs/convex/agent-usage.mdx
Validate inputs. Require exactly 2 args: source URL and output path. Keep URL as full https://... form. Convert with script. Execute scripts/mdnew_to_mdx.sh. Confirm output. Verify file exists. Print or inspect frontmatter for title, description, sourceUrl, retrievedAt. Add indexes for folder-based docs (required). Any docs folder must include index.mdx. If docs/ exists, docs/index.mdx must exist. Index files should link child docs/subfolders. Keep frontmatter: title, description, sourceUrl (local://... allowed), retrievedAt. Report result. Return output path(s), overwrite status, and any created/updated index files.
The generated MDX must include frontmatter: title description sourceUrl retrievedAt (UTC YYYY-MM-DD) Body is cleaned to remove common docs-site artifacts and excess blank lines.
For behavior details and cleanup rules, read: references/mdnew_to_mdx.md Use the bundled script directly: scripts/mdnew_to_mdx.sh
Dependencies: bash, curl, awk, mktemp. Output file is overwritten if it already exists. Re-run anytime to refresh docs snapshot from upstream.
Workflow acceleration for inboxes, docs, calendars, planning, and execution loops.
Largest current source with strong distribution and engagement signals.