build-my-context7

Download and filter documentation from manifests for Context7 integration.

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "build-my-context7" with this command: npx skills add jokejason/local-context7/jokejason-local-context7-build-my-context7

Build My Context7

Download and filter documentation from manifests for Context7 integration.

Quick Start

/build-my-context7 # Process ALL manifests /build-my-context7 zod-docs # Process only zod-docs manifest

Output goes to output/ .

Workflow

Phase 1: Check Arguments

Check if $ARGUMENTS is provided:

  • If argument provided: Process only that specific manifest

  • If no argument: Process all manifests

Phase 2: Discovery

If processing a specific manifest:

  • Verify the manifest exists at .claude/skills/download-docs/scripts/manifests/{argument}.json

  • If not found, list available manifests and ask user to choose

If processing all manifests:

  • List all manifests:

ls .claude/skills/download-docs/scripts/manifests/*.json

  • Extract manifest names (without .json extension)

Phase 3: Processing

Spawn manifest-processor sub-agent(s):

Task tool call:

  • subagent_type: manifest-processor
  • prompt: "{manifest-name}"

The sub-agent handles everything:

  • Downloads files from the manifest source

  • Detects source type (URL vs GitHub)

  • Applies AI filtering for GitHub sources (skips for URL sources)

  • Returns a summary

For multiple manifests: Spawn ALL sub-agents in a SINGLE message for maximum parallelism.

Phase 4: Summary

After sub-agent(s) complete, compile results into a summary table:

Manifest Source Downloaded Filtered Final Status

name url/github N N/N/A N ✅/❌

Remind user to run /generate-agent-skills if needed.

Requirements

  • jq

  • JSON parsing

  • git

  • GitHub cloning

  • curl

  • URL downloads

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

General

filter-docs

No summary provided by upstream source.

Repository SourceNeeds Review
General

download-docs

No summary provided by upstream source.

Repository SourceNeeds Review
Automation

generate-agent-skills

No summary provided by upstream source.

Repository SourceNeeds Review