session-flow

Melodic Software — Claude Code plugins

A public Claude Code plugin marketplace of reusable, repo-agnostic skills, hooks, and agents. Each plugin is designed to work in any repository and to be customized by consumers without editing the plugin itself.

The catalog below is generated from the plugin manifests and kept in sync by CI. New plugins clear the per-plugin migration gate in docs/MIGRATION-PLAYBOOK.md.

Use this marketplace

/plugin marketplace add melodic-software/claude-code-plugins
/plugin install <plugin-name>@melodic-software

Browse and manage with /plugin. To refresh after updates: /plugin marketplace update melodic-software.

Enable plugin suggestions for an organization

Some catalog entries declare relevance signals so Claude Code can suggest the plugin when a session's work matches (matching runs locally; nothing is reported anywhere). Suggestions are opt-in per marketplace: they surface only after an administrator allowlists the marketplace in managed settings — declare the marketplace source AND allowlist its name in the same file:

{
  "extraKnownMarketplaces": {
    "melodic-software": {
      "source": {
        "source": "github",
        "repo": "melodic-software/claude-code-plugins"
      }
    }
  },
  "pluginSuggestionMarketplaces": ["melodic-software"]
}

The source declaration is required for any non-official marketplace: the allowlisted name is ignored if the locally registered marketplace came from a different source, which stops an unrelated catalog from registering under an allowlisted name to get its plugins suggested. Reference: Recommend plugins for your org.

A few personal or external-service plugins install disabled (defaultEnabled: false) until the user opts in with /plugin enable; an existing install is never flipped by catalog changes.

Catalog

Discovery

• knowledge — Ingest external knowledge into durable, synthesized artifacts. Ships a book-distillation pipeline (PDF/EPUB into concept-organized, author-attributed skill reference files), a YouTube pipeline (watch, transcript, link harvest, and repo-applicability synthesis), and a course-digest pipeline (extract and synthesize online video courses — Dometrain, Teachable — into repo-applicable recommendations), plus a re-runnable setup action; a configurable library directory governs where synthesized artifacts land in the consuming repo.
• context7 — Looks up current library documentation, API references, and code examples via Context7 (ctx7 CLI or the Context7 MCP server) with a two-step resolve-then-query workflow: a lookup skill (default lookup plus an upstream drift-check action) and a setup skill for CLI install, auth, and MCP configuration.
• firecrawl — Web scraping, search, crawling, and file parsing through the firecrawl-cli binary with a write-to-disk-then-Read pattern that keeps large results out of context — plus a gated maintainer update flow tracking the upstream CLI and skill source.
• discovery — Structured discovery before changes: explore the local codebase (inline or in an isolated forked subagent) and run disciplined multi-source external research with source tiers, falsification, and recency gates — persisting EXPLORE.md / RESEARCH.md handoff artifacts.

Design