From notes
Use when starting a conversation, after agents return results, or when the user references their notes — manages a checklist of captured thoughts
npx claudepluginhub lilo-labs/claude-code-pluginsThis skill uses the workspace's default tool permissions.
You have access to a notes system where the user captures thoughts — especially while agents are running. Notes are stored as checklists with IDs, tags, and done/pending status.
Guides Next.js Cache Components and Partial Prerendering (PPR) with cacheComponents enabled. Implements 'use cache', cacheLife(), cacheTag(), revalidateTag(), static/dynamic optimization, and cache debugging.
Migrates code, prompts, and API calls from Claude Sonnet 4.0/4.5 or Opus 4.1 to Opus 4.5, updating model strings on Anthropic, AWS, GCP, Azure platforms.
Automates semantic versioning and release workflow for Claude Code plugins: bumps versions in package.json, marketplace.json, plugin.json; verifies builds; creates git tags, GitHub releases, changelogs.
You have access to a notes system where the user captures thoughts — especially while agents are running. Notes are stored as checklists with IDs, tags, and done/pending status.
1. Conversation start: Run the notes script to see pending notes:
"${CLAUDE_PLUGIN_ROOT}/scripts/notes.sh" show --pending
"${CLAUDE_PLUGIN_ROOT}/scripts/notes.sh" show --global --pending
If there are pending notes, acknowledge them briefly: "You have N pending notes — I'll keep these in mind." Do not act on them unless the user asks.
2. After agents return: Before continuing work after a subagent completes, check for new notes. The user may have added thoughts while the agent was running:
"${CLAUDE_PLUGIN_ROOT}/scripts/notes.sh" show --pending
Surface any notes relevant to the work that just completed.
3. When you resolve a noted concern: If your work directly addresses a pending note, mark it done:
"${CLAUDE_PLUGIN_ROOT}/scripts/notes.sh" done <id>
Tell the user: "Marked note #N as done — [brief reason]."