From workbench-core
Process any pending session summaries by dispatching background agents. Use when the warmup notices unprocessed markers, or run manually to clear the backlog. Does NOT block the session — dispatches agents in the background and moves on.
npx claudepluginhub mike-bronner/claude-workbench --plugin workbench-coreThis skill uses the workspace's default tool permissions.
This is an execution-aware skill — check `skills/process-pending-summaries.learnings.md` in the vault before proceeding. If it exists, apply accumulated learnings.
Expert guidance for Next.js Cache Components and Partial Prerendering (PPR). **PROACTIVE ACTIVATION**: Use this skill automatically when working in Next.js projects that have `cacheComponents: true` in their next.config.ts/next.config.js. When this config is detected, proactively apply Cache Components patterns and best practices to all React Server Component implementations. **DETECTION**: At the start of a session in a Next.js project, check for `cacheComponents: true` in next.config. If enabled, this skill's patterns should guide all component authoring, data fetching, and caching decisions. **USE CASES**: Implementing 'use cache' directive, configuring cache lifetimes with cacheLife(), tagging cached data with cacheTag(), invalidating caches with updateTag()/revalidateTag(), optimizing static vs dynamic content boundaries, debugging cache issues, and reviewing Cache Component implementations.
Guides building MCP servers enabling LLMs to interact with external services via tools. Covers best practices, TypeScript/Node (MCP SDK), Python (FastMCP).
Share bugs, ideas, or general feedback.
This is an execution-aware skill — check skills/process-pending-summaries.learnings.md in the vault before proceeding. If it exists, apply accumulated learnings.
The user has invoked /workbench:process-pending-summaries, or the session warmup detected pending markers and asked you to handle them.
Scan ~/.claude-memory-cache/pending-summaries/ for .json marker files:
ls ~/.claude-memory-cache/pending-summaries/*.json 2>/dev/null
If none exist, tell the user there's nothing pending and exit.
For each marker, read it to get the session_id, marker_path, and log_path. Then spawn a background summary-writer agent:
Agent tool:
subagent_type: workbench:summary-writer
run_in_background: true
prompt: |
Process pending session summary.
session_id: {session_id}
marker_path: {marker_path}
log_path: {log_path}
Follow your agent definition. Write the summary, promote any decisions, delete the marker, and exit.
Dispatch all agents in a single turn — don't wait for one to finish before starting the next.
Tell the user how many summaries were dispatched (e.g. "Dispatched 3 background summary-writers. They'll process in the background — you can work normally.").
Then proceed with whatever the user actually wanted to do this session. Do NOT wait for the agents to complete.