Batch execution with subagent pipeline — load plan, create native Tasks, run implement-review pipeline per batch
Executes batched development tasks using a three-stage implement-review pipeline with native task coordination.
npx claudepluginhub jugrajsingh/skillgardenThis skill is limited to using the following tools:
references/batch-protocol.mdExecute tasks from a plan using a 3-stage subagent pipeline per task with native Task coordination.
$ARGUMENTS = path to task_plan.md or slug.
If $ARGUMENTS is empty:
For each task in the current batch, create three native Tasks using TaskCreate:
Implementation Task
Spec Review Task
Quality Review Task
This creates a dependency chain: Implement -> Spec Review -> Quality Review
For each task in the batch, run the 3-stage pipeline sequentially.
Spawn a Task agent (subagent_type: general-purpose) with implementer instructions.
Provide the agent with:
Agent instructions:
When agent completes, update the native Task status to completed.
If implementation fails (tests won't pass after reasonable attempts):
Only runs after Stage 1 completes successfully.
Spawn a Task agent (subagent_type: general-purpose, model: sonnet) with spec-reviewer instructions.
Provide the agent with:
Agent instructions:
When agent completes, update the native Task status.
If spec review FAILS:
Only runs if spec review PASSES.
Spawn a Task agent (subagent_type: general-purpose, model: sonnet) with quality-reviewer instructions.
Provide the agent with:
Agent instructions:
Severity symbols:
When agent completes, update the native Task status.
If critical findings exist:
After all tasks in the current batch complete (or are flagged):
Mirror native Task statuses to progress.md:
Log batch completion in progress.md Batch Log section:
### Batch {N} — {DATE}
- Tasks completed: {N}/{total}
- Spec reviews: {pass_count} pass, {fail_count} fail
- Quality findings: {critical} critical, {major} major, {minor} minor
Present batch checkpoint via AskUserQuestion with three options:
After all batches complete:
shipit:verifying skill for final verification against the full plan's acceptance criteria## Execution Complete
Plan: {slug}
Batches: {completed}/{total}
Tasks: {done}/{total} ({blocked} blocked, {skipped} skipped)
### Review Summary
- Spec reviews: {pass}/{total}
- Quality findings: {critical} critical, {major} major, {minor} minor
### Verification
{ result from verifying skill }
### Next Steps
{ recommend /shipit:ship if verification passes }
{ recommend fixing issues if verification fails }
references/batch-protocol.md for detailed pipeline and failure handling protocolExpert 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.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.