From shipit
Use when about to claim work is complete — runs test suite, checks acceptance criteria, and collects concrete evidence
npx claudepluginhub jugrajsingh/skillgarden --plugin shipitThis skill is limited to using the following tools:
Run evidence-based verification: test suite execution, acceptance criteria checking, regression detection, and gate decision.
Guides Next.js Cache Components and Partial Prerendering (PPR) with cacheComponents enabled. Implements 'use cache', cacheLife(), cacheTag(), revalidateTag(), static/dynamic optimization, and cache debugging.
Guides building MCP servers enabling LLMs to interact with external services via tools. Covers best practices, TypeScript/Node (MCP SDK), Python (FastMCP).
Generates original PNG/PDF visual art via design philosophy manifestos for posters, graphics, and static designs on user request.
Run evidence-based verification: test suite execution, acceptance criteria checking, regression detection, and gate decision.
$ARGUMENTS = optional scope (slug or "current plan").
If $ARGUMENTS is empty:
Detect the test runner from project files:
Execute the test suite and capture full output (stdout + stderr):
# Example for Python:
pytest --tb=short -v 2>&1
Record results:
If the test suite fails to run at all (import errors, configuration issues), report this as a critical failure immediately.
Source acceptance criteria based on available context:
If slug provided and plan exists:
If no plan available:
Extract criteria from commit messages:
git log develop...HEAD --format="%B" | grep -i "acceptance\|criteria\|verify"
Extract from PR description if one exists
If no criteria found, report: "No acceptance criteria found. Verification limited to test suite results."
List each criterion with a number for reference.
For each criterion, collect concrete evidence (test output, file diff, command output). Run regression check on broader suite. Generate verification report.
Full procedures, evidence rules, and report template: references/evidence-collection.md
The gate is PASS only when ALL of the following are true:
The gate is BLOCKED when ANY of the following are true:
If BLOCKED, list every failure explicitly:
### Gate Decision
BLOCKED
Failures:
1. Test suite: {N} tests failing
2. Criterion #2: {what failed}
3. Regression: {what regressed}
Recommended actions:
1. {specific action to fix failure 1}
2. {specific action to fix failure 2}