skills/dev-create-b4push-script/SKILL.md
Create a before-push validation script (b4push) and project-level b4push skill. Analyzes the project, identifies check steps (quality, build, test, doc site, e2e), generates scripts/run-b4push.sh, adds package.json entry, creates .claude/skills/b4push/skill.md. Use when: (1) User says 'create b4push', 'add b4push', 'before push script', (2) Setting up a new project's CI/validation workflow.
npx skillsauth add takazudo/claude-resources dev-create-b4push-scriptInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Generate a comprehensive before-push validation script for the current project.
Read package.json to understand:
check, build, test, lint, format, typecheckdoc/, docs/, website/ directories with their own package.json)generate-* scripts in doc)Common step patterns (adapt to project):
| Step | Command | When to include |
| --- | --- | --- |
| Code quality | pnpm check or pnpm lint && pnpm format | Always |
| TypeScript build | pnpm build | If build script exists |
| Unit tests | pnpm test | If test script exists |
| Doc data generation | cd doc && pnpm run generate-* | If doc site has generate scripts |
| Doc quality checks | cd doc && pnpm run check | If doc site has check script |
| Doc site build | cd doc && pnpm build | If doc site exists |
| E2E tests | Start server + run playwright | If e2e tests exist |
For projects with e2e tests, add server lifecycle management (start, wait for ready, run tests, kill).
Create scripts/run-b4push.sh based on the template in assets/run-b4push-template.sh.
Key patterns:
set -euo pipefail for strict error handlingFAILURES=() array - continues all steps even if some failstep(), pass(), fail() helper functions(cd "$DIR" && command) to isolate directory changesROOT_DIR="$(cd "$(dirname "$0")/.." && pwd)" for reliable path resolutionMake the script executable: chmod +x scripts/run-b4push.sh
Add to package.json:
{
"scripts": {
"b4push": "./scripts/run-b4push.sh"
}
}
Create .claude/skills/b4push/skill.md based on assets/b4push-skill-template.md.
Customize:
pnpm check:fix, cd doc && pnpm check:fix)The skill should have user-invocable: true and allowed-tools: [Bash]. The description must include triggers for automatic invocation on big changes, PR completion, etc.
Run pnpm b4push to verify all steps execute correctly. Fix any issues found.
These projects have working b4push setups:
development
Link Claude Code skill names mentioned in a CodeGrid article (data/{series}/{n}.md) to the author's public claude-resources repo, pinned to the latest commit hash so links don't rot. Use when: (1) user says 'linkify cc resources', 'link the skills', 'link skill names', or invokes /dev-linkify-cc-resources; (2) editing a CodeGrid article that mentions `/commits`, `/pr-complete`, `/skill-creator` or other Claude Code skills and they should point to claude-resources. Only links skills that actually exist in the public repo; skips hypothetical examples and code blocks.
development
Second opinion from Claude Opus on a plan or approach. Use when: (1) Planning phase of /big-plan needs a higher-quality review than /codex-2nd / /gco-2nd / /gcoc-2nd, (2) User says 'opus 2nd' or 'opus opinion', (3) Wanting Anthropic's larger model to critique a plan. Spawns a general-purpose Agent with model: opus that reads the plan file and returns structured feedback. Anthropic quota — not free.
tools
AI-based testing via subagent + a per-task test-flow skill. Use when the user wants to verify something that mechanical assertions can't fully capture — image recognition, visual size/position comparison, animation smoothness, multi-step manual flows that need AI judgment. Triggers: 'AI-based test', 'AI test', 'visual verify', 'image recognition test', 'manual operation test', 'human-eye check', 'verify visually', 'compare screenshots', 'looks the same', 'looks correct'. The skill's job is to (1) author a focused test-flow skill that captures the exact procedure + verdict criteria, then (2) dispatch a verification subagent via the Agent tool that loads BOTH the test-flow skill AND a browser-driving skill (/verify-ui primary, /headless-browser fallback) so the subagent has clear context and consistent verdicts. NEVER uses `claude -p` — subagent dispatch goes through the Agent tool exclusively.
development
End-of-workflow audit of touched GitHub issues, PRs, and branches via a Sonnet subagent. Use when: (1) /big-plan, /x-as-pr, or /x-wt-teams finishes its main work and needs to verify every touched resource is in the right state (closed when done, kept when ongoing, deleted when dead), (2) User says 'cleanup resources', 'audit cleanup', or 'check what should be closed', (3) A long workflow ends and the manager wants a structured paper trail of what it closed/kept/deleted. Auto-execute by default — the Sonnet agent proposes, the manager (you) executes safe actions and prints a final report.