메뉴
Pre-push code quality verification — lint, typecheck, and tests run locally before pushing. Covers discovering project verification commands, run order, scope-appropriate checks, and fixing failures. Used as a dependency from workflow skills.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | mav-local-verification |
| description | Pre-push code quality verification — lint, typecheck, and tests run locally before pushing. Covers discovering project verification commands, run order, scope-appropriate checks, and fixing failures. Used as a dependency from workflow skills. |
| user-invocable | false |
| disable-model-invocation | true |
Run lint, typecheck, and tests locally before every push. Never push code that fails local checks.
--no-verify with git commandsdigraph verify {
"Ready to push?" [shape=diamond];
"Discover verification commands" [shape=box];
"Run lint" [shape=box];
"Lint passes?" [shape=diamond];
"Fix lint issues" [shape=box];
"Run typecheck" [shape=box];
"Typecheck passes?" [shape=diamond];
"Fix type errors" [shape=box];
"Run tests" [shape=box];
"Tests pass?" [shape=diamond];
"Fix failing tests" [shape=box];
"Push to remote" [shape=box];
"Ready to push?" -> "Discover verification commands" [label="yes"];
"Discover verification commands" -> "Run lint";
"Run lint" -> "Lint passes?";
"Lint passes?" -> "Run typecheck" [label="yes"];
"Lint passes?" -> "Fix lint issues" [label="no"];
"Fix lint issues" -> "Run lint";
"Run typecheck" -> "Typecheck passes?";
"Typecheck passes?" -> "Run tests" [label="yes"];
"Typecheck passes?" -> "Fix type errors" [label="no"];
"Fix type errors" -> "Run typecheck";
"Run tests" -> "Tests pass?";
"Tests pass?" -> "Push to remote" [label="yes"];
"Tests pass?" -> "Fix failing tests" [label="no"];
"Fix failing tests" -> "Run tests";
}
Projects use different tooling. Discover the available commands by checking these sources in order:
package.json scripts (Node.js projects):
cat package.json | jq '.scripts | keys[]' 2>/dev/null
Look for: lint, typecheck, type-check, tsc, test, test:unit, check
Makefile targets:
grep -E '^[a-zA-Z_-]+:' Makefile 2>/dev/null
Look for: lint, check, test, verify, validate
Monorepo root (if applicable):
cat package.json | jq '.scripts' 2>/dev/null
Look for workspace-level commands like test:all, lint:all, or use the package manager's workspace filter.
Common patterns if no scripts are found:
| Tool | Lint | Typecheck | Test |
|---|---|---|---|
| npm/pnpm | pnpm lint | pnpm typecheck | pnpm test |
| Turborepo | pnpm turbo lint | pnpm turbo typecheck | pnpm turbo test |
| Make | make lint | make typecheck | make test |
| Python (uv) | uv run ruff check | uv run mypy . | uv run pytest |
| Go | golangci-lint run | (built into compile) | go test ./... |
Run in this order — each stage catches different classes of issues:
Stop at the first failure. Fix it before proceeding to the next stage.
Not every change needs the full suite:
| Change type | Lint | Typecheck | Tests |
|---|---|---|---|
| Code changes | Yes | Yes | Yes — at minimum the affected test files |
| Config/YAML only | No | No | No (unless config affects runtime) |
| Documentation only | No | No | No |
| New dependencies added | Yes | Yes | Yes — full suite |
For the final push before PR creation, always run the full suite regardless of change type.
Scan a project for missing best-practice areas and implement the top recommendation for each gap (linting, unit testing) — installs tools, writes configs, verifies, and commits. Pass 'recommend' to stop after writing recommendations without implementing (replaces the old do-recommend skill).
Implement a focused code change. Use this skill as the wrapper for any implementation work so the Maverick workflow report captures what was done and so the agent applies the project's coding standards before editing. Intended to be invoked once per task from inside a do-issue-* or do-epic phase, not standalone.
Audit a codebase for security risks in one of two modes. In full-audit mode it scans the entire codebase and writes a findings report to docs/security-audit.md (run as part of do-init or on demand). In update mode it reviews only a diff plus the code it could impact, returning a structured findings list as a pre-push gate for do-issue-solo and do-issue-guided. Covers secrets exposure, dependency vulnerabilities, authentication and authorisation patterns, input validation, transport security, and common OWASP risks.
Create, restructure, or update technical documentation. Handles greenfield projects, refactoring non-compliant docs, and incremental updates after code changes.
Work on a multi-story GitHub epic end-to-end. Builds a DAG from the child stories, groups them into waves, runs waves in parallel via per-story worktrees, ejects PRs that fail agent-code-review for human handling, and propagates blocks to downstream stories. Requires git worktrees.
Initialise a project for use with Maverick — verifies the GitHub App, installs the CLI if needed, writes the project config with integration tracking, scaffolds docs, generates project skills, runs an initial cybersecurity audit, then commits the changes and opens a PR.