verify-app
Runs checks per AGENTS.md and writes the verification transcript to tasks/20_verification.md.
Runs checks per AGENTS.md and writes the verification transcript to tasks/20_verification.md.
Run project verification checks using standard Makefile targets. Use when user says "verify pipeline", "check my work", "run tests", or "validate changes". Wraps `make verify-pipeline` (E2E), `make verify-analysis` (Logic), or `make verify-all`. Ensures environment constraints (e.g. Railway Shell) are met.
SAST/DAST/SCA automation, CI/CD security pipelines, vulnerability management
Temporal research for dependencies - validates versions, discovers issues, updates landmines. Use for existing projects, mid-project dependency additions, or when /flight-prd --no-research was used.
Use when user says 'release', 'リリース', 'deploy', 'publish', 'vtag', 'version up', 'バージョンアップ', or discusses merging to main/develop. Guides through version bump and release flow.
Archives completed changes and merges specification deltas into living documentation. Use when changes are deployed, ready to archive, or specs need updating after implementation. Triggers include "archive change", "merge specs", "complete proposal", "update documentation", "finalize spec", "mark as done".
Validates application readiness for Render/production deployment. Auto-runs when user mentions deployment. Prevents "works locally, fails in production" issues. Always run this BEFORE any deployment.
container-useを使用したクローズドな開発・テスト環境の構築手順、並行作業ガイドライン、技術スタック別設定例を提供
Guides agents through SPEC-First TDD workflow with context engineering, TRUST principles, and @TAG traceability. Essential for /alfred:1-plan, /alfred:2-run, /alfred:3-sync commands. Covers EARS requirements, JIT context loading, TDD RED-GREEN-REFACTOR cycle, and TAG chain validation.
Evaluates whether a programming language dependency should be used by analyzing maintenance activity, security posture, community health, documentation quality, dependency footprint, production adoption, license compatibility, API stability, and funding sustainability. Use when users ask "should I use X or Y?", "are there better options for [feature]?", "what's a good library for [task]?", "how do we feel about [dependency]?", or when considering adding a new dependency, evaluating an existing dependency, or comparing/evaluating package alternatives.
Independent verification agent for Ontology Builder Pipeline. Cross-validates outputs against inputs, checks traceability, validates constraints, and identifies issues. Use as a separate agent to verify pipeline outputs.
This skill should be used when the user asks to "propose architecture", "design implementation approach", "choose between approaches", or in Phase 4 of /dev workflow after exploration is complete. Proposes 2-3 architecture approaches with clear trade-offs, decomposes features into independent tasks, and obtains explicit user approval before implementation begins.
Audits the architecture visualization plan (Common Definitions & Draft Issues) before execution. Strictly enforces SYSTEM_ARCHITECT values and ensures zero regressions by validating against loaded SSOT context via active-reconnaissance and ssot-verification.
Use when (1) release is deployed and verified, (2) closing related issues and PRs, (3) creating GitHub release with changelog, (4) finalizing release documentation. Completes the release lifecycle.
Validates production readiness through performance benchmarking, accessibility audits, security reviews, and code quality checks. Use after implementation phase completes, before deployment, or when conducting quality gates for features. (project)
Use when setting up a new dev machine for Claude Code, onboarding to a project, or optimizing development environment - interactive installer that detects existing setup, configures shell, editor, git, templates, and quality gates with configurable enforcement
Detect project type and configuration for generic application releases
Complete Play Store setup - orchestrates scanning, privacy policy, version management, Fastlane, and workflows (Internal track only)
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
Iterative 3-phase workflow with peer review cycle for changes needing validation (15-30 min)
Operacoes e deploy do Sr Cardoso (Cloud Run, Firestore rules/indexes, env vars, scripts, Docker). Use quando configurar ambiente, rodar deploy, revisar infra GCP ou rotinas de setup.