stepanenkoviktor0110-boop/ai-dev-methodology

stepanenkoviktor0110-boop/ai-dev-methodology

Agent Claude Code

Researches codebase for a feature: files, patterns, tests, integrations, risks. Creates or deepens code-research.md. Used by user-spec-planning and tech-spec-planning.

stepanenkoviktor0110-boop/ai-dev-methodology

Agent Claude Code

Review code quality after implementation. Use after completing code tasks to verify quality standards. Proactive: invoke automatically after any code implementation.

stepanenkoviktor0110-boop/ai-dev-methodology

Agent Claude Code

Bidirectional requirements traceability: user-spec -> tech-spec/tasks and back. Detects missing requirements (gaps), unauthorized additions (scope creep), overengineering (YAGNI, unnecessary abstractions) and underengineering (missing error handling, shallow architecture). Use when: validating tech-spec completeness…

stepanenkoviktor0110-boop/ai-dev-methodology

Agent Claude Code

Reviews CI/CD pipeline and deployment configuration quality. Checks GitHub Actions workflows, deploy scripts, secrets management, platform configuration. Orchestrator specifies what to check and provides file paths.

stepanenkoviktor0110-boop/ai-dev-methodology

Agent Claude Code

Reviews project-knowledge documentation quality against documentation-writing principles. Checks for code blocks, generic content, missing operational details, duplication, bloat. Orchestrator specifies project path or uses current directory.

stepanenkoviktor0110-boop/ai-dev-methodology

Agent Claude Code

Reviews infrastructure setup quality: folder structure, pre-commit hooks, Docker config, testing setup, .gitignore security. Orchestrator specifies what to check and provides file paths.

stepanenkoviktor0110-boop/ai-dev-methodology

Agent Claude Code

Evaluates interview completeness for user-spec planning. Reviews interview data against project knowledge and code research to identify gaps and suggest questions. Use when: orchestrator reaches completeness gate after interview cycles, before creating user-spec draft.

stepanenkoviktor0110-boop/ai-dev-methodology

Agent Claude Code

Post-deploy verification agent. Executes AVP via MCP tools on live environment, verifies all acceptance criteria (user-spec + tech-spec), picks up deferred criteria from pre-deploy QA. Returns JSON report.

stepanenkoviktor0110-boop/ai-dev-methodology

Agent Claude Code

Pre-deploy acceptance testing agent. Runs test suite and verifies acceptance criteria. Returns JSON report.

stepanenkoviktor0110-boop/ai-dev-methodology

Agent Claude Code

Reviews LLM prompt quality against prompt-master principles. Checks clarity, structure, examples, compression, positive framing. Use after writing or modifying LLM prompts.

stepanenkoviktor0110-boop/ai-dev-methodology

Agent Claude Code

Validates task files against codebase reality: file/function existence, feasibility, hallucinations, basic security, TDD adequacy, implementation hints accuracy. Use when: validating task files after task-creator generates them, during /decompose-tech-spec validation phase. Not for: template compliance…

stepanenkoviktor0110-boop/ai-dev-methodology

Agent Claude Code

Comprehensive security analysis against OWASP Top 10. If given code files — audits code for vulnerabilities. If given tech-spec — reviews security decisions in architecture. Orchestrator specifies what to check and provides file paths.

stepanenkoviktor0110-boop/ai-dev-methodology

Agent Claude Code

Verifies factual claims in tech-spec or tasks against actual codebase. Detects mirages: non-existent files, functions, dependencies, patterns, name mismatches. Orchestrator specifies feature path. Agent reads documents and checks every claim in code. Use during tech-spec validation (phase 2, step 5) and task…

stepanenkoviktor0110-boop/ai-dev-methodology

Agent Claude Code

Validates skills against quality standards from skill-master. Use after creating or modifying a skill to check compliance.

stepanenkoviktor0110-boop/ai-dev-methodology

Agent Claude Code

Reads stack-researcher report files in isolated context, writes consolidated comparison table and registry entries into Project Knowledge, returns a one-line summary. Used by stack-research skill to keep the orchestrator's context window clean.

stepanenkoviktor0110-boop/ai-dev-methodology

Agent Claude Code

Researches one stack element (library, API, service, tool) against official documentation and returns a focused structured report. Used by stack-research skill inside project-planning and tech-spec-planning.

stepanenkoviktor0110-boop/ai-dev-methodology

Agent Claude Code

Creates task files from tech-spec Implementation Tasks section. Reads actual code files listed in tech-spec, discovers project knowledge, generates tasks by updated template with TDD Anchor, reviewers, skills. Use when: generating task/.md files after tech-spec is approved, during /decompose-tech-spec or manual task…

stepanenkoviktor0110-boop/ai-dev-methodology

Agent Claude Code

Validates task files against task template and task-creator rules. Reads sources of truth, checks structure, content quality, and consistency. Triggers: after task-creator generates files, on re-validation after fixes. Not for: security (security-auditor), spec coverage (completeness-validator).

stepanenkoviktor0110-boop/ai-dev-methodology

Agent Claude Code

Validates tech-spec template compliance and implementation task quality: sections present, frontmatter correct, standards compliance, verification plan, task skill correctness, task brevity, decisions placement. Security, adequacy, testing strategy, and code mirage detection handled by dedicated validators. Use before…

stepanenkoviktor0110-boop/ai-dev-methodology

Agent Claude Code

Prescriptive test quality analysis: finds problems and provides concrete fixes. Analyzes written test code, test strategy from tech-spec, or both. Orchestrator specifies what to check and provides file paths.

stepanenkoviktor0110-boop/ai-dev-methodology

Agent Claude Code

Validates user-spec for adequacy and feasibility — not document quality, but whether the proposed solution is reasonable, buildable with current stack, right-sized, and not over/under-engineered. Does not check document quality (template compliance, section completeness, acceptance criteria wording) — that is…

stepanenkoviktor0110-boop/ai-dev-methodology

Agent Claude Code

Validates user-spec quality and completeness — document structure, content coverage, acceptance criteria testability, edge cases, contradictions, and interview coverage. Scope: document quality only. Solution adequacy (feasibility, overengineering, alternatives, stack compatibility) is handled by…

stepanenkoviktor0110-boop/ai-dev-methodology

Agent Claude Code

You are a Sketch Mode interviewer. Your job is to collect just enough information to fill the 4-section sketch.md template — nothing more.