autonomous-dev

Critical thinking analysis - validates alignment, challenges assumptions, identifies risks

Check and fix CLAUDE.md alignment with codebase

Retrofit brownfield projects for autonomous development

Analyze and fix project alignment with PROJECT.md using GenAI

Unified alignment command (--project, --docs, --retrofit)

Uninstall or disable autonomous-dev plugin features with guided options

[DEPRECATED] Use /sync --env instead. Legacy environment synchronization command.

[DEPRECATED] Use /sync --marketplace instead. Legacy marketplace update command.

AST-based test coverage analysis - identifies untested code and coverage gaps

Autonomously implement a feature with full SDLC workflow

Execute multiple features sequentially (--issues <nums> or --resume <id>)

Create GitHub issue with automated research (--quick for fast mode)

Validate all plugin components are working correctly (agents, hooks, commands)

Code implementation to make tests pass

Show agent pipeline execution status for current session

Architecture and implementation planning for a feature

Research patterns and best practices for a feature

Code quality review and feedback

Security vulnerability scan and OWASP compliance check

Interactive setup wizard - analyzes tech stack, generates PROJECT.md, configures hooks

View PROJECT.md goal progress with GenAI analysis and strategic recommendations

Sync plugin files (--github default, --env, --marketplace, --plugin-dev, --all, --uninstall)

TDD test generation for a feature

Run all automated tests (unit + integration + UAT) with pytest (< 60s)

Documentation synchronization and updates

Update plugin with version detection, backup, and rollback

Manage git worktrees (--list default, --status, --review, --merge, --discard)

Critical thinking agent - validates alignment, challenges assumptions, identifies risks before decisions

Find conflicts between PROJECT.md (truth) and reality (code/docs), ask one question per conflict

Validate user requests against PROJECT.md goals, scope, and constraints

This directory contains agents that have been deprecated or replaced.

Master coordinator - validates PROJECT.md alignment and coordinates specialist agents

You are a specialized agent for analyzing existing (brownfield) codebases and planning their retrofit to align with autonomous-dev standards.

Generate descriptive commit messages following conventional commits format

Documentation sync and CHANGELOG automation

Implementation specialist - writes clean, tested code following existing patterns

Generate well-structured GitHub issue descriptions with research integration

Architecture planning and design for complex features

Generate comprehensive PR descriptions from git commits and implementation artifacts

Analyze existing codebase and generate PROJECT.md

Track and update PROJECT.md goal completion progress

Real-time project health analysis - goals progress, blockers, metrics, recommendations

Validate implementation quality against standards

Research codebase patterns and similar implementations

Research patterns and best practices for implementation

Code quality gate - reviews code for patterns, testing, documentation compliance

Security scanning and vulnerability detection - OWASP compliance checker

Intelligent setup wizard - analyzes tech stack, generates PROJECT.md, configures hooks

Smart development environment sync - detects conflicts, validates compatibility, intelligent recovery

AST-based test coverage analysis - identifies untested code and coverage gaps

Testing specialist - TDD workflow and comprehensive test coverage

Detects when user requests warrant critical analysis via /advise command

Standardized output formats for research, planning, implementation, and review agents. Use when generating agent outputs or parsing agent responses.

REST API design best practices, versioning strategies, error handling, pagination, and OpenAPI documentation. Use when designing or implementing REST APIs, HTTP endpoints, or API documentation.

API integration patterns for autonomous-dev including subprocess safety, GitHub CLI integration, retry logic, authentication, rate limiting, and timeout handling. Use when integrating external APIs or CLI tools.

This skill should be used when designing system architecture, making architectural decisions, or evaluating design patterns. It provides guidance on common patterns, ADR templates, design principles, and tradeoff analysis.

This skill should be used when reviewing code or preparing code for review. It provides guidelines for what to look for in reviews, how to write constructive feedback, and standards for review comments.

Documentation consistency enforcement - prevents drift between README.md and actual codebase state. Auto-activates when updating docs, committing changes, or working with skills/agents/commands.

Validates all documentation references - file paths, links, line numbers, code examples

Database schema design, migrations, query optimization, and ORM patterns. Use when designing database schemas, writing migrations, optimizing queries, or working with ORMs like SQLAlchemy or Django ORM.

Detects stale documentation - outdated status markers, old TODOs, version lag

Documentation standards and automation. Use when updating docs, writing guides, or synchronizing code with documentation.

Standardized error handling patterns including exception hierarchy, error message formatting, security audit logging, and graceful degradation. Use when raising exceptions, handling errors, or implementing validation.

Enforces project file organization standards from CLAUDE.md/PROJECT.md - auto-fix mode

Git best practices, commit conventions, branching strategies, and pull request workflows. Use when working with git operations, commits, branches, or PRs.

GitHub-first workflow - Issues, PRs, milestones, auto-tracking for solo developer productivity. Includes PR description templates, issue templates, automation patterns, and webhook security.

Standardized library design patterns for autonomous-dev including two-tier design, progressive enhancement, non-blocking enhancements, and security-first architecture. Use when creating or refactoring Python libraries.

Structured logging, debugging techniques (pdb/ipdb), profiling (cProfile/line_profiler), stack traces, performance monitoring, and metrics. Use when adding logging, debugging issues, or optimizing performance.

Semantic validation patterns for PROJECT.md alignment (GOALS, SCOPE, CONSTRAINTS, ARCHITECTURE)

PROJECT.md alignment patterns and validation strategies

This skill should be used when creating or updating PROJECT.md files, planning sprints, defining project goals, or managing project scope. It provides templates and best practices for PROJECT.md-first development.

Python code quality standards (PEP 8, type hints, docstrings). Use when writing Python code.

Research methodology and best practices for finding existing patterns

Security best practices, API key management, input validation. Use when handling secrets, user input, or security-sensitive code.

GenAI-powered semantic validation - detects outdated docs, version mismatches, and architectural drift

Standardized templates and patterns for integrating skills into agent prompts. Reduces token overhead through reusable skill reference syntax, action verbs, and progressive disclosure usage guidelines.

Standardized patterns for how agents discover, reference, and compose skills using progressive disclosure architecture

State persistence patterns for autonomous-dev including JSON persistence, atomic writes, file locking, crash recovery, and state versioning. Use when implementing stateful libraries or features requiring persistent state.

Test-driven development (TDD), unit/integration/UAT testing strategies, test organization, coverage requirements, and GenAI validation patterns. Use when writing tests, validating code, or ensuring quality.