autonomous-dev

GenAI-first testing with structural assertions, congruence validation, and tier-based test structure. Use when writing tests, setting up test infrastructure, or validating coverage. TRIGGER when: test, pytest, coverage, TDD, test patterns, congruence, validation. DO NOT TRIGGER when: production code implementation, documentation, config-only changes.

One topic, one home. Routes content to its canonical store (CLAUDE.md, PROJECT.md, MEMORY.md, docs/, memory/) and audits for duplication. TRIGGER when: auditing CLAUDE.md/PROJECT.md/MEMORY.md sizes, deduplicating docs, applying the content-allocation pattern to a new repo, running /align --content. DO NOT TRIGGER when: implementing features, writing tests, routine code edits, debugging.

Prompt engineering patterns for writing agent prompts and skill files — constraint budgets, register shifting, HARD GATE patterns, anti-personas. Use when writing or reviewing agents/*.md or skills/*/SKILL.md. TRIGGER when: agent prompt, skill file, prompt engineering, model-tier compensation, HARD GATE, prompt quality. DO NOT TRIGGER when: user-facing docs, README, CHANGELOG, config files.

7-step planning workflow for pre-implementation design. Enforced by plan_gate hook, critiqued by plan-critic agent. Use when creating plans, design documents, or architecture decisions before implementation. TRIGGER when: plan, planning, /plan, design document, architecture decision. DO NOT TRIGGER when: implementation, coding, testing.

Structured logging, debugging (pdb/ipdb), profiling (cProfile/line_profiler), and performance monitoring. Use when adding logging, debugging issues, or optimizing performance. TRIGGER when: logging, debug, profiling, performance monitoring, metrics, stack trace. DO NOT TRIGGER when: feature implementation, testing, documentation, config changes.

10-point code review checklist covering correctness, tests, error handling, type hints, naming, security, and performance. Use when reviewing PRs or evaluating code quality. TRIGGER when: code review, PR review, review checklist, code quality check. DO NOT TRIGGER when: writing new code, debugging, refactoring without review context.

REST API design best practices covering versioning, error handling, pagination, and OpenAPI documentation. Use when designing or implementing REST APIs or HTTP endpoints. TRIGGER when: API design, REST endpoint, HTTP route, OpenAPI, swagger, pagination. DO NOT TRIGGER when: internal library code, CLI tools, non-HTTP interfaces.

Subprocess safety, GitHub CLI integration, retry logic, authentication, rate limiting, and timeout handling. Use when integrating external APIs or CLI tools. TRIGGER when: subprocess, gh cli, API call, retry logic, rate limiting, authentication. DO NOT TRIGGER when: internal function calls, pure Python logic, config file edits.

File-by-file architecture planning with ADR format, dependency ordering, and testability gates. Use when designing system architecture or creating ADRs. TRIGGER when: architecture plan, system design, ADR, file breakdown, component design. DO NOT TRIGGER when: simple config edits, single-file bug fixes, documentation-only changes.

Multi-dimensional data assessment for training quality evaluation including IFD scoring, factuality, and reasoning validation. Use when scoring training data or evaluating dataset quality. TRIGGER when: quality scoring, data assessment, IFD, factuality, training data quality. DO NOT TRIGGER when: code quality, test coverage, documentation, non-data tasks.

Patterns for agent skill discovery, referencing, and composition using progressive disclosure architecture. Use when building agents, composing skills, or optimizing context usage. TRIGGER when: skill discovery, agent integration, skill composition, progressive disclosure. DO NOT TRIGGER when: implementing features, writing tests, documentation-only changes.

Systematic debugging methodology — reproduce, isolate, bisect, fix, verify. Use when diagnosing failures, tracing errors, or investigating unexpected behavior. TRIGGER when: debug, error, traceback, stack trace, bisect, breakpoint, failing test, unexpected behavior. DO NOT TRIGGER when: writing new features, code review, documentation, refactoring.

Documentation standards enforcing Keep a Changelog format, README structure, ADR templates, and Google-style docstrings. Use when writing CHANGELOG entries, updating READMEs, or documenting APIs. TRIGGER when: changelog, readme, documentation, docstring, ADR, API docs. DO NOT TRIGGER when: code-only changes, test files, config updates without API changes.

Error handling strategy — exception hierarchies, retry patterns, circuit breakers, graceful degradation, and error boundaries. Use when designing error handling, implementing retries, or building resilient systems. TRIGGER when: error handling, exception, retry, circuit breaker, fallback, graceful degradation, resilience. DO NOT TRIGGER when: writing tests, documentation, config changes, simple bug fixes.

Git workflow and GitHub collaboration patterns including conventional commits, branch naming, PR workflow, and gh CLI usage. Use when creating commits, branches, or pull requests. TRIGGER when: git commit, branch, PR, pull request, merge, gh cli. DO NOT TRIGGER when: code implementation, testing, documentation without git operations.

Two-tier design, progressive enhancement, non-blocking patterns, and security-first architecture for Python libraries. Use when creating or refactoring Python libraries. TRIGGER when: library design, module architecture, reusable component, two-tier. DO NOT TRIGGER when: simple scripts, config files, documentation-only changes.

Python code quality standards covering PEP 8, Black formatting, type hints, Google-style docstrings, and error handling. Use when writing or reviewing Python code. TRIGGER when: python, formatting, type hints, docstrings, PEP 8, black, isort. DO NOT TRIGGER when: non-Python files, markdown, config, shell scripts.

Safe refactoring techniques — extract, inline, rename, move, simplify conditionals, and decompose functions. Use when restructuring code without changing behavior. TRIGGER when: refactor, extract method, rename, inline, simplify, decompose, clean up, code smell. DO NOT TRIGGER when: adding features, fixing bugs, writing tests, documentation.

4-phase research methodology: codebase recon, targeted web search, deep source analysis, and evidence synthesis. Use when investigating patterns, evaluating libraries, or analyzing best practices. TRIGGER when: research, investigate, evaluate options, compare libraries. DO NOT TRIGGER when: implementation tasks, bug fixes, routine code changes.

Scientific method for validating claims with pre-registration, power analysis, statistical rigor, and Bayesian methods. Use when testing hypotheses, running experiments, or validating claims from papers. TRIGGER when: validate, hypothesis, experiment, backtest, evidence, statistical test. DO NOT TRIGGER when: routine coding, config changes, documentation, non-experimental tasks.

Security best practices covering API key management, input validation, injection prevention, and OWASP patterns. Use when handling secrets, user input, or security-sensitive code. TRIGGER when: security, API key, secret, input validation, injection, OWASP. DO NOT TRIGGER when: non-security code, styling, documentation, test scaffolding.

JSON persistence, atomic writes, file locking, crash recovery, and state versioning patterns. Use when implementing stateful libraries or features requiring persistent state. TRIGGER when: state persistence, atomic write, file locking, crash recovery, checkpoint. DO NOT TRIGGER when: stateless utilities, pure functions, config reads, documentation.

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.

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.

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

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

PROJECT.md alignment patterns and validation strategies