akaszubski/autonomous-dev
29 skills · 486 total installs
$npx skills add akaszubski/autonomous-devSkillInstalls
git-githubGit workflow and GitHub collaboration patterns including conventional commits, branch naming, PR workflow, and gh CLI usage.library-design-patternsTwo-tier design, progressive enhancement, non-blocking patterns, and security-first architecture for Python libraries.scientific-validationScientific method for validating claims with pre-registration, power analysis, statistical rigor, and Bayesian methods.api-designREST API design best practices covering versioning, error handling, pagination, and OpenAPI documentation.python-standardsPython code quality standards covering PEP 8, Black formatting, type hints, Google-style docstrings, and error handling.skill-integrationPatterns for agent skill discovery, referencing, and composition using progressive disclosure architecture.state-management-patternsJSON persistence, atomic writes, file locking, crash recovery, and state versioning patterns.code-review10-point code review checklist covering correctness, tests, error handling, type hints, naming, security, and performance.documentation-guideDocumentation standards enforcing Keep a Changelog format, README structure, ADR templates, and Google-style docstrings.semantic-validationGenAI-powered semantic validation - detects outdated docs, version mismatches, and architectural drifttesting-guideGenAI-first testing with structural assertions, congruence validation, and tier-based test structure.agent-output-formatsStandardized output formats for research, planning, implementation, and review agents. Use when generating agent outputs or parsing agent responses.api-integration-patternsSubprocess safety, GitHub CLI integration, retry logic, authentication, rate limiting, and timeout handling. Use when integrating external APIs or CLI tools.architecture-patternsFile-by-file architecture planning with ADR format, dependency ordering, and testability gates. Use when designing system architecture or creating ADRs.observabilityStructured logging, debugging (pdb/ipdb), profiling (cProfile/line_profiler), and performance monitoring.advisor-triggersDetects when user requests warrant critical analysis via /advise commandconsistency-enforcementDocumentation consistency enforcement - prevents drift between README.md and actual codebase state.project-alignmentPROJECT.md alignment patterns and validation strategiesproject-alignment-validationSemantic validation patterns for PROJECT.md alignment (GOALS, SCOPE, CONSTRAINTS, ARCHITECTURE)research-patterns4-phase research methodology: codebase recon, targeted web search, deep source analysis, and evidence synthesis.security-patternsSecurity best practices covering API key management, input validation, injection prevention, and OWASP patterns.quality-scoringMulti-dimensional data assessment for training quality evaluation including IFD scoring, factuality, and reasoning validation.debugging-workflowSystematic debugging methodology — reproduce, isolate, bisect, fix, verify. Use when diagnosing failures, tracing errors, or investigating unexpected behavior.error-handlingError handling strategy — exception hierarchies, retry patterns, circuit breakers, graceful degradation, and error boundaries.refactoring-patternsSafe refactoring techniques — extract, inline, rename, move, simplify conditionals, and decompose functions.content-allocationOne topic, one home. Routes content to its canonical store (CLAUDE.md, PROJECT.md, MEMORY.md, docs/, memory/) and audits for duplication.planning-workflow7-step planning workflow for pre-implementation design. Enforced by plan_gate hook, critiqued by plan-critic agent.prompt-engineeringPrompt engineering patterns for writing agent prompts and skill files — constraint budgets, register shifting, HARD GATE patterns, anti-personas.realign-meta-frameworkShared framework for all realignment training workflows. Provides the common pipeline template, quality thresholds, and performance optimization guidance used…