Claude Skills by akaszubski

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.

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

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

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GenAI-powered semantic validation - detects outdated docs, version mismatches, and architectural drift

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.

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.

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.

Shared framework for all realignment training workflows. Provides the common pipeline template, quality thresholds, and performance optimization guidance used across all domain-specific realignment workflows.

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.

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.

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.

7-step planning workflow for pre-implementation design. Plan EXISTENCE is enforced by the plan_gate hook; the plan-critic CRITIQUE is enforced separately (unified_pre_tool's plan-exit marker gate, and the /implement STEP 5.5b verdict gate). 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.

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.

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.

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.