pjlib

Remove AI-generated code slop by comparing current branch against base branch and eliminating unnecessary comments, defensive bloat, type workarounds, and style inconsistencies. Use this skill when reviewing AI-generated code, before merging PRs, when code quality seems degraded, or when you notice AI tells like excessive comments or defensive checks. Trigger for phrases like "remove slop", "clean AI code", "remove unnecessary code", "fix code quality", or when diff shows obvious AI-generated patterns.

Expert BAML (BoundaryML) schema design, code review, and test generation following established standards and conventions. Use this whenever users mention BAML, want to design AI functions, create schemas for LLM interactions, generate test cases, or review existing BAML code. Covers class/function/enum design, client configuration, prompt engineering, and comprehensive testing patterns.

Audit Claude Code agents, skills, commands, and hooks for quality, completeness, and adherence to templates and best practices. Use this skill when reviewing workspace components, ensuring quality standards, preparing for deployment, or investigating component issues. Trigger for phrases like "audit components", "check agents", "review skills", "validate commands", or proactively before major releases or when onboarding new components.

Comprehensive helper for working with the DevLoop development observability tool - both using it to analyze development patterns and contributing to its development. Use when running DevLoop commands, interpreting council mode analysis, understanding git activity patterns, reviewing Claude Code sessions, or working on DevLoop's hexagonal architecture codebase. Trigger for phrases like "run devloop", "analyze branch", "council mode", "development patterns", or when working on the DevLoop Rust codebase itself.

Remove emojis from project files and replace them with text equivalents. Use this skill when the user mentions removing emojis, cleaning up documentation, code review mentions emoji issues, or when you notice emojis in files that should be emoji-free. Also trigger for phrases like "clean emojis", "no emojis", "remove emoji", or "emoji cleanup".

Guide automated git bisect sessions to find regression commits with smart test execution and commit analysis. Use this skill when tracking down bugs introduced by specific commits, finding when tests started failing, debugging performance regressions, or investigating when features broke. Trigger for phrases like "find the bad commit", "when did this break", "bisect", "regression hunt", or when the user needs to identify which commit introduced an issue.

Automatically clean up merged branches, stale remotes, and organize repository structure. Use this skill when you notice merged branches, stale remote-tracking branches, cluttered branch lists, or when completing feature work. Trigger for phrases like "clean up branches", "delete merged branches", "prune remotes", "organize git", or when branch count exceeds 10-15 active branches. Also activate proactively after PR merges or when git branch output shows many [gone] references.

Navigate and understand minibox codebase architecture

Build, test, and debug workflows for minibox container runtime

Run and debug containers with minibox runtime operations

Development environment setup for minibox container runtime

Infrastructure for running parallel agent tests with automatic metric collection, programmatic grading, and benchmark aggregation. Use this skill when the user wants to A/B test different approaches, compare agent configurations, benchmark performance improvements, run parallel experiments, or test multiple variations of a prompt or implementation. Trigger for phrases like "test in parallel", "compare approaches", "benchmark", "A/B test", "run experiments", or when the user wants to collect timing/token metrics from multiple agent runs.

Coordinated multi-agent workflow for comprehensive Rust development with parallel architecture review, optimization scanning, and test engineering. Use when starting new Rust features, reviewing architecture changes before PR submission, conducting code quality assessments, or setting up testing infrastructure. Triggers parallel execution of architect-reviewer, rust-optimization-scanner, and test-engineer agents for maximum efficiency.

Automated Rust testing workflow that runs tests, analyzes failures using pattern matching, suggests fixes based on common Rust idioms, and re-runs to verify. Use after writing new Rust code, when fixing failing tests in CI/CD, during TDD cycles, debugging async/tokio runtime issues, or fixing type mismatches and borrow checker errors. Detects patterns like missing tokio test attributes, type mismatches, borrow checker conflicts, and assertion failures.

Comprehensive security infrastructure patterns including zero-trust architecture, compliance automation (SOC2/PCI-DSS), infrastructure as code security baselines, threat monitoring, and incident response automation. Use when implementing security controls, automating compliance, setting up security monitoring, or responding to security incidents.

Identify, quantify, and prioritize technical debt in software projects with actionable remediation plans. Use this skill when reviewing codebases, planning refactoring work, analyzing slow development velocity, investigating bug patterns, or preparing technical roadmaps. Trigger for phrases like "technical debt", "code quality issues", "refactoring needs", "maintenance burden", or when velocity metrics show degradation.

Comprehensive test automation patterns including test suite architecture, unit/integration/E2E testing frameworks, performance testing, CI/CD integration, and quality metrics. Use when implementing test strategies, setting up test automation, configuring test frameworks, or establishing quality gates.