Run a senior-level Java/Spring backend live-coding interview practice, guiding the user with Socratic prompts, strict code review (readability, edge cases, data structures), and staged hints without giving direct answers.

Build and review production-grade web and mobile frontends using LiveKit with Next.js. Covers real-time video/audio/data communication, WebRTC connections, track management, and best practices for LiveKit React components.

Guidelines for developing modular, reusable Livewire components.

Detects common LLM coding agent artifacts in codebases. Identifies test quality issues, dead code, over-abstraction, and verbose LLM style patterns. Use when cleaning up AI-generated code or reviewing for agent-introduced cruft.

Write effective LLM prompts, commands, and agent instructions. Goal-oriented over step-prescriptive. Role + Objective + Latitude pattern. Use when writing prompts, designing agents, building Claude Code commands, or reviewing LLM instructions. Keywords: prompt engineering, agent design, command writing.

Orchestrate multiple LLMs as a council, generating collective intelligence through peer review and chairman synthesis

Expert in building production-grade streaming interfaces for LLM responses that feel instant and responsive.

Validates Stories/Tasks with GO/NO-GO verdict, Readiness Score (1-10), Penalty Points, and Anti-Hallucination verification. Auto-fixes to reach 0 points, delegates to ln-002 for docs. Use when reviewing Stories before execution or when user requests validation.

L3 Worker. Reviews task implementation for quality, code standards, test coverage. Creates [BUG] tasks for side-effect issues found outside task scope. Sets task Done or To Rework. Usually invoked by ln-400 with isolated context, can also review a specific task on user request.

Fixes tasks in To Rework and returns them to To Review. Applies reviewer feedback only for the selected task.

Runs a single Story final test task (label "tests") through implementation/execution to To Review.

Story-level quality orchestrator with 4-level Gate (PASS/CONCERNS/FAIL/WAIVED) and Quality Score. Pass 1: code quality -> regression -> manual testing. Pass 2: verify tests/coverage -> calculate NFR scores -> mark Story Done. Use when user requests quality gate for Story or when ln-400 delegates quality check.

Worker that checks DRY/KISS/YAGNI/architecture compliance with quantitative Code Quality Score. Validates architectural decisions via MCP Ref: (1) Optimality - is chosen approach the best? (2) Compliance - does it follow best practices? (3) Performance - algorithms, configs, bottlenecks. Reports issues with SEC-, PERF-, MNT-, ARCH-, BP-, OPT- prefixes.

Audit project documentation quality across 8 categories (Hierarchy, SSOT, Compactness, Requirements, Actuality, Legacy, Stack Adaptation, Semantic Content). Delegates to ln-601 for deep semantic verification of project documents. Use when documentation needs quality review, after major doc updates, or as part of ln-100-documents-pipeline. Outputs Compliance Score X/10 per category + Findings + Recommended Actions.

Audit code comments and docstrings quality across 6 categories (WHY-not-WHAT, Density, Forbidden Content, Docstrings, Actuality, Legacy). Use when code needs comment review, after major refactoring, or as part of ln-100-documents-pipeline. Outputs Compliance Score X/10 per category + Findings + Recommended Actions.

Risk-Based Value audit worker (L3). Calculates Usefulness Score = Impact (1-5) × Probability (1-5) for each test. Returns KEEP/REVIEW/REMOVE decisions based on thresholds (≥15 KEEP, 10-14 REVIEW, <10 REMOVE).

Detects unsafe training load spikes (>20-30% week-over-week) and emits safety flags. Use in nightly background jobs or when reviewing weekly training volume with conservative adjustment recommendations.

Delegate complex, multi-step codebase exploration to local Ollama models. Best for analysis, review, and understanding tasks that require reasoning across multiple files.

This skill should be used for configuring devloop project settings via .devloop/local.md, git workflow preferences, commit settings, review options

Эксперт по локальному маркетингу. Используй для гео-таргетинга, local SEO, маркетинга для офлайн-бизнеса и региональных кампаний.

Review current changes against project guidelines before PR

Route security-sensitive tasks to local LLM to prevent data exfiltration.

Local SEO dominance system for UK service businesses. FAIL/PASS enforcement. GBP + area pages + reviews.

Test local Jekyll build and visualize pages using Playwright MCP. Starts the development server, navigates through key pages, captures screenshots, and validates rendering. Use when testing local changes before deployment.

Inspect error logs quickly; use when log snippets or stack traces are mentioned.

Log recent learning to the current session.

>

Writes user-friendly logger messages in active voice for Simple History event logs. Fixes passive voice issues. Use when creating or modifying logger classes in loggers/ directory, writing getInfo() messages, fixing passive voice, reviewing log message clarity, or adding new events to the activity log.

Employs the logging module judiciously to log important events, warnings, and errors.

Guide logging practices based on Dave Cheney's minimalist philosophy. Use when adding log.Info/Debug/Error/Warn/Fatal calls, reviewing logging code, handling errors with log+return pattern, discussing log levels, or designing error handling strategies.

Autonomous multi-step work with dual-reviewer supervision (1A2A workflow) and compound engineering principles

Audit all outdated dependencies with detailed research on changelogs, breaking changes, bug fixes, and deprecations. Creates a temporary plan without updating anything. Use when you want to review what changed in your dependencies before upgrading.

This skill should be used when users need to write, review, or debug Stata code for data cleaning and analysis. Use this skill for tasks involving data import, variable management, data documentation, merging/appending datasets, creating analysis variables, and following IPA/DIME Analytics coding standards. This skill should be invoked when working with .do files, .dta files, or any Stata-related data processing tasks.

E2E development: investigate → dig → decompose → implement → test → review → PR

Capability skill — procedure for turning a known-open finding in docs/BUGS.md into a landed fix. No persona. Any agent may invoke this skill; the procedure itself enforces greenfield discipline — falsifying test first, blast-radius walk, minimal correct fix (not quick-hack), reviewer floor, spec updates. Previously architect-only to guard against quick hacks; the safeguards baked into this procedure plus GOVERNANCE §20 reviewer floor plus the skill-creator workflow make the restriction redundant as of round 29.

Validate and triage review findings of an implementation plan. Classify each finding using the unified taxonomy (FIX, FIX_UNCLEAR, ASK_USER, REJECT_FALSE_POSITIVE, REJECT_WONT_FIX, REJECT_ALREADY_FIXED). Reads the actual codebase to verify each finding against reality.

Python best practices for pentest scripts — requests sessions, error handling, output, CLI args

Write high-quality, maintainable tests for Java projects using modern best practices.

>

Review code changes for async-signal-safety violations in KSCrash crash handlers, signal handlers, and monitor code. Verifies suspect system calls by reading the actual implementation in Apple's open-source repos on github.com/apple-oss-distributions rather than guessing. Use when the user asks to review a diff/branch/PR/file for signal safety, or before landing changes that touch signal handlers, Mach exception handlers, or anything reachable from `Sources/KSCrashRecording`, `Sources/KSCrashRecordingCore`, `Sources/KSCrashBootTimeMonitor`, or `Sources/KSCrashDiscSpaceMonitor`.

Guide evaluation of healthcare AI systems with domain-specific safety criteria, clinical accuracy rubrics, and score interpretation. Use when building or reviewing health/medical AI evaluations.

plan-design-review

Fast single-pass FXA-specific commit review covering security, conventions, logic/bugs, tests, and migrations. No subagents — runs directly in the main context.

>

Create a draft pull request targeting develop. Auto-generates PR body from design files, GitHub issues, and/or commit history. Use when opening a PR.

Merge PR с pre/post проверками, sync main и cleanup. Используй при merge PR вместо ручного gh pr merge.

Full R017 verification (5+3 rounds) before commit

Review budget allocation and ROI

Monitor and report on Ralph Wiggum loop progress. Provides real-time status, iteration summaries, and progress tracking via Archon state. Use to check on running or completed loops, view iteration history, and diagnose issues.

Generates commit messages and creates commits. Use when writing commit messages, committing changes, or reviewing staged changes.