Peer review the **new work** on the current niche/* branch (vs origin/ on a -general branch, or vs origin/niche/-general on a feature branch).
Query the codemap structural index — central, coupled, deps, rdeps, import path, symbol-level source extraction, and function-level call graph (fn-deps, fn-rdeps, fn-central,…
Check message queue status, list queues, monitor DLQ counts and consumers. Use when asked about "queues", "queue status", "DLQ", "dead letter", "consumers", "messages pending",…
Review my code, code review, is this ready to ship, check for bugs, security audit, review this PR, pre-merge check, is this safe to deploy, check code quality.
Internal reference skill loaded by audit and fix skills for version-specific Rails breaking changes and fix patterns. Not a user-facing skill — do not activate this directly.
Manage Python dependencies in Ray — add/remove/upgrade packages, work with raydepsets lock files, debug dependency conflicts, and regenerate compiled requirements.
Audit React components for unnecessary useEffect patterns. Detects 9 anti-patterns from "You Might Not Need an Effect" and proposes fixes with severity levels.
Safety analysis before refactoring -- dependency graph, test coverage, public API exposure, blast radius verdict.
Create a detailed refactor plan with tiny commits via user interview, then file as a GitHub issue RFC.
Search the Nullcost provider catalog by keyword or plain-English asks like cheap auth service, free-tier hosting, or good value Postgres.
Atomic rename of Python symbols (functions, classes, methods) or modules using the structural index. Finds all static callers, import sites, __all__ re-exports, and Sphinx…
Render an ARIS Markdown / JSON artifact (IDEA_REPORT, AUTO_REVIEW, KILL_ARGUMENT, PAPER_PLAN, research-wiki state, etc.) into a single-file HTML view designed for human reading.
Generate a comprehensive onboarding guide for any codebase. Produces a REPO_TOUR.md with a 30-second summary, annotated directory tree, Mermaid architecture diagram, key files…
Multi-agent review resolution with trust-but-verify methodology. Accepts a PR number/URL or a local code-review report file.
Reviews an architecture (file, repo, design doc, or pasted text) against scalability, security, reliability, compliance, and anti-pattern checklists plus fitness functions.
Use when checking if code follows ARCHITECTURE.md patterns - runs automated conformance checks.
Use when architecture violations were found and need automated fixing by priority.
Run the stata-reviewer agent on a do-file. Produces a structured code-review report covering reproducibility, logging, naming, magic numbers, table/figure quality, and conformance…
Orchestrates a comprehensive code review using up to 6 specialist skills. Dispatches code-review, code-simplifier, comment-analyzer, silent-failure-hunter, type-design-analyzer,…
Set the rigor level (0-10) for how critically Claude challenges your decisions. Level 0 = 'just do it bro', level 10 = full devil's advocate questioning everything.
Polish the active feature before review — code polish always; UI normalize + ship-quality pass when UI is touched.
Add a new coding/architecture rule. The user describes it in natural language (any language), the skill writes it in English structured format to the correct file.
Construct, critique, and audit arguments using the complete methodology from Weston's "A Rulebook for Arguments".
Use when the user runs /ruby-upgrade-toolkit:rules or asks to add, list, validate, show, remove, disable, enable, or explain project-specific upgrade rules — gem pins, gem swaps,…
Run the current repo's mise release pipeline, or bootstrap one if missing. Use when user wants to release, version bump, publish a package, or set up release automation for a new…
Roda, monitora e diagnostica scripts Python/notebooks na workstation. Cobre: verificar se está executando, tempo decorrido/restante, uso de GPU/CPU, escolha de GPU com menor…
Start dev server and run QA testing on a feature. Handles server setup, mode selection, and QA agent spawning with correct configuration.
Design an AUD savings-rate target with sinking funds, sub-account architecture, automation triggers, and a 12-month milestone plan.
Создание нового Python-скрипта автоматизации с docstring, argparse и регистрацией в README. Используй при добавлении скрипта валидации, синхронизации или другой автоматизации…
Обновление логики, рефакторинг или удаление Python-скрипта автоматизации. Используй при изменении поведения скрипта, добавлении новых проверок, исправлении ошибок или удалении…
Проверка Python-скрипта на соответствие стандарту — docstring, argparse, кодировка, регистрация в README.
Run GPU workloads on Modal — training, fine-tuning, inference, batch processing. Zero-config serverless: no SSH, no Docker, auto scale-to-zero.
Check service/container status, health, events, and resource usage across environments. Use when asked about "pods", "service status", "check services", "crashloop", "restart",…
GitHub intelligence for ShipGuard — scans repos for code audit, debugging, and self-improving agent techniques, then files actionable improvement proposals.
Drive an approved implementation plan to completion phase by phase, test-first, through the red→green→refactor cycle, but only for phases whose implementation does not exist yet.
Stateful, phased test-rollout orchestrator for existing products. Writes a durable phased rollout document at `context/foundation/test-plan.md` BEFORE handing off, then drives…
This skill should be used when the user asks to "optimize for Instagram", "YouTube Shorts format", "make it 9:16", "square video", "TikTok format", "Reels format", "prepare for…
Deploy and launch a feature or product. Runs a quality gate, pre-launch checklist, and executes deployment. Use when the user is ready to ship.
Define the technical approach — mechanisms, design decisions, stack direction, and component structure.
Derive technical performance criteria from the engineering blueprint. Writes goals/engineering.json with response times, reliability, coverage thresholds.
Process user feedback into investigated bug specs with root cause analysis. Triggers: 'triage feedback', 'process bug reports', 'user testing feedback'.
Generate and maintain code-anchored test case specifications. Use when setting up test coverage, reviewing what to test, or before team implementation.
Commits code changes with automated CHANGELOG and design document updates. Runs build/lint verification before commit. Use after completing a feature, bug fix, or refactoring.
Manage XML sitemaps. Use when: auditing sitemap health, generating sitemaps, or planning sitemap architecture.
Design, create, audit, and improve Claude Agent Skills with expert-level progressive disclosure. Use when building new skills, reviewing existing skills, debugging activation…
**MEASUREMENT SKILL** — Benchmark framework for measuring skill effectiveness. A/B tests agent outputs with and without a target skill, scoring correctness, completeness, and…
Interactive guide for creating new Claude skills or refactoring existing ones following Anthropic best practices.
Scaffold a starter evals/suite.yaml for a Claude Code skill. Reads description, examples, and edge-case table to seed activation, functional, and edge-case tests that satisfy the…
Cycle de vie complet des skills Claude. Creation, validation structurelle Anthropic + SkillsBench (/65), evaluation semantique (/100), pressure testing (/5).
Apply SOLID, YAGNI, DRY, and KISS principles in Kotlin/Android — SRP, OCP, LSP, ISP, DIP, avoiding premature abstraction, identifying genuine duplication, and keeping code focused…
Generate SOX sample selections, testing workpapers, and control assessments. Use when planning quarterly or annual SOX 404 testing, pulling a sample for a control (revenue, P2P,…
SPARC methodology — Specification, Pseudocode, Architecture, Refinement, Completion. Five-phase structured workflow for algo-heavy or non-trivial features where the right shape is…
Creates immutable context files and architecture documentation through spec-driven workflow with structural anti-skip enforcement.
Expert knowledge base for Claude Code Terminal — the CLI tool itself, not coding tasks. Implements 4 knowledge-retrieval phases with structural anti-skip enforcement using the…
Coordinates spec-driven development lifecycle from Epic -> Sprint -> Story -> Architecture -> Development -> QA -> Release with structural anti-skip enforcement.
Orchestrates production releases through spec-driven deployment workflow with structural anti-skip enforcement.
Spring Boot coding guidelines for REST APIs, data access, caching, and configuration. This skill covers Spring-specific patterns. For core Java, use java-coding skill.
Assess Site Reliability maturity across five dimensions — SLOs/SLIs, runbooks, on-call, postmortems, game days — with per-dimension commentary and uplift path.
Single-session driver for a multi-iteration skill-chain run. Spawns `bin/skill-chain.py --chain --loop N` as a subprocess via `bin/drive-chain.py`, watches the live event…
Mandatory Starbard Standard compliance check for all Python code. Enforces SOLID principles, explicit typing, separation of concerns, domain exceptions, testability, and Starbard…