Runs a McKinsey-grade spend analysis on a transactional spend file (CSV / Excel / Coupa export). Performs schema inference, data quality assessment, normalization (supplier name…
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.
Use for writing, reviewing, debugging, or testing Python code that parses, inspects, transforms, builds, qualifies, optimizes, formats, or transpiles SQL with SQLGlot.
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…
Initialize and run a game with coordinated multi-agent architecture. Use when user wants to start a playtest, run a game, test game rules, or launch multi-agent game simulation.
Instantiates your entire company as parallel AI agents that watch, decide, and coordinate through shared state.
Apply Sun Tzu strategy as a practical subagent planning lens before choosing battles, architecture, rollout, or competitive moves.
Setup and manage Supabase PostgreSQL tables with Cube.js semantic layer definitions. Creates tables, migrations, and matching Cube models.
Bootstrap a complete Supabase schema from a domain spec — tables, RLS, triggers, indexes, seeds, type generation. Wraps erd / rls / index skills for new-project setup.
Deep allure-server code review the MODEL or the USER can invoke: routes changed files to domain-expert agents, runs the mechanical gates, checks correctness + architecture + reuse…
Comprehensive Svelte 5 assistant — component generation with runes syntax, code review, debugging, and SvelteKit patterns.
Devil's Advocate stress-testing for code, architecture, PRs, and decisions. Surfaces hidden flaws through structured adversarial analysis with metacognitive depth.
Infrastructure operations skill for monitoring servers, validating tokens, and managing backups. Triggers: /infra-status, /token-check, /backup-now
Run Tailscale inside a Kubernetes pod reliably — persistent identity, SSH host keys, RBAC, stop/start without re-registration, and API-based device cleanup.
Function-level refactor workflow using call graph tools (Epic 114). Use before changing a symbol's signature, deleting a function, or refactoring callers — maps blast radius via…
Deploy a service to the staging environment with health checks and rollback. Use when asked to deploy, push to staging, release to staging, or test a deployment.
**WORKFLOW SKILL** — Persist analysis so it survives context compression and chains between tasks. USE FOR: any task whose decisions affect future work — features, refactors,…
TBM Templateの初期セットアップを支援します。Docker Compose環境の構築、サンプルデータのロード、Grafanaダッシュボードの動作確認、トラブルシューティングを行います。「セットアップ」「環境構築」「初期設定」「docker compose up」「TBMを始めたい」「dbt…
Test-Driven Development com red-green-refactor enforced. Use quando construir feature ou fix de bug usando TDD, mencionar "red-green-refactor", quiser tracer bullets, ou pedir…
TDD Planning (Spec Anchored) - 얇은 앵커 문서(규칙 + 예제 검산표 + 미확정)를 에이전트 1회 + 사용자 리뷰 1회로 작성. --full로 3단계 풀 플로우(도메인 규칙→예시→테스트 목록).
tdd-plan에 넘길 요구사항 원천 문서(xxx-plan-input.md)를 질의응답으로 점진 작성. 주제 한 줄이나 흩어진 메모에서 시작해 범위·도메인 규칙·예제·경계 조건·미확정 사항을 채운다. "요구사항 정리", "tdd-plan 입력 문서 만들기", "TDD 시작 전 요구사항 정리" 요청 시 사용.
Test-Driven Repair — given a failing test, spawn a bounded headless `claude -p` (Read/Edit/Bash only) that makes the test pass without modifying it.
Orchestrate the backend team through a full feature implementation cycle: API design, database design, service implementation, and testing.
Start het DevOps-team voor observatie en monitoring. Health checks, CI status, infrastructure issues, DNS/SSL troubleshooting. GEEN deploys — die gaan via /team-release.
Start een Agent Team voor E2E frontend testing. Gebruik na feature development om de app via de browser te verifiëren, of voor regressietests.
Orchestrate the QA team through a full testing cycle. Coordinates qa-lead (strategy + test plan) and qa-tester (test case writing + bug reporting) to produce a complete QA package…
ADR（Architecture Decision Record）や設計書・仕様書・Runbook・ポストモーテムなどの技術ドキュメントを、 「YAML frontmatter（メタデータ）+ 固定見出し（章構成）+ 自然言語の散文（本文）」のハイブリッド構造で 新規作成・整形する。メタデータだけを機械可読にして横断検索・フィルタに使い、…
Interactive author for the architecture vision template — target, gap, migration, anti-scope, cadence.
Build and query the telemetry dashboard for Claude Code agent sessions. Session stats, tool breakdown, cost cards, and error rates from Supabase otel_events.
Import existing Azure resources into Terraform/Terragrunt state. Use when: terraform apply fails with "already exists", "resource already exists", "RoleAssignmentExists",…
Reviews test coverage quality from a behavioral perspective, identifying critical gaps and test quality issues. Does not check line coverage — checks meaningful scenario coverage.
Audit and prune a bloated test suite down to the minimum tests that hit the coverage threshold and guard real behavior.
Compare CSS extraction results between two runs or two selectors on the same page, to verify consistency and correctness
Quality review of test files and manual evidence documents. Goes beyond existence checks — evaluates assertion coverage, edge case handling, naming conventions, and evidence…
Run a live CSS extraction test against a URL and selector, verify output contains HTML, CSS, and Tailwind classes
Detect non-deterministic (flaky) tests by reading CI run logs or test result history. Aggregates pass rates per test, identifies intermittent failures, recommends quarantine or…
Generate a comprehensive Foundry/Forge test suite for a Solidity contract. Produces structured, high-coverage tests with fuzz testing, invariant testing, and fork testing…
Use when: converting review findings, identified test gaps, or unverified behaviors into a concrete, prioritized test plan with assertions, layer choice, ownership, and a…
Test how tool-gates evaluates any tool invocation (Bash, Read, Write, Edit, Glob, MCP) and show the permission decision (allow / ask / deny / defer).
**DEFAULT for WRITING OR STRENGTHENING TESTS — author missing tests with behavior contracts: coverage-targeted test additions with behavior contracts, boundary cases, and removed…
Generate a comprehensive Hardhat test suite for a Solidity contract. Produces structured, high-coverage tests following battle-tested smart contract testing methodology.
Read-only diagnostic that reports the state of a project's test suite — count vs. proportionality, coverage vs.
Generate engine-specific test helper libraries for the project's test suite. Reads existing test patterns and produces tests/helpers/ with assertion utilities, factory functions,…
Identify which tests need rerunning after a code change — traces static call graph (function-level) or import graph (module-level) to find affected test files, then emits a…
Autonomously diagnose a codebase, apply minimal fixes, and rerun tests until they pass or a real blocker is reached.
Audit how well a project proves it works against a 5-level testing maturity scale, find untested critical paths and weak tests, propose options, then split the chosen work into…
Use when a project needs testing BEYOND unit tests — fuzzing, property-based, load, E2E, or mutation.
Plan test strategies and execute test-driven development cycles, including coverage addition and test repair.
Generate a user-facing test checklist from git diff, or execute an existing test plan via Playwright.
Use when: writing, reviewing, or auditing a test (not a test plan) for quality - tests with no assertion or that cannot fail, assertions on incidental implementation detail…
Verify a released archon binary works end-to-end via a specific install path. Use when: cutting a new release, reproducing a user bug report on the released version, or validating…
Scaffold the test framework and CI/CD pipeline for the project's engine. Creates the tests/ directory structure, engine-specific test runner configuration, and GitHub Actions…
Tests a deployed, activated Power Pages site at runtime using browser-based navigation, page crawling, and API request verification via Playwright.
Agentic 시스템을 위한 TDD 전략을 수립한다. LLM 클라이언트 mock(VCR-style), golden dataset 기반 eval(최소 5건), hypothesis 기반 property-based test로 비결정성을 제어한다.
Build and test iOS apps on simulator using XcodeBuildMCP. Use after making iOS code changes, before creating a PR, or when verifying app behavior and checking for crashes — from…
Evaluates test implementation and coverage, identifying gaps, weak assertions, and untested paths. Use when auditing test quality, coverage, or testing strategy.
Designs and runs performance and load tests: workload modelling from real traffic, thresholds tied to SLOs, warmup and ramp shapes, percentile-based analysis, and lightweight CI…
Write and fix Unit, Hilt integration, and Espresso tests following MovieFinder patterns