Master skill — set up the full agent harness for any repo so an agent can work it reliably: legible (map-not-manual docs + custom lints), executable (one-command dev stack), verifiable (e2e gate + a verify-before-ship loop), plus commit hygiene and entropy control. Use when onboarding a new/unfamiliar codebase to agent-driven development — "set up the harness", "make this repo agent-ready", "harness this codebase".

Use when deciding WHERE to point SEO effort, not how to write a page. Triggers: a new site or brand with no rankings and no authority ("cold start", "starting from zero", "nobody knows us"), deciding what to double down on, a page or cluster that ranks but earns nothing, hunting emerging or newly-coined keywords before competitors arrive, "should we build a cluster or one page", "what do we write next", "we get impressions but no clicks", "our traffic plateaued despite publishing", whether to chase a head term at all, or turning any of it into recurring automation. Also use when asked why an SEO effort stalled despite consistent output. NOT for writing an article, keyword expansion mechanics, or auditing a single tactic for penalty risk.

Delegate tasks to ANY CLI agent (claude, codex, aider, ...) running in a detached tmux session, with a race-safe done-signal protocol and multi-turn iteration. Use when delegating work to a non-Claude CLI agent, when the user says "tmux delegate", "run agent in tmux", "delegate to codex/aider", or when executor work should run in an observable background terminal instead of the Agent tool.

Spin up a new loop (domain) in a file-based knowledge base — bootstrap the substrate if it's missing, gather the loop's charter, scaffold domains/<loop>/README.md, then do ONE real test run and record it in the loop's Timeline and LOG.md. Use when the user says "set up a new loop", "create a domain", "start a new beat/workstream", or names a recurring job they want the agent to own.

Set up an end-to-end test suite in any repo, following practices that make e2e a reliable per-PR gate: real flows over bypass, layered assertions, a reusable auth/session helper, video+trace evidence, and a compounding suite. Use when a repo has no e2e (or weak e2e) and you want system-level tests — "set up e2e", "add end-to-end tests", "scaffold a test gate".

Scaffold a one-command `dev-local` launcher for ANY codebase. Investigates the repo to find its services, ports, and infra dependencies, then generates a single `scripts/dev-local.sh` (up/down/status/logs/restart) that runs every dev server in one tmux session, plus a short skill doc describing it. Use when someone says "set up dev-local", "make a one-command dev launcher", "I want one script to start this repo", "scaffold dev-local for this project".

Scaffold an isolated CLOUD dev box per agent (via crabbox + Daytona) for any codebase — the parallel-safe counterpart to dev-local-setup. Each agent gets its own full stack (own DB + dev server) and an in-box browser for e2e, so concurrent loops never collide on ports/state. Sets up the snapshot image, .crabbox.yaml, an idempotent setup.sh (also boots the stack locally), and a cbx.sh wrapper. Use when the user says "set up crabbox", "give each agent its own box", "add cloud testing", "make this repo testable in the cloud / on Daytona", "parallel-test this", or when setup-codebase-harness needs true per-agent isolation.

Audit a repo's agent context — CLAUDE.md files, codebase docs, skills, and tool/MCP designs — against Anthropic's Claude 5 context-engineering guidance ("unhobbling": Anthropic cut ~80% of Claude Code's system prompt with no eval loss). Finds overconstraint, conflicting instructions, redundancy, stale facts, and missing "unknown knowns"; produces a scored findings report with concrete rewrites, then applies approved fixes. Use when someone says "audit my CLAUDE.md", "context audit", "unhobble this repo", "review our agent docs/skills/tools", or after upgrading to Claude 5-generation models.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

IMMEDIATELY USE THIS SKILL before answering any task - internal design thinking that identifies the question type, selects applicable skills, and converges on the best approach before implementation

Comprehensive guide for developing WebGPU-enabled Three.js applications using TSL (Three.js Shading Language). Covers WebGPU renderer setup, TSL syntax and node materials, compute shaders, post-processing effects, and WGSL integration. Use this skill when working with Three.js WebGPU, TSL shaders, node materials, or GPU compute in Three.js.

Registers node major version vanity URL in the sibling vanity repo

Generates CHANGELOG.md entries for upgrade versions found in upgrades/software/ by parsing init.go and upgrade.go

Set up development environment by loading direnv. Must be run before any make targets (tests, builds, linting).

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.

Reference for OrangeHRM's service layer — the `*/Service/<Name>Service.php` classes that sit between Endpoints/Controllers and DAOs and hold business logic, the `*ServiceTrait` DI access pattern, the lazy-getter convention for composing services, where to register services in `PluginConfigurationInterface::initialize()`, and what belongs in a service vs in a DAO vs on an entity Decorator. Use whenever the user is adding a service method, deciding where business logic should live, composing one service from another, or asking "is there already a service for X?" Companion to `daos` (the layer services call into), `rest-endpoints` (the layer that calls services), `entities` (the Decorator alternative for entity-bound logic).

Reference for OrangeHRM's task scheduling — the `orangehrm:run-schedule` command that operators run from system cron (every minute), the `SchedulerConfigurationInterface` that plugins implement to register tasks at framework boot, the `Schedule` / `Task` / `CommandInfo` value objects (Task extends `Crunz\Event`, so all Crunz fluent scheduling methods like `->cron()`, `->everyMinute()`, `->hourly()`, `->daily()`, `->weekdays()`, `->between()`, etc. are available), and the `TaskSchedulerLog` entity that records every task execution. Use whenever the user is adding a recurring background task, wiring up cron, debugging a job that should have run but didn't, or asking about setting up the host-level cron entry. Companion to `console-commands` (scheduled jobs are console commands underneath), `events` (the same plugin-config-implements-interface pattern), `mail` (a common scheduled task is draining queued emails on hosts where it can't happen via TERMINATE).

Reference for OrangeHRM's REST API v2 input validation — `ParamRule`, `ParamRuleCollection`, `Rule`, the `Rules::*` constant catalog (OrangeHRM custom rules + Respect/Validation rules), the `ValidationDecorator` for required/not-required wrapping, composite rules (ALL_OF / ANY_OF / ONE_OF / NONE_OF), and writing custom rule classes. Use whenever the user is writing or editing a `getValidationRuleFor*()` method on an Endpoint, debugging a 422 "Invalid parameter" response, asking which rule exists for a check, writing a new `Rules\Foo` class, or wondering why a required-looking field passes empty-string. Companion to the `rest-endpoints` skill which covers the Endpoint dispatch flow.

Reference for shaping OrangeHRM REST API v2 responses — the `Normalizable` + `ModelTrait` contract, writing a Model class that maps a Doctrine entity to a JSON object, the `filter` array (getter chain — supports nested-getter sequences for related entities), the `attributeNames` array (output JSON keys), `EndpointResourceResult` vs `EndpointCollectionResult`, the `ParameterBag` meta envelope, generic non-entity models (`ArrayModel`, `ArrayCollectionModel`), and the `MODEL_MAP` pattern for `?model=default|detailed` variants. Use whenever the user is writing or editing a Model class, picking which `EndpointResult` to return, debugging "why is field X missing/null in the JSON response", adding a detailed-vs-default model variant, or returning an ad-hoc payload that doesn't come from an entity. Companion to `rest-endpoints` (the dispatch spine) and `rest-openapi` (Model classes carry `@OA\Schema`).

Reference for OrangeHRM's OpenAPI v3 annotations via zircote/swagger-php — what to add to Endpoint methods and Model classes, the project's shared component refs (RecordNotFound, ForbiddenResponse, sortOrder, limit, offset), how class constants are used inside annotations, and the `generate-open-api-doc` command. Use whenever the user is annotating a new endpoint, debugging a `generate-open-api-doc --throw` failure in CI, asking which `#/components/…` ref to use, or referencing constants inside `@OA\*` blocks. **CI enforces this** — the `Lint` workflow runs `generate-open-api-doc --throw`, so a PR without proper annotations fails the build. Companion to `rest-endpoints` (where the annotations live, on handler methods) and `rest-serialization` (where Model `@OA\Schema` blocks live).