slopsentral

Design OpenAPI component schemas with discriminated variants, constrained primitives, subtype/composition choices, nullability, examples, and invalid-state prevention.

Set up a repository for marketplace-driven AI tooling. Use when onboarding a new repo, refreshing a checked-in marketplace reference, installing core marketplace plugins, or documenting which configured marketplaces should be available by default.

Use when validation, authorization, normalization, or state checks produce facts later code must retain. Replace primitive contracts, flags, sentinel states, string protocols, and call-order conventions with proof-carrying values in any language.

Use when Kotlin work needs type-driven modeling, parse-dont-validate boundaries, semantic package layout, explicit failures, API review, or package cohesion checks.

Pkl engineering for typed configuration contracts, expressions, amendments, evaluation, formatting, tests, projects, dependencies, rendering, and packages. Use when a repository contains `.pkl` modules or `PklProject`, or when configuration behavior should be modeled and enforced with Apple Pkl.

Use when creating or validating referential plugin manifests, marketplace entries, primitive references, or payload-to-reference plugin conversions.

Use when a behavior, invariant, bug fix, contract, or refactor should be developed red-green-refactor and any shell-invokable check can provide focused executable proof.

Use when Kotlin work needs typed design discipline, invariant-oriented Kotlin standards, filesystem-backed evidence, Kast semantic tooling, Gradle validation, TDD, or PR-ready proof.

Route Pkl design work to concise best-practice and advanced-pattern reference catalogs. Use when choosing a Pkl modeling pattern, reviewing configuration design, or looking for versioned official examples without loading a large monolithic skill.

Model Pkl specifications, resources, imports, packages, and provenance, and locate authoritative Pkl documentation or repository content. Use when defining configuration schemas, resource boundaries, source maps, or first-party research inputs.

Set up and diagnose Pkl CLI, language-server, editor, formatter, renderer, documentation, code-generation, and build tooling. Use when installing Pkl, configuring an LSP or editor, choosing JSON/YAML output, or checking local readiness.

Use when creating or revising standalone agent profiles, including frontmatter, triggers, prompts, tool limits, examples, and delegation checks.

Use when authoring hook primitives, provider adapters, executable hook scripts, plugin wiring, dependency checks, or repo-local hook validation.

Use when explicitly asked to create or refresh local repo maps such as AGENTS.local.md, OUTDATED.local.md, or generated navigation summaries.

Use when auditing skills, agents, hooks, concepts, plugin manifests, runtime links, promotion readiness, provenance, or cleanup safety.

Use when routing evals, missed triggers, wrong primitive loads, bypassed skills, session evidence, or trigger-description tuning need diagnosis.

Use when explicitly asked to map repo instruction boundaries, split AGENTS.md guidance, or document generated/manual edit surfaces.

Use when creating, revising, consolidating, or evaluating reusable skills, including triggers, references, scripts, overlap checks, and promotion.

Use when consolidating scattered skills, agents, hooks, concepts, instructions, plugin manifests, promotion records, duplicate queues, or provenance.

Use when JSON Schema assets need authoring, extraction, validation, lifecycle changes, discriminator policy, examples, or validator-backed contract checks.

Author or revise OpenAPI specifications with schema-driven operation contracts, invariant-filled component schemas, typed errors, examples, and validation/generation evidence.

Rate or review OpenAPI specifications against type-driven and schema-driven criteria, with evidence-backed findings, scorecards, validation notes, and concrete contract-strengthening fixes.

Create, refresh, and impact-check OKF knowledge bundles for Kotlin/Gradle codebases with source-backed Markdown concept documents. Use when docs should be generated from concrete repository facts, linked to code evidence, and kept current without a provider-specific data store.

Guide users through a structured workflow for shaping documentation, proposals, technical specs, decision docs, RFCs, and other agent-readable reference material. Use when the user wants to write, revise, organize, or reader-test a substantial document with a local non-first-party skill name.

Create or maintain compact repository signature indexes that help agents route source reads, back OKF concept documents, and understand documentation impact without opening every file. Use when a codebase needs generated type or symbol summaries, JVM fully qualified names, deterministic source maps, knowledge-base backing, or drift checks for signature-level documentation.

Create, revise, or restructure technical documentation sites that use MkDocs, Zensical, Material-style Markdown features, or similar docs-as-code navigation. Use when documentation work needs site config awareness, page structure, nav updates, generated-doc boundaries, or consistent prose across docs pages.

Use when the user asks to create, refine, or measure a concrete goal before work begins, especially with the goal tool.

Use when local Git work needs status inspection, user-work protection, safe branching, diff review, staging, commits, recovery, or publication prep.

Use when GitHub Actions, PR checks, workflow YAML, dispatches, caches, artifacts, secrets, permissions, release pipelines, or CI logs need repair.

Use when work needs a branch, commit, push, PR, draft/ready transition, check babysitting, CI repair, merge handoff, or PR evidence.

Write, review, or harden Bash and shell automation used by hooks, CI, release scripts, installers, and local developer tooling. Use when shell scripts need predictable failure handling, quoting, dry-run boundaries, temporary-file cleanup, argument parsing, or safer destructive-operation guardrails.

Iterate on Kotlin, JVM, and Gradle projects with structured build evidence. Use when running Gradle tasks, fixing failing tests, reading JUnit or JaCoCo reports, diagnosing Kotlin compilation or incremental-build problems, improving coverage, or getting a Kotlin/Gradle build green.

Use when reviewing Kotlin diffs, PRs, or changed files for type safety, parse-dont-validate boundaries, package cohesion, duplication, primitive traps, or expected failures.

Use when Kotlin work must prove an architectural invariant by demonstrating a currently representable invalid state or operation, then moving enforcement into the Kotlin type system so that misuse is no longer reachable.

Refactor existing knowledge into an Open Knowledge Format (OKF) bundle — convert loose notes, docs, READMEs, wikis, or a catalog/metadata export into markdown concept files with YAML frontmatter, index.md, and a knowledge graph. Use when migrating existing knowledge to OKF, normalizing a notes folder, or exporting a catalog to OKF.

Build self-contained Claude-compatible HTML artifact bundles from React/Vite projects. Use when the requested deliverable must be bundled into one shareable HTML file, especially for stateful or multi-component artifacts. Use frontend-design for general web UI/product design; use this skill for scaffold, shadcn component setup, bundling, and artifact handoff mechanics.

Migrate supported instruction files, skills, agents, and MCP config into Codex project and global files.

Design and scaffold composable CLIs that let agents discover, resolve, read, inspect, and safely mutate external systems through stable commands and JSON output. Use when turning an API, SDK, admin tool, logs source, or web workflow into an agent-usable command-line surface.

Create, read, maintain, and visualize Open Knowledge Format (OKF) bundles — directory trees of Markdown "concept" files with YAML frontmatter that link into a knowledge graph. Triggers on `/okf` (and `/okf init|update|query|validate|viz`). Use when asked to capture a project's knowledge as OKF, keep an okf/ bundle in sync after changes, navigate a bundle to answer a question, or when a folder of .md files carries a `type:` frontmatter field (the Google Cloud Open Knowledge Format).

Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.