saschb2b

@saschb2b source repo

24 skills
0 followers
6 hours ago last updated

▌
Okf · saschb2b bundle
Create, inspect, retrieve, author, revise, enrich, audit, repair, research, analyze change impact, migrate, validate, and maintain knowledge for AI agents as conformant Open Knowledge Format (OKF) bundles. Use for /okf commands; work on an existing OKF bundle; documentation of tables, datasets, views, metrics, runbooks, playbooks, APIs, schemas, or join paths; exports from catalogs, metadata, websites, URLs, or source code; and any knowledge an agent will read later. Apply implicitly when editing an OKF bundle so conformance, provenance and sources, generated and verified trust signals, freshness, log.md, indexes, and cross-links remain current. Tracks OKF v0.2, including attested computations and migration from v0.1.

0
installs
▌
Odsf · saschb2b bundle
Author, validate, and maintain a design system for AI agents as a conformant Open Design System Format (ODSF) bundle, a profile (v0.2) of Open Knowledge Format v0.2 that adds design tokens, runnable HTML/CSS example assets, wireframe views, and design-oriented concept types. Commands init, add, token, asset, edit, enrich, link, index, log, validate, export, migrate, consume. Use when the user types /odsf or asks to package a design system for an agent, document design tokens, components, patterns, behaviors, or guidelines so an agent builds UI that matches it, capture a component's skeleton or wireframe (layout, spacing, order, hierarchy, responsive reflow), make a design system or component library agent-readable or portable, adopt or migrate an OKF bundle, project tokens to CSS variables, or follow the ODSF spec. Apply implicitly whenever you write or transform design-system knowledge an agent will build from (a token scale, a component spec), and whenever you edit an existing ODSF bundle.

0
installs
▌
Godot · saschb2b bundle
Godot game engine development skill, a dated snapshot tracking the current stable Godot (4.x, currently 4.7). Covers GDScript static typing and syntax, scene and node architecture, the resource system, signals, autoloads, the SceneTree and lifecycle, physics and movement, collision and raycasts, input, math and vectors, navigation and pathfinding, TileMapLayer, UI and Control nodes, animation and tweens, audio, shaders, particles, saving and persistence, performance, testing, multiplayer, the editor and CLI workflow, the .tscn/.tres/project.godot text formats, and version-specific pitfalls and breaking changes. Use when working on any Godot project, whether writing GDScript, creating or editing scenes and resources, configuring project.godot, building game systems, or debugging Godot-specific issues. Triggers on any Godot game development task. Check the project's Godot version first; this snapshot ages, so verify version-specific claims against the official docs when the snapshot date looks old.

0
installs
▌
Ask UX · saschb2b bundle
Force UX questioning before any UI work, refactor, or redesign. Use when the user asks to design, redesign, restyle, polish, "fix", or "make nicer" a screen, component, page, or flow. Also use when the user describes a problem in UI terms ("the button is hard to find", "this form is confusing", "this page is ugly") and is about to reach for a visual fix, since most UI-shaped complaints have UX-shaped causes.

0
installs
▌
No Slop · saschb2b bundle
Write and revise human-facing prose in a plain, professional register, stripping the tells that mark text as AI-generated. Works top down. First restructure the document (reorder, merge, split, delete, or replace sections and generated scaffold), then rebuild paragraphs and sentences with ASD-STE100 Simplified Technical English and the mechanics adopted from the Microsoft Writing Style Guide, then kill word-level tells and check with a bundled linter. Use when writing or editing a README, blog post, doc, PR or commit message, email, release note, changelog, error message, runbook, or any copy a person will read. Also use when asked to make text sound less like AI, remove AI slop, restructure or de-bloat a doc, cut the marketing voice, write plain or controlled technical English, fix over-structuring or list-itis, make wording inclusive or accessible, tighten or professionalize a draft, or to review prose you just generated. Extends to comments, commits, PRs, test names, error and log strings, and formatting.

0
installs
▌
To Story · saschb2b bundle
Reshape a draft ticket, Jira issue, or GitHub issue from an engineer's braindump into a real user story with INVEST-clean acceptance criteria, and split stories that are too large using SPIDR. Use when the user wants to write, refine, review, sharpen, or split a ticket / story / issue, or when they share a draft that reads like a note-to-self (commit hashes, file paths, "see Slack thread", no user in sight).

0
installs
▌
MCP Server · saschb2b bundle
Build, extend, and maintain a Model Context Protocol (MCP) server across its whole lifecycle against the current spec and official SDKs. Covers the architecture, choosing a transport (stdio vs Streamable HTTP), writing tool definitions agents actually use, adding tools without breaking existing agents, versioning and deprecation, the security threat model (tool poisoning, token passthrough, prompt injection, OAuth), testing with the MCP Inspector, and publishing to the registry. Use when building an MCP server, exposing a CLI, API, or app to AI agents (Claude Code, Cursor, Cline, Windsurf), adding or reviewing MCP tools, fixing an agent that calls the wrong tool or loads too many, securing or authorizing an MCP server, migrating transports, or shipping and versioning one. Also for any new agent-tool integration where the target has a scripting API, CLI, or HTTP surface.

0
installs
▌
Trust Card · saschb2b bundle
Generate, sign, attest, and verify holistic trust cards for OKF knowledge bundles and agent skills. A card binds content, artifact, and capability provenance into one OKF concept and renders a graded trust gradient instead of a binary "verified" badge, and can be drawn as a shareable SVG book cover. Use this skill whenever the user wants to make a skill card, trust card, or provenance card; render or visualize a card; sign or attest a bundle or skill; prove a bundle is unaltered; declare or check a permission/capability manifest; or decide whether a skill or knowledge bundle is safe to load, even if they only say "card", "sign it", "is this skill trustworthy", or "verify this bundle".

0
installs
▌
Autopilot · saschb2b bundle
Work autonomously on a project without waiting for direction. On command, survey the codebase, pick one high-value low-risk improvement, do it, verify it, commit it, then pick the next, looping like a self-directed intern. Use when the user hands off open-endedly ("work on your own", "keep improving this", "find something worth doing", "don't wait for me", "go autonomous", "run for a while", "be a passionate intern", "do whatever you think is valuable") or invokes /autopilot, and you have to choose the work yourself rather than wait for instructions or feedback.

0
installs
▌
Codegen API · saschb2b bundle
Set up typesafe API code generation in 2026, preferring framework-agnostic options factories over generated hooks. Walks the decision matrix for REST (OpenAPI via hey-api) and GraphQL (graphql-codegen client preset, gql.tada), wires the minimal config for the chosen stack, and uses fragment masking for component composition. Use when starting an API integration, wiring an OpenAPI spec into a frontend, setting up GraphQL types, asked about useQuery, queryOptions, TypedDocumentNode, or fragment masking, or when seeing legacy patterns like generated useGetX hooks, per-query prop types, or @graphql-codegen/typescript-react-apollo. Counterweight to LLM training corpora that mostly reflect the pre-2024 hooks pattern, biasing default output toward generated hooks.

0
installs
▌
Test Stinky · saschb2b bundle
Detect test-suite quality smells in any language or framework, explain the cost of each, and propose a fix with a source link. A counterweight to agents that blindly chase coverage and ship huge, slow, flaky suites. Covers test intent and naming, assertions (assertion-free, weak, tautological, snapshot-everything), fixtures and duplication (DAMP over DRY, mystery guests, logic in tests), test doubles (over-mocking, mock drift), determinism (time, randomness, order, shared state, hermeticity), async waiting (sleeps vs condition waits), speed and cost (inverted pyramid, redundant layers), coverage theater, and lifecycle hygiene (skipped-test rot, retries as policy, green-by-rerun), plus a suite-level shape pass with a slimming plan and a mechanical gate stack. Use when reviewing or writing tests, auditing, slimming, or speeding up a test suite, hunting flaky or slow tests, or asked to sniff, smell-check, or clean up specs or a test folder. Defers production-code smells to react-stinky and tauri-stinky.

0
installs
▌
Fable Mode · saschb2b bundle
Adopt the structural operating discipline of Anthropic's Fable model in whatever agent harness is running, so the host model (GPT 5.6, Gemini, or any coding agent) orients, parallelizes, delegates, verifies, and reports the way Fable does. Ships the doctrine as a vendored OKF bundle; the operating loop, parallel dispatch, delegation economy, orchestration patterns, verification gates, faithful reporting, the irreversibility gate, context economy, tool and code conduct, memory discipline, trust boundaries against prompt injection, a harness-mapping runbook, and a delta map against the leaked GPT 5.6 system prompt. Use when the user asks the agent to behave or think like Fable or Claude, act more structurally like Fable, enter fable mode, work like an Anthropic agent, tighten agentic workflow discipline, batch tool calls, verify before claiming done, stop narrating and start acting, or invokes /fable-mode. This changes how work is executed; choosing the work autonomously stays with autopilot.

0
installs
▌
React Stinky · saschb2b bundle
Detect React and TypeScript maintainability smells across the whole component, hook, and module, explain the cost of each, and propose a fix with a source link. Covers prop and API design (naming, booleans, callbacks, variants, controlled state, generics, refs, styling, JSDoc), state and data flow (redundant state, stale closures, context and ref misuse), effects and lifecycle, component structure and hooks, rendering correctness (keys, mutation, impure renders, hydration, the leaked 0 from &&), accessibility and focus management, async handlers, error boundaries, unsafe HTML, TypeScript discipline (any, casts, untyped catch, exhaustiveness), and a cross-file duplication pass. Defers memoization and re-render performance to react-compiler and color literals to theme-colors. Use when reviewing or writing React components or hooks, auditing for maintainability, or asked to sniff, smell-check, lint, or clean up a codebase, folder, file, or pasted snippet. Respects native HTML attributes and library conventions.

0
installs
▌
Tauri Stinky · saschb2b bundle
Detect Rust and Tauri maintainability smells across the backend crate, the IPC boundary, and the app shell, explain the cost of each, and propose a fix with a source link. Covers Rust discipline (error handling and panics, ownership and clones, type design, module structure, async correctness, overgeneration and dead code, unsafe and lint hygiene, testing) and the Tauri layer (command design, managed state, events vs channels, capabilities and security, IPC contract and type codegen, config and build footprint), plus a cross-boundary contract audit and a mechanical gate stack (fmt, clippy, test, audit, deny, machete). Use when reviewing or writing Rust code or a Tauri app, auditing src-tauri, setting up quality gates or CI lints for Rust, or asked to sniff, smell-check, lint, or clean up a Rust or Tauri codebase, crate, command, or pasted snippet. Defers React component and hook smells to react-stinky and color literals to theme-colors.

0
installs
▌
Theme Colors · saschb2b bundle
Audit and refactor UI code so every color value comes from the theme. Replace hex codes, rgba(), hsl(), oklch() literals, and named CSS colors with theme palette tokens (primary, secondary, error, warning, info, success, background, text) and the alpha() helper for transparency. Use when writing or reviewing any UI component, when starting a new MUI or design-system theme, when a designer hands off colors as hex annotations, when seeing color literals scattered across component files, or when an LLM produced styling with hardcoded hex values. Counterweight to LLM training corpora dominated by tutorial code that inlines hex codes and rgba literals instead of role-based theme tokens.

0
installs
▌
Breadcrumbs · saschb2b bundle
Heal codebase understanding gaps exposed during implementation, debugging, or investigation. Use when tracing reveals misleading names, repeated backtracking, disconnected navigation paths, hidden contracts, surprising dependencies, stale documentation, unclear errors, undocumented constraints, false leads, or avoidable complexity. Make the smallest durable improvement at the source through clearer code, types, validation, tests, errors, comments, or existing documentation. Also use when a task was harder to grasp than it should have been or you think "that should have been documented." Do not create a breadcrumb trail, investigation log, freshness system, or separate knowledge store.

0
installs
▌
Game Design · saschb2b bundle
Analyze, design, critique, balance, and rework video game mechanics, systems, and interface, grounded in a cross-game pattern catalog and design frameworks (MDA, core loops, flow, game feel, economy). The first stop for any design-touching change or discussion, including mid-implementation in an engine like Godot. Use when designing, balancing, brainstorming, or reworking a mechanic, progression, economy, loadout, inventory, loot, shop, enemy or difficulty scaling, reward, menu, or UI system; when tuning drop rates, prices, curves, or scaling; when asking whether something is fun, too grindy, or has a dominant strategy; when designing menus, HUD, transitions, onboarding, dialogue, guidance, input prompts, or accessibility; when capturing, pitching, or iterating a game idea, concept, vision, design pillars, or GDD, persisted as a living concept bundle; or when self-authoring game systems while building one. Rides alongside godot, which writes the engine code, while this decides what that code should do.

0
installs
▌
Audit Actions · saschb2b bundle
Audit a repository's GitHub Actions workflows for unsafe pull_request_target usage that can lead to supply chain compromise. Use when the user asks to audit workflows, review CI/CD security, check pwn request risk, harden Actions, or after a supply chain incident in a dependency. Also use proactively when reviewing any PR that touches .github/workflows/.

0
installs
▌
Comment Stinky · saschb2b bundle
Detect code-comment smells in any language, explain the cost of each, and propose the rewrite. Built against the failure mode where a comment narrates the edit that produced it (now, no longer, previously, instead of the old X) rather than the standing reason the code has its shape, because the reader only ever has the file, never the diff. Six pillars and 37 categories cover change narration and diff residue, redundancy (restating the code, signature echo, banner ceremony), missing intent (magic constants, workarounds, swallowed errors, unstated invariants), truth and decay (stale and lying comments, dead anchors), placement and form (a comment that wants to be a name, a test, or a doc comment, unowned TODOs), and voice. Ships a four-question write gate and a taxonomy of the nine comments worth writing. Apply implicitly whenever you write or edit a comment or docstring, and when asked to comment, document, audit, or clean up comments in a codebase, diff, file, or snippet. Defers prose register to no-slop.

0
installs
▌
React Compiler · saschb2b bundle
Write and review React code as if the React Compiler is enabled. Skip manual useMemo, useCallback, and React.memo by default, and audit existing code for stale manual memoization. Use when writing or refactoring any React component in a React 19+ codebase, when reviewing a React PR, when setting up the eslint-plugin-react-hooks configuration, or when seeing memoization patterns in code an LLM produced. Counterweight to pre-compiler React in LLM training corpora, which biases default output toward manual memoization unless prompted otherwise.

0
installs
▌
Android Compose · saschb2b bundle
Modern Android development with Jetpack Compose as the default UI toolkit and Material 3 Expressive as the default design direction, a dated snapshot. Covers Compose fundamentals (composables, modifiers, state hoisting, side effects, lazy lists, strong skipping, recomposition), Material 3 and Expressive theming and components (MaterialExpressiveTheme, MotionScheme, button groups, split buttons, FAB menu, floating toolbars, wavy progress indicators, shape morphing, dynamic color), architecture (ViewModel, StateFlow, collectAsStateWithLifecycle, Hilt), type-safe Navigation Compose and Navigation 3, data (Room, DataStore, Retrofit, Ktor, Coil), the Gradle Kotlin DSL build with version catalogs and KSP, testing, performance, and View interop. Use when building Android UI in Compose, theming with Material 3 or Expressive, wiring architecture or navigation, configuring the build, or debugging Compose issues. Check the project's versions first; re-verify version facts against the official Android and AndroidX docs.

0
installs
▌
Storybook Pentest · saschb2b bundle
Pentest Storybook components two ways. Whether they break under stress, and whether they actually do their job well. Test one story, a component group, or the whole Storybook, and write every finding into an OKF bundle with screenshots, severity, and a reproducible URL. The break pass probes extreme and hostile text, empty and overloaded data, accessibility, keyboard use, zoom, reflow, RTL, dark mode and forced colors, and broken media. The value pass judges fitness for purpose against usability heuristics, asking whether the control is clear, the label specific, the error message useful, and the promise its name makes kept. Use when asked to pentest, stress-test, audit, break, or find edge cases or UX issues in a Storybook, design system, or component; when a component misbehaves with long text, empty states, dark mode, RTL, zoom, or keyboard use, or is confusing or does the wrong thing; or when stories need an a11y or usability sweep. Complements react-stinky (code quality) and visual-consistency (polish).

0
installs
▌
Visual Consistency · saschb2b bundle
Detect and fix visual and layout consistency defects in rendered UI, the systematic raggedness AI generators emit and seniors notice at a glance. Covers uneven card heights in a grid, sibling cards whose internal sections (title, body, footer) do not line up, trailing icons such as open-in-new-tab at ragged X positions, and arbitrary off-scale spacing, plus alignment, repeated elements (buttons, radius, shadow, icons), type scale, tables and numeric alignment, borders, overflow, layout shift, touch targets, and focus rings. Each smell carries an objective detection signal, a concrete CSS fix (subgrid, equal-height grids, spacing tokens, tabular-nums), an exception guard, a severity, and whether an agent may fix it freely or must surface a design call first. Use when reviewing or building any UI, when a card grid or list looks busy or ragged, when spacing feels arbitrary, or when asked to tidy or align a layout so it scans cleanly. Defers color to theme-colors and component code smells to react-stinky.

0
installs
▌
Javascript Ecosystem · saschb2b bundle
Default to the latest stable major versions of JavaScript and TypeScript frameworks and their current paradigms, instead of the older versions and patterns that dominate LLM training data. A version-and-paradigm changelog index that routes to per-tool notes. Use when writing, reviewing, scaffolding, or upgrading any JS or TS project, when choosing dependency versions, when an agent emits an outdated pattern, or when working with React, Angular, Vue, Svelte, Solid, Next.js, Nuxt, React Router, Remix, SvelteKit, Astro, TanStack Start, Material UI, Tailwind, shadcn, Mantine, Chakra, TanStack Query, Redux, Zustand, Jotai, TypeScript, Vite, Node, ESLint, pnpm, Bun, or Biome. Check the project's installed version first; this snapshot ages.

0
installs

24 published skills