kuker24

@kuker24 source repo

62 skills
0 followers
5 hours ago last updated

▌
Grilling · kuker24
Stress-test a plan with design-tree frontier rounds. Use when the user wants grilling as a primitive. Full product interviews that should leave CONTEXT.md/ADRs use /grill-with-docs.

0
installs
▌
Codebase Design · kuker24 bundle
Design or deepen a module interface, seam, test surface, or abstraction. Skip ordinary implementation, product interviews, and multi-sketch architecture bake-offs (/architect).

0
installs
▌
Domain Modeling · kuker24 bundle
Sharpen fuzzy or conflicting domain terms, relationships, CONTEXT.md glossaries, or ADRs. Skip merely reading CONTEXT.md for vocabulary. Product interviews that still need a plan use /grill-with-docs.

0
installs
▌
Emil Design Eng · kuker24
UI motion, transition, and interaction feel after Impeccable. Use when polishing animation, easing, press/hover, or interruptible chrome motion. Do not use for static UI, photoreal video, scroll-craft stories, scroll-world camera chains, or deterministic HTML-to-video compositions (hyperframes). Easing, seam timing, and pointer chrome already live here — do not load a separate cut-the-curve, motion-doctrine, oversized-cursor, or seam-craft specialist.

0
installs
▌
Writing For Agents · kuker24 bundle
Author or edit SKILL.md, CLAUDE.md, AGENTS.md, skill descriptions, or context pointers. Skip choosing which existing workflow to run (/ask-matt).

0
installs
▌
Tdd · kuker24 bundle
Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.

0
installs
▌
Adhd · kuker24
Parallel divergent ideation for coding agents. Spawns N isolated branches under different cognitive frames (regulator, biology, speedrunner, 10-year-old, $0 budget), scores, clusters, prunes traps, and deepens top survivors. Use on /adhd, "ADHD mode", brainstorm/ideate intents, or open-ended design, architecture, naming, API/SDK surface, and fuzzy-debugging decisions. Skip for syntax, lookups, bugs with known root cause, or closed phrasing ("quick", "standard", "canonical", "textbook"). Full pre-flight gate is in the skill body.

0
installs
▌
Gh Axi · kuker24
Operate GitHub through the gh-axi CLI - issues, pull requests, workflow runs, workflows, releases, repositories, labels, gists, Projects (v2), Actions secrets and variables, search, and raw API access. Use whenever a task touches GitHub: listing or filing issues, reviewing or merging PRs, checking CI runs, triggering workflows, cutting releases, managing Projects boards, managing Actions secrets/variables, or working with gists via `gist list`, `gist view`, `gist edit`, `gist rename`, `gist create`, `gist delete`, or `gist clone`.

0
installs
▌
To Spec · kuker24
Turn the current conversation into a spec and publish it locally under .scratch — no interview, just synthesis of what you already discussed. Use after grilling, or when the user asks for a spec or /to-spec.

0
installs
▌
Academic · kuker24 bundle
Academic research, literature synthesis, thesis/paper drafting, and peer review. Use for scholarly literature surveys, claim-to-source tracing, academic manuscripts (IMRaD/proposals), and rigorous peer critique. Not for library/API docs (research), one-off document OCR/render (smartdoc), or local book ingest (smartbook-ingest).

0
installs
▌
Ask Matt · kuker24 bundle
Pick the GrokBuild skill or flow that fits. Use when the user asks which skill to use, which workflow, "alur apa", "ask matt", or is choosing between planning, implement, review, and design paths.

0
installs
▌
Research · kuker24
Investigate a question against official docs, specs, or first-party APIs and write cited Markdown if asked. Use for external/library facts. Skip why *this repo* chose an approach (/why), and academic literature/theses (academic).

0
installs
▌
Smartdoc · kuker24 bundle
SmartDoc

0
installs
▌
Code Tour · kuker24 bundle
Create CodeTour `.tour` files — persona-targeted walkthroughs with verified file and line anchors under `.tours/`. Use for onboarding, architecture, PR, RCA, or "explain how this works" when a reusable guided artifact is wanted. Not for chat-only explanations, prose docs (technical-writing), or implementation work.

0
installs
▌
Humanizer · kuker24 bundle
Remove AI writing tells from text and prose. Use when the user asks to humanize, unslop, remove AI tone, sound natural, or polish writing to sound human. Not for source code, tests, commands, or technical documentation structure (use /technical-writing).

0
installs
▌
Prototype · kuker24 bundle
Throwaway evidence to answer one design question (logic/state or UI variants). Skip ordinary implementation, ADHD, and multi-model bake-offs (/arena).

0
installs
▌
Why · kuker24 bundle
Why this repo chose an approach: git history, ADRs, PRs, local docs. Use for /why, 'why does this repo do X', design rationale, regressions. Manual only. Official library docs use research / Context7. GitHub ops use /gh-axi.

0
installs
▌
API Design · kuker24 bundle
Design or review REST API contracts — resource naming, HTTP methods, status codes, pagination, filtering, errors, versioning, and rate-limit headers. Use when shaping or auditing HTTP endpoints. Not for library/API docs (research/Context7), consumer-provider schema ownership (contract-first), or auth/secrets review (full-audit-keamanan).

0
installs
▌
Impeccable · kuker24 bundle
Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks. Editorial HTML/SVG diagrams route to diagram-design.

0
installs
▌
To Tickets · kuker24
Break a plan, spec, or the current conversation into tracer-bullet tickets with blocking edges. Default tracker is local files under .scratch. Use after a spec, or when the user asks to break work into tickets or run /to-tickets.

0
installs
▌
Vercel Ops · kuker24
Use when the user configures Vercel deploy, project env (names only), Next.js app router hosting, preview URLs, or vercel.json. Not for inventing visual UI, not for frontend-design aesthetics, not for Mongo/Supabase schema.

0
installs
▌
Browser Act · kuker24
Browser automation CLI for specialized multi-session browser workflows. Use only when the user explicitly requests BrowserAct, specifies a browser-act CLI command, or requires pre-configured persistent/multi-account sessions. For exploratory QA of local application UI under development, use playwright-qa instead. Never use chrome-direct.

0
installs
▌
Hyperframes · kuker24 bundle
Deterministic video composition from HTML, CSS, and seekable animations rendered to MP4 via headless Chrome and FFmpeg. Use for programmatic video creation, motion graphics, animated explainers, and HTML-to-video rendering. Not for photoreal/cinematic media (visual-studio), UI interaction feel (emil-design-eng), scroll-led storytelling (scroll-craft), or 3D camera worlds (scroll-world).

0
installs
▌
Mongodb Ops · kuker24
Use when the user designs MongoDB schemas, indexes, aggregation, transactions, or Atlas-compatible data access. Not for UI, not for Supabase Postgres, not for deploying Vercel.

0
installs
▌
Arena · kuker24
Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for /arena, 'arena this', or when one attempt at a non-trivial artifact would lock in the wrong shape. Manual only.

0
installs
▌
Eval Harness · kuker24 bundle
Evaluation harness and benchmark design for prompts, agents, and LLM workflows. Implements eval-driven development (EDD), test suite generation, pass@k metrics, and regression testing. Use when validating agent behavior, comparing prompt iterations, or establishing objective quality gates for LLM outputs. Not for standard application unit tests (tdd), exploratory browser testing (playwright-qa), or security auditing (full-audit-keamanan).

0
installs
▌
Scroll Craft · kuker24 bundle
Build scroll-led storytelling websites where scroll is the timeline: scrollytelling, signature interaction, pin/pan/reveal, layered hero, cinematic scroll without camera flight. Use when the user runs /scroll-craft, or asks for a site where scrolling tells the product story. Not for ordinary dashboards or landings (impeccable), continuous camera fly-through / diorama / 3D world (scroll-world), chrome motion (emil-design-eng), or photoreal ads (visual-studio).

0
installs
▌
Scroll World · kuker24 bundle
Build a scroll-scrubbed fly-through landing: as the visitor scrolls, a pre-rendered camera flies into each scene and on to the next with no cuts. Use when: 3D world landing, diorama site, Emons-style isometric world, scroll cinematic, browse-through-the-industry hero, camera-scrub page, or the user runs /scroll-world. Uses GrokBuild image_gen, image_edit, and image_to_video plus a portable vanilla-JS scrub engine. Load OpenCode native image tools if present, else DEGRADED before any generate/edit/video call. Not for scroll-led storytelling without a camera world (use scroll-craft), an ordinary landing (use impeccable), photoreal ads/identity with no world page (use visual-studio), or UI chrome motion (use emil-design-eng after Impeccable).

0
installs
▌
Supabase Ops · kuker24
Use when the user works on Supabase Auth, RLS, Postgres schema/migrations, Edge Functions, Storage, Realtime, supabase-js, or @supabase/ssr. Not for visual UI, not for MongoDB, not for Vercel deploy-only.

0
installs
▌
Unslop · kuker24
Cut AI tells from user-facing prose when the user runs /unslop. Manual alias for humanizer. Do not auto-apply. Do not rewrite code. Technical documentation structure uses /technical-writing.

0
installs
▌
Wizard · kuker24 bundle
Generate an interactive bash wizard for steps only a human can perform (dashboard, OAuth, secret provision, cutover). Do not use for work the agent can do itself.

0
installs
▌
Playwright QA · kuker24 bundle
Primary exploratory browser QA adapter for web applications under development. Use to navigate local UI, exercise forms, inspect rendered DOM/state, take snapshots and screenshots, and verify visual flows via Playwright CLI. Respects existing project test suites (Playwright Test/Cypress) for regressions. Skip for backend-only tasks, explicit BrowserAct requests, or deep observed-failure diagnostics (chrome-devtools-axi).

0
installs
▌
Visual Studio · kuker24 bundle
Produce photoreal product stills, reusable identity packs, UGC/ad videos, cinematic VFX shots, and video thumbnails with GrokBuild image_gen, image_edit, image_to_video, and reference_to_video. Use when: product photo, studio shot, lifestyle, Pinterest pin, hero banner, carousel, ad pack, virtual try-on, UGC, unboxing, product review, TV spot, cinematic video, VFX, character sheet, size-ref, face-lock, YouTube thumbnail, Shorts cover, or the user runs /visual-studio. Load OpenCode native image tools if present, else DEGRADED before any generate/edit/video call. Not for UI/frontend (use impeccable), game sprites or tiles (use game-asset-core), or UI motion (use emil-design-eng).

0
installs
▌
Reflect · kuker24 bundle
Mine this conversation for durable learnings, classify them, show them, and wait for explicit approval before any skill edit. Use for /reflect. Manual only. Never auto-edit skills.

0
installs
▌
Contract First · kuker24 bundle
Coordinate multiple consumers and providers around one versioned, machine-checkable API or event contract so fields, nullability, and errors do not drift. Use when frontend/backend or services will implement in parallel. Not for REST style guides (api-design), module seams inside one commit (codebase-design), or product interviews (grill-with-docs).

0
installs
▌
Diagram Design · kuker24 bundle
Design editorial HTML and inline SVG diagrams for software architecture, sequence flows, ER data models, system boundaries, and concept maps. Use for high-clarity technical diagrams, visual architecture documentation, and converting raw Mermaid/draw.io into polished visuals. Not for frontend application UI (impeccable) or code-level seam design (codebase-design).

0
installs
▌
Diagnosing Bugs · kuker24 bundle
Hard unknown bugs, regressions, or measured slowdowns that still need a red-capable reproduction loop. Skip typos, known-cause fixes, and test-first work that already has a failing test (/tdd).

0
installs
▌
Grill With Docs · kuker24
Relentless interview to sharpen a plan. Writes CONTEXT.md, a glossary, and ADRs as you go. Use when a feature still needs a plan, the user wants grilling, or they ask for /grill-with-docs.

0
installs
▌
Skill Stocktake · kuker24 bundle
Audit and maintain quality, hygiene, and boundary integrity across OpenCodeBestFriend skills. Checks frontmatter schema, trigger keywords, exclusivity fences, path references, and test coverage. Use when reviewing installed or warehouse skills, auditing catalog health, or cleaning up skill bloat. Not for code-level security audits (full-audit-keamanan), code style review (matt-code-review), or prompt text optimization (prompt-optimizer).

0
installs
▌
Architect · kuker24 bundle
Sketch types, signatures, and module structure before code, then stay in the loop while implementation fills in. Use for /architect when jumping to code would lock in the wrong shape. Manual only. Module/seam vocabulary lives in codebase-design; this skill is the bake-off.

0
installs
▌
Wait What · kuker24
Stop. That last message did not land — re-pitch it.

0
installs
▌
Click Path Audit · kuker24 bundle
Trace each user-facing control through its handler and shared-store writes to find sequential undo, async races, stale closures, and missing transitions. Use when buttons look wired but do nothing, or after a refactor of shared UI state. Not for exploratory browser QA (playwright-qa), ordinary red-green bugs (diagnosing-bugs), or visual layout (impeccable).

0
installs
▌
Matt Code Review · kuker24
Two-axis Standards + Spec review of a pinned diff. Use only when the user asks for that two-axis review, or runs /matt-code-review. Default review is in-session.

0
installs
▌
Prompt Optimizer · kuker24 bundle
Analyze, critique, and optimize system prompts, task instructions, and agent framing. Enhances structural clarity, edge-case handling, negative constraints, and output schema adherence without executing the underlying task. Advisory only; does not mutate installed skills. Use when refining prompt text, reducing ambiguity, or fixing prompt drift. Not for ordinary coding tasks, prose humanizing (humanizer), or writing agent documentation (writing-for-agents).

0
installs
▌
Smartbook Ingest · kuker24 bundle
SmartBook ingest

0
installs
▌
Found This Design · kuker24 bundle
Find 3 or 5 matching UI designs from the local design bank at `$OPENCODE_DESIGN_BANK` or `~/Design` (Refero styles + Motionsites sections) for the current web project or a redesign brief, then generate a high-fidelity first-viewport photo of this product in each recommended world. Use when the user runs /found-this-design or /found_this_design, or asks to find a design, cari desain, rekomendasi desain, design yang cocok, preview desain, prototype visual, design bank, Refero, Motionsites, or which visual direction fits this site. Not for implementing UI (use impeccable after a pick) or photoreal product/ad video (use visual-studio).

0
installs
▌
Install Anti Slop · kuker24 bundle
Install, audit, configure, or remove opinionated Anti-Slop Oxlint rules in local TypeScript or JavaScript repositories. Use ONLY when explicitly requested to add anti-slop rules, audit TS/JS anti-patterns, configure anti-slop profiles, or migrate/remove an anti-slop setup. Skip for Python/Go/Rust, prose editing (use /unslop), and ordinary coding tasks.

0
installs
▌
Interrogate · kuker24 bundle
Adversarial multi-reviewer challenge of a pinned change. Use for /interrogate, 'adversarial review', or 'tear this apart'. Do not auto-apply. Manual only. Default two-axis review is /matt-code-review.

0
installs
▌
Blast Radius · kuker24
Find what a change could break somewhere else before it ships, and prove the one safety fact by running real code. Use for /blast-radius, 'what could this break', or reviewing a small diff you do not trust. Manual only.

0
installs
▌
Decision Log · kuker24 bundle
Keep a reviewable operational decision trail for long-running work: a TSV log with one row per decision (what, why, evidence, result). Use for /decision-log. Do not record hidden reasoning.

0
installs
▌
Chrome Devtools Axi · kuker24
Control a Chromium session through chrome-devtools-axi after opencode-chromium-cdp start. Use when an observed browser issue needs diagnostics (click, form, console, network). Skip if curl or web_fetch is enough. Not for exploratory multi-role QA (use browser-act).

0
installs
▌
Full Audit Keamanan · kuker24 bundle
Use for broad defensive security audits across code, config, auth, secrets, supply chain, AI/LLM integrations, and deployment.

0
installs
▌
Figure It Out · kuker24
Design an auditable playbook when no narrower skill fits: a large migration, an ambitious multi-part change, or work a human reviews after stepping away. Use for /figure-it-out. Manual only. Do not inflate a small task.

0
installs
▌
Automation Audit Ops · kuker24 bundle
Evidence-first inventory of live automations — cron, GitHub Actions, hooks, MCP servers, wrappers, and connectors — then keep / merge / cut / fix-next. Use when asking what is live, broken, redundant, or missing before changing anything. Not for skill-catalog hygiene (skill-stocktake), agent-loop diagnosis (agent-architecture-audit), or GitHub issue/PR operations (gh-axi).

0
installs
▌
Matt Implement · kuker24
Implement a piece of work based on a spec or set of tickets.

0
installs
▌
Full Performance Audit · kuker24 bundle
Audit application performance including latency, throughput, memory, and bundle size. Use when profiling applications, identifying bottlenecks, or optimizing performance.

0
installs
▌
Cost Aware LLM Pipeline · kuker24 bundle
Design and optimize cost-efficient LLM application architectures. Covers model tiering, task complexity routing, prompt caching strategies, token budget fences, and retry backoff. Use when reducing API spend, establishing token budgets, or architecting multi-model fallback cascades. Not for client runtime latency/bundle audits (full-performance-audit) or prompt phrasing refinement (prompt-optimizer).

0
installs
▌
Technical Writing · kuker24
Layered technical-writing standard: Diátaxis structure, Google developer style sentences, STE instruction rules, Global English syntax. Use for /technical-writing or when writing or reviewing docs, RFCs, readmes, PR descriptions, or commit messages. AI-tell cleanup of existing prose uses /unslop.

0
installs
▌
Agent Architecture Audit · kuker24 bundle
Audit agent system architectures, LLM pipelines, prompt wrapper layers, tool loop boundaries, and context propagation. Use when an agent application exhibits regressions, tool calling failures, context pollution, or infinite repair loops. Not for code-level defensive security or secrets auditing (full-audit-keamanan), web UI (impeccable), or ordinary application bugs (diagnosing-bugs).

0
installs
▌
Create Verification Skill · kuker24 bundle
Generate a project-local verification skill that drives your app the way a user does — any language, framework, or platform. Use for /create-verification-skill, \"make a control skill for this repo\", or when a project has no scripted way to prove UI/CLI/service behavior.

0
installs
▌
Maintain Verification Skill · kuker24
Periodic pass that keeps a project's verification skill and feature map honest: parallel source readers per feature, one live session driving every feature, at most one PR of proven corrections. Use for /maintain-verification-skill or \"audit the verify skill\".

0
installs
▌
Improve Codebase Architecture · kuker24 bundle
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick. Manual only. Default report is zero-network inline CSS/SVG.

0
installs

62 published skills