luongnv89

Run coding tasks via opencode using free cloud models. Use when asked to offload work to opencode.ai or run a free model. Don't use for local models (Ollama, LM Studio), Claude/OpenAI calls, or when Claude should do the work itself.

Install local-first security hardening: pre-commit secret detection, offline dependency scans, static analysis, reports, and gated free CI. Use when hardening repos or adding security hooks. Don't use for incident response or cloud security reviews.

Generate exactly 3 simple, fast, healthy recipes from food photos, ingredient lists, or cravings. Use for what-to-cook-tonight requests. Don't use for restaurants, meal plans, baking, or medical diets.

6-phase website cloning and improvement orchestrator. Takes a URL and produces an improved version (performance + UI/UX) via Vite/React/shadcn/Tailwind hosted on GitHub Pages. Use when asked to clone a site, rebuild a website, or make a better version of a URL. Orchestrates sibling skills with approval gates — don't use for single-phase work.

Analyze any website URL across 6 dimensions: UI/UX, category, style, performance (LCP/CLS/TTFB/weight/requests), surface-level security, and SEO (score 0-100 with breakdown). Outputs structured JSON for downstream skills. Use when asked to analyze, audit, or scan a website. Don't use for full SEO audits or penetration testing.

Execute the approved tasks.md to build a Vite + React + shadcn/ui + Tailwind CSS website deployable to GitHub Pages. Collects assets from the original site and creates new assets per plan. Emits builder metadata for the final report. Use when asked to build, implement, or code a website from a plan. Don't use for design review or planning — those are upstream phases.

Convert website analyzer output into a comprehensive plain-language report for non-technical users. Prompts for validation before persisting. Use when asked to report on a website analysis, create an end-user report, or translate technical metrics into plain language. Don't use for technical audit reports targeting developers, raw SEO audits, or penetration testing. Approval gate: never saves without explicit user approval.

Turn approved end-user report into a full improvement proposal with what/why/value for each change. Writes prd.md after user approval. Use when asked to propose website improvements, create a PRD for a site rebuild, or plan improvements with measurable impact. Don't use for implementation planning or coding — those are separate phases.

Interactive lesson-level quiz for Claude Code tutorials. Tests understanding of a specific lesson (01-10) with 8-10 questions mixing conceptual and practical knowledge. Use before a lesson to pre-test, during to check progress, or after to verify mastery. Use when asked to "quiz me on hooks", "test my knowledge of lesson 3", "lesson quiz", "practice quiz for MCP", or "do I understand skills".

Comprehensive code review with security, performance, and quality analysis. Use when users ask to review code, analyze code quality, evaluate pull requests, or mention code review, security analysis, or performance optimization.

Забезпечення відповідності всіх комунікацій голосу та тону бренду. Використовуйте при створенні маркетингових текстів, клієнтських комунікацій, публічного контенту, або коли користувачі згадують голос бренду, тон чи стиль написання.

Комплексне код-рев'ю з аналізом безпеки, продуктивності та якості. Використовуйте, коли користувачі просять переглянути код, проаналізувати якість коду, оцінити pull request, або згадують код-рев'ю, аналіз безпеки чи оптимізацію продуктивності.

Генерація вичерпної, точної документації API з вихідного коду. Використовуйте при створенні або оновленні документації API, генерації специфікацій OpenAPI, або коли користувачі згадують документацію API, ендпоінти чи документацію.

Систематичний рефакторинг коду на основі методології Мартіна Фаулера. Використовуйте, коли користувачі просять рефакторити код, покращити структуру коду, зменшити технічний борг, очистити застарілий код, усунути запахи коду (code smells) або покращити супровідність коду. Ця навичка проводить через поетапний підхід з дослідженням, плануванням та безпечною інкрементальною реалізацією.

Створення чернетки блог-посту з ідей та ресурсів. Використовуйте, коли користувачі хочуть написати блог-пост, створити контент з дослідження або підготувати статтю. Проводить через дослідження, мозковий штурм, складання плану та ітеративне написання з контролем версій.

Створення або оновлення файлів CLAUDE.md відповідно до найкращих практик для оптимального онбордингу AI-агента

Re-ingest every already-enabled repo in data/skill-index-resources.json: sync the working tree, run preindex, rebuild the catalog for verification, summarize updated/unchanged/failed/skipped, then gate commit + PR behind explicit confirmation. Use when asked to refresh the index, re-ingest indexed repos, or batch-maintain already-indexed skill sources. Don't use for adding new repos (use skill-index-updater), improving a single skill (use skill-auto-improver), or installing/updating skills on the local machine (use asm install or asm update).

Add GitHub skill repos to the ASM index: clone, audit, eval, regenerate index, rebuild catalog, open PR. Use when given GitHub URLs to onboard. Don't use for authoring (skill-creator), improving (skill-auto-improver), or install (asm install).

Create, improve, evaluate, and benchmark skills. Use when authoring a new skill, updating an existing one, running evals, or optimizing a skill's description for triggering. Don't use for invoking skills, writing prose, or scaffolding Python projects.

Improve a SKILL.md to pass the skill-creator standard (quick_validate, frontmatter audit, ≤500 lines) AND the asm-eval 85/8 floor. Use to level up a skill before publish. Don't use for authoring from scratch, bulk evaluation, or prose rewriting.

Validate a skill. Don't use for unrelated docs.

Validate a skill when asked. Don't use for unrelated docs.

Validate a skill when asked. Don't use for unrelated docs.

Validate a skill. Don't use for unrelated docs.

Review a PR end-to-end with CI checks, fix cycles, and optional auto-merge. Use for PR review, cleanup, or readiness checks. Don't use for creating PRs, raw issue analysis, or non-PR code review.

Create an atomic PR that closes a GitHub issue end-to-end via a 6-step pipeline. Use when asked to resolve issue #N, fix #N, implement #N, work on #N, take issue #N, or /issue-resolver. Don't use for analyzing an issue without implementing (use /issue-analysis), reviewing an existing PR (use /issue-pr-review), or bulk backlog processing (use /auto-pilot).

Review a PR end-to-end with CI checks, fix cycles, and optional auto-merge. Use for PR review, cleanup, or readiness checks. Don't use for creating PRs, raw issue analysis, or non-PR code review.

Create an atomic PR that closes a GitHub issue end-to-end via a 6-step pipeline. Use when asked to resolve issue #N, fix #N, implement #N, work on #N, take issue #N, or /issue-resolver. Don't use for analyzing an issue without implementing (use /issue-analysis), reviewing an existing PR (use /issue-pr-review), or bulk backlog processing (use /auto-pilot).

Run a fully autonomous triage-resolve-review-merge loop over the GitHub issue backlog with zero user prompts. Use when asked to auto-pilot, autopilot, resolve everything, work through the backlog, run the loop, or keep going until done. Don't use for single-issue work (use /issue-resolver), one-shot triage (use /issue-triage), or interactive PR review (use /issue-pr-review).

Generate a project-specific .gitissue.yml by auto-detecting language, framework, test runner, and repo size. Use when asked to init gitissue, setup gitissue, configure gitissue, first time setup, /init-gitissue, or to set up IDD on a new repo. Don't use for editing an existing .gitissue.yml (edit directly), creating GitHub issues (use /issue-creator), or general git/repo initialization like git init or npm init.

Analyze a single GitHub issue for root cause, affected files, implementation options, complexity, and risk; persists to .gitissue/analysis-N.json. Use when asked to analyze issue #N, investigate issue, impact analysis, how hard is #N, or /issue-analysis. Don't use for creating/filing issues (use /issue-creator), bulk triaging (use /issue-triage), or actually resolving the issue (use /issue-resolver).

Analyze and triage open GitHub issues for dependencies, priorities, parallelizable work, staleness, and already-fixed detection, caching results to .gitissue/triage.json. Use when asked to triage issues, prioritize issues, what should I work on next, or /issue-triage. Don't use for analyzing one specific issue (use /issue-analysis), resolving an issue (use /issue-resolver), or creating new issues (use /issue-creator).

Extract a design system from a screenshot (PNG/JPG/WEBP) or a live URL and produce a schema-compliant `design.v1.json` file plus a ready-to-use agent prompt for applying the design to any website/app. When run inside the sleek-ui repository, offers to add the extracted design to the public catalog as a PR — updating `public/designs/`, `src/data/designs/`, `src/data/designs.ts`, and generating a preview. Use when users ask to "extract a design from this screenshot", "clone this site's design", "reverse-engineer the design tokens", "reskin my app to look like {site}", "generate a sleek-ui design from this URL", or provide an image/URL and want a reusable design system.

Analyze and tune a running llama.cpp server for local coding agents: propose config (ctx, prompt cache, MTP), benchmark before/after, report deltas. Use to optimize llama-server for Claude Code or Aider. Don't use for vLLM, ollama, or non-llama.cpp.

Generate exactly 3 quick healthy recipes with quantities, nutrition estimates, Telegram layout, visual cues, and images from food photos, ingredients, cravings, or recipe search. Don't use for restaurants, meal plans, baking, or medical diets.