with one click
quick-healthy-recipes
// 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.
// 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.
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.
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.
| name | quick-healthy-recipes |
| description | 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. |
| license | MIT |
| effort | medium |
| metadata | {"version":"1.0.0","author":"Luong NGUYEN <luongnv89@gmail.com>"} |
Turn food photos, ingredient lists, or a short cooking desire into exactly 3 practical recipes that are simple, fast, and healthy enough for a normal weeknight.
Use this skill when the user asks things like:
Do not use it for restaurant recommendations, long meal plans, baking projects, special-diet medical advice, or gourmet cooking that requires advanced technique.
Optimize every answer for:
Common pantry items are acceptable: salt, pepper, oil, butter, garlic, onion, vinegar, lemon, soy sauce, eggs, rice, pasta, bread, beans, yogurt, cheese, herbs, and basic spices.
If images are provided, inspect them before suggesting recipes. Identify:
If text is provided, extract:
Ask a question only when a safety-critical detail is missing. Otherwise, make a reasonable assumption and state it briefly.
Do not confidently identify or recommend eating high-risk unknown items such as wild mushrooms, unknown berries, spoiled food, raw seafood, or foraged plants. If the food might be unsafe, say so and suggest using only verified ingredients.
Do not give medical nutrition advice. For allergies, pregnancy, diabetes, kidney disease, or other medical constraints, keep guidance general and tell the user to follow their clinician's advice.
Create exactly 3 distinct options. Each option should vary by cooking style or meal format, for example:
For each recipe, keep ingredient additions short. Prefer one protein booster and one carb/fiber base when the raw ingredients alone are not balanced.
Put the best fit first. The first recipe should usually be the fastest and most realistic with the least extra shopping.
Use this exact structure. Keep it concise.
Looks like: [ingredient identification or parsed request]
Assumption: [one short assumption, or "none"]
1. [Recipe name] — [time]
Best if: [why this is the top fit]
Extra ingredients: [0–5 common items]
Steps:
- [short step]
- [short step]
- [short step]
Healthy balance: [protein + veg/fiber + carb/fat note]
2. [Recipe name] — [time]
Best if: [why choose it]
Extra ingredients: [0–5 common items]
Steps:
- [short step]
- [short step]
- [short step]
Healthy balance: [protein + veg/fiber + carb/fat note]
3. [Recipe name] — [time]
Best if: [why choose it]
Extra ingredients: [0–5 common items]
Steps:
- [short step]
- [short step]
- [short step]
Healthy balance: [protein + veg/fiber + carb/fat note]
Pick tonight: [one sentence recommendation]
Before finalizing, check:
If a recipe fails the checklist, replace it before answering.