agentleFS
tejask0tejask0/agent-skills/food-check/SKILL.md

food-check

Skill0 starsChanged 4 months agoMITView on GitHub

Analyse a dish, meal, or ingredient combination across five dimensions: digestion compatibility, nutrient absorption, Ayurvedic food combining rules, micronutrient and protein content, and overall pros/cons with actionable suggestions. ALWAYS use this skill when the user mentions eating a dish or a mix of ingredients and asks whether it is good, healthy, safe, or okay — even with casual phrasing like "I'm eating X and Y together, is this fine?", "does this combo work?", "what do you think of this meal?", "check this", "is this good?", "analyse this food", or when the user describes their diet, meals, or post-workout food. Trigger any time food items are listed together and some form of health or suitability check is implied.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Produce all five sections in one response: Keep each section to 2–3 tight bullets.

    line 15
  2. Distinctive:

    Call out any real conflicts only (fermentation risk, enzyme clash, bloating trigger).

    line 25
  3. Distinctive:

    Every "con" must have a corresponding fix in the Verdict.

    line 53
  4. Distinctive:

    No research dumps. If a concern is minor, skip it.

    line 55
  5. Distinctive:

    If the user has stated a diet or fitness goal (e.g.

    line 56

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Food Check Skill

Analyse a dish or ingredient combination and return a structured five-section report. Be concise and actionable — this is a quick decision tool, not a research paper. Max 2–3 bullets per section. No padding, no restating obvious facts.

Workflow

  1. Parse the input — identify every ingredient, cooking method (if mentioned), and any relevant user context (fitness goal, dietary preference, post-workout timing, an allergy or ingredient to avoid, etc.). If a critical detail is missing and materially changes the analysis, ask one clarifying question. Otherwise proceed.
  2. Produce all five sections in one response. Keep each section to 2–3 tight bullets.

Five-Section Output Format


🔥 1. Digestion

  • Rate ease of digestion: Easy / Moderate / Heavy.
  • Call out any real conflicts only (fermentation risk, enzyme clash, bloating trigger). Skip minor or theoretical ones.
  • Best timing if relevant (pre/post workout, avoid at night, etc.).

🧬 2. Absorption

  • Name the 1–2 meaningful enhancers or blockers in this combo.
  • One fix if there's a clear absorption problem (e.g., "add lemon for iron").

🌿 3. Ayurveda

  • Flag any Viruddha Ahara (incompatible) pairs. Label it: classical rule vs. modern evidence.
  • State net dosha impact in one line.
  • Skip if no meaningful concern.

📊 4. Protein & Key Nutrients

  • Protein estimate (g) for a typical serving.
  • Is the amino acid profile complete? If not, name the limiting amino acid and the simplest fix.
  • Top 2–3 micronutrient wins. Flag critical gaps (C, B12, D, Omega-3) only if absent.

✅ 5. Verdict

  • Rating: Good / Okay with tweaks / Not ideal / Avoid
  • Keep: what's working.
  • Fix: specific ingredient to add, remove, or swap — with the reason. If amino acids are incomplete, name what to add. If an incompatible pair exists, say which one to drop or separate. If a nutrient is missing, name the exact ingredient that fills it.
  • Bottom line: one sentence.

Output Rules

  • Max 2–3 bullets per section. If there's nothing meaningful to say in a section, write "No issues" and move on.
  • Every "con" must have a corresponding fix in the Verdict. Don't flag a problem without solving it.
  • Ingredient suggestions must be practical and specific: not "add protein" but "add 2 tbsp hemp seeds" or "swap curd for Greek yogurt".
  • No research dumps. If a concern is minor, skip it.
  • If the user has stated a diet or fitness goal (e.g. vegetarian, high-protein, cutting), factor it in when relevant.

Example Trigger Phrases

  • "I'm eating rice, rajma, and curd — is this fine?"
  • "Check this: peanut butter + banana + oat smoothie"
  • "Had paneer with lemon juice, any issues?"
  • "Does this combo work: tofu stir-fry with broccoli and soy sauce?"
  • "check this dish" / "is this combo good?" / "analyse this food"

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.