# Send ClawdBites to your agent Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually. ## Fast path - Download the package from Yavira. - Extract it into a folder your agent can access. - Paste one of the prompts below and point your agent at the extracted folder. ## Suggested prompts ### New install ```text I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete. ``` ### Upgrade existing ```text I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run. ``` ## Machine-readable fields ```json { "schemaVersion": "1.0", "item": { "slug": "clawdbites", "name": "ClawdBites", "source": "tencent", "type": "skill", "category": "内容创作", "sourceUrl": "https://clawhub.ai/kylelol/clawdbites", "canonicalUrl": "https://clawhub.ai/kylelol/clawdbites", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/clawdbites", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=clawdbites", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "README.md", "SKILL.md" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "slug": "clawdbites", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-29T07:28:22.024Z", "expiresAt": "2026-05-06T07:28:22.024Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=clawdbites", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=clawdbites", "contentDisposition": "attachment; filename=\"clawdbites-0.1.0.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "clawdbites" }, "scope": "item", "summary": "Item download looks usable.", "detail": "Yavira can redirect you to the upstream package for this item.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/clawdbites" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] } }, "links": { "detailUrl": "https://openagent3.xyz/skills/clawdbites", "downloadUrl": "https://openagent3.xyz/downloads/clawdbites", "agentUrl": "https://openagent3.xyz/skills/clawdbites/agent", "manifestUrl": "https://openagent3.xyz/skills/clawdbites/agent.json", "briefUrl": "https://openagent3.xyz/skills/clawdbites/agent.md" } } ``` ## Documentation ### Instagram Recipe Extractor Extract recipes from Instagram reels using a multi-layered approach: Caption parsing — Instant, check description first Audio transcription — Whisper (local, no API key) Frame analysis — Vision model for on-screen text No Instagram login required. Works on public reels. ### When to Use User sends an Instagram reel link User mentions "recipe from Instagram" or "save this reel" User wants to extract recipe details from a video post ### How It Works (MANDATORY FLOW) ALWAYS follow this complete flow — do not stop after caption if instructions are missing: User sends Instagram reel URL Extract metadata using yt-dlp (--dump-json) Parse the caption for recipe details Check completeness: Does caption have BOTH ingredients AND instructions? ✅ YES: Present the recipe ❌ NO (missing instructions or incomplete): Automatically proceed to audio transcription — do NOT stop or ask the user If audio transcription needed: Download video: yt-dlp -o "/tmp/reel.mp4" "URL" Extract audio: ffmpeg -y -i /tmp/reel.mp4 -vn -acodec pcm_s16le -ar 16000 -ac 1 /tmp/reel.wav Transcribe: whisper /tmp/reel.wav --model base --output_format txt --output_dir /tmp Merge caption ingredients with audio instructions Present clean, formatted recipe (combining caption + audio as needed) User decides what to do (save to notes, add to wishlist, etc.) Completeness check heuristics: Has ingredients = contains 3+ quantity+item patterns (e.g., "1 cup flour", "2 lbs chicken") Has instructions = contains action verbs (blend, cook, bake, mix, pour, add) + sequence OR numbered steps ### Extraction Command yt-dlp --dump-json "https://www.instagram.com/reel/SHORTCODE/" 2>/dev/null Key fields from JSON output: description — The caption containing the recipe uploader — Creator's name channel — Creator's handle webpage_url — Original URL like_count — Popularity indicator ### Recipe Parsing Look for these patterns in the caption: Macros: "X Calories | Xg P | Xg C | Xg F" "Macros per serving" "Cal/Protein/Carbs/Fat" Ingredients: Lines starting with quantities (1 cup, 2 tbsp, 24oz) Lines with measurement units Emoji bullet points (🥩 🌽 🧀 etc.) Sections: "For the [component]:" "Ingredients:" "Instructions:" "Directions:" ### Output Format Present extracted recipe cleanly: ## [Recipe Name] *From @[handle]* **Macros (per serving):** X cal | Xg P | Xg C | Xg F ### Ingredients - [ingredient 1] - [ingredient 2] ... ### Instructions 1. [step 1] 2. [step 2] ... --- Source: [original URL] ### User Actions After Extraction Let the user decide what to do: "Save to my recipes" → Save to Apple Notes (if meal-planner skill available) "Add to wishlist" → Save to memory/recipe-wishlist.json "Just show me" → Display only, no save "Plan this for next week" → Hand off to meal-planner skill ### Wishlist Storage Optional storage for recipes user wants to try later: memory/recipe-wishlist.json: { "recipes": [ { "name": "Recipe Name", "source": "instagram", "sourceUrl": "https://instagram.com/reel/...", "handle": "@creator", "addedDate": "2026-01-26", "tried": false, "macros": { "calories": 585, "protein": 56, "carbs": 25, "fat": 28, "servings": 3 }, "ingredients": [...], "instructions": [...] } ] } ### Error Handling If yt-dlp fails: Check if URL is valid Instagram reel format May be a private account — inform user Suggest user paste caption text manually as fallback If no recipe found in caption (IMPORTANT): After extracting, scan the caption for recipe indicators: Ingredient quantities (numbers + units like oz, cups, tbsp, lbs) Recipe sections ("For the...", "Ingredients:", "Instructions:") Cooking verbs (bake, cook, sauté, mix, combine) Macro information (calories, protein, carbs, fat) If none found, tell the user clearly: "I pulled the caption but it doesn't look like the recipe is there — it might just be a teaser or the recipe is only shown in the video itself. Here's what the caption says: [show caption] A few options: Check the comments — sometimes creators post recipes there Check their bio link — might lead to the full recipe Describe what you saw in the video and I can help find a similar recipe" Recipe detection heuristics: HAS_RECIPE if caption contains: - 3+ ingredient-like patterns (quantity + food item) - OR "recipe" + ingredient list - OR macro breakdown + ingredients - OR numbered/bulleted instructions NO_RECIPE if caption is: - Mostly hashtags - Just a description/teaser - Under 100 characters - No quantities or measurements ### Integration with meal-planner The meal-planner skill can reference this skill: When planning meals, check wishlist for untried recipes Suggest wishlist recipes that match pantry items Mark recipes as "tried" after they're used in a meal plan ### Audio Transcription (V2) — MANDATORY FALLBACK When caption is missing instructions, ALWAYS transcribe the audio automatically. Do not stop and ask the user — just do it. This is the most common case since creators often put ingredients in captions but speak the instructions. Step 1: Download video yt-dlp -o "/tmp/reel.mp4" "https://instagram.com/reel/XXX" Step 2: Extract audio ffmpeg -i /tmp/reel.mp4 -vn -acodec pcm_s16le -ar 16000 -ac 1 /tmp/reel.wav Step 3: Transcribe with Whisper /Users/kylekirkland/Library/Python/3.14/bin/whisper /tmp/reel.wav --model base --output_format txt --output_dir /tmp Step 4: Parse transcript for recipe Look for cooking instructions, ingredients mentioned verbally. ### Inference for Missing Measurements ALWAYS infer quantities when not provided. Never present a recipe without amounts — estimate based on context and standard package sizes. ### Vague Language → Specific Amounts What they sayInfer"some chicken"~1 lb"a bit of garlic"2-3 cloves"handful of spinach"~2 cups"drizzle of oil"1-2 tbsp"season to taste"½ tsp salt, ¼ tsp pepper"splash of soy sauce"1-2 tbsp"a few tablespoons"2-3 tbsp"some rice"1 cup dry"cheese on top"½ - 1 cup shredded"diced onion"1 medium onion"bell peppers"2 peppers ### Standard Package Sizes (when item mentioned without amount) IngredientStandard PackageInferPuff pastry17oz sheet1 sheetGround beef/turkey1 lb pack1 lbChicken breast~1.5 lb pack1.5 lbsSausage links14oz / 4-5 links1 packageBacon12oz / 12 slices½ package (6 slices)Shredded cheese8oz bag1-2 cupsTortillas8-10 count1 packageCanned beans15oz can1 canBroth/stock32oz carton1-2 cupsPasta16oz box8oz (half box)Rice2 lb bag1-2 cups dry ### Context-Aware Scaling By recipe type: Stir fry for 2 → 1 lb protein, 4 cups veggies Soup/stew → 1.5-2 lbs protein, 4 cups broth Sheet pan meal → 1.5 lbs protein, 3-4 cups veggies Appetizers → smaller portions, estimate ~12-15 pieces per batch By servings mentioned: "Serves 4" → Scale standard amounts for 4 "Meal prep for the week" → Assume 5-8 servings No servings mentioned → Default to 4 servings By protein target (if user has macro goals): 40-50g protein per serving → ~6-8oz cooked meat per portion Scale recipe protein accordingly ### Output Format Always present inferred amounts clearly: ### Ingredients - 1 lb ground turkey *(estimated)* - 1 medium onion, diced *(estimated)* - 2 cups broth *(estimated based on typical soup)* Mark inferred quantities with (estimated) so user knows what came from the source vs inference. ### Combined Extraction Flow 1. TRY CAPTION (instant) └── yt-dlp --dump-json → parse description └── Recipe found? → DONE ✅ └── Check for "pinned" / "in comments" / "check comments" → FLAG 2. IF FLAGGED: CHECK FOR CREATOR COMMENT └── Look through comments for creator's username └── If creator comment found with recipe → DONE ✅ └── If not found → continue + notify user 3. TRY AUDIO (30-60 sec) └── Download video └── Extract audio with ffmpeg └── Transcribe with Whisper (base model) └── Parse transcript for recipe └── Infer missing measurements └── Recipe found? → DONE ✅ 4. PRESENT RESULTS + PROMPT IF NEEDED └── Show what was extracted from audio └── If "pinned" was flagged, tell user: "The creator mentioned the full recipe is pinned in the comments. I extracted what I could from the audio, but if you want the exact measurements, paste the pinned comment here and I'll merge it with what I found." 5. TRY FRAME ANALYSIS (if audio incomplete) └── Extract 5-8 key frames with ffmpeg └── Send to Claude vision └── Ask: "Extract any recipe text, ingredients, or measurements shown" └── Merge findings with audio transcript 6. FALLBACK (nothing found) └── Inform user: "Recipe wasn't in caption or audio/video" └── Offer: search for similar recipe based on video title/description ### Frame Analysis Extract key frames and analyze with vision model. Extract frames: # Extract 1 frame every 5 seconds ffmpeg -i /tmp/reel.mp4 -vf "fps=1/5" /tmp/frame_%02d.jpg # Or extract specific number of frames evenly distributed ffmpeg -i /tmp/reel.mp4 -vf "select='not(mod(n,30))'" -vsync vfr /tmp/frame_%02d.jpg Send to vision model: Use Claude's image analysis to read each frame: Recipe cards / title screens Ingredient lists shown on screen Measurements in text overlays Step-by-step instructions displayed Vision prompt: Analyze this frame from a cooking video. Extract any: - Recipe name or title - Ingredients with quantities - Cooking instructions - Nutritional information / macros - Any other recipe-related text shown If no recipe text is visible, respond with "No recipe text found." Merge strategy: Audio transcript = primary source (spoken instructions) Frame analysis = supplement (exact measurements, recipe cards) Combine both, prefer specific measurements from visual over inferred from audio ### Pinned Comment Detection Scan caption for these phrases (case-insensitive): "recipe pinned" "pinned in comments" "check comments" "in the comments" "comment below" "recipe below" "full recipe in comments" If detected, flag and notify user after extraction: "Heads up — the creator said the recipe is pinned in the comments. I got what I could from the audio, but yt-dlp can't access pinned comments without login. If you want the exact recipe, copy the pinned comment and send it to me — I'll format it properly." ### Requirements yt-dlp — brew install yt-dlp ffmpeg — brew install ffmpeg whisper — pip3 install openai-whisper (runs locally, no API key) No Instagram login required for public reels ## Trust - Source: tencent - Verification: Indexed source record - Publisher: kylelol - Version: 0.1.0 ## Source health - Status: healthy - Item download looks usable. - Yavira can redirect you to the upstream package for this item. - Health scope: item - Reason: direct_download_ok - Checked at: 2026-04-29T07:28:22.024Z - Expires at: 2026-05-06T07:28:22.024Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/clawdbites) - [Send to Agent page](https://openagent3.xyz/skills/clawdbites/agent) - [JSON manifest](https://openagent3.xyz/skills/clawdbites/agent.json) - [Markdown brief](https://openagent3.xyz/skills/clawdbites/agent.md) - [Download page](https://openagent3.xyz/downloads/clawdbites)