[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6PWBPT068DKGAPH8DV8H3MY":3,"skill-same:01M6PWBPT068DKGAPH8DV8H3MY":96},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":29,"publishedAt":51,"linkOnly":52,"markdownContent":53,"markdownBody":54,"frontMatter":55,"refName":66,"commitSha":67,"skillDirectory":68,"forksCount":69,"repositoryHtmlUrl":70,"repositoryHomepageUrl":71,"ownerHtmlUrl":72,"ownerBlogUrl":73,"ownerDescription":74,"updatedAt":75,"install":76,"resources":89},"01M6PWBPT068DKGAPH8DV8H3MY","gpt-image-2-6",null,"Guide to OpenAI's GPT Image 2.6 on varg (gpt_image_2_6) and the entry point to the GPT Image 2.6 skill set: Flare vs Sunburst, quality vs reasoning_effort, sizes and aspect presets, what fal rejects (xhigh and max effort, SVG, over 16 GIF frames), measured prices, failure modes, the exact varg MCP and REST calls, and prompt recipes for the text-heavy layouts people shared on X: infographic, product launch poster, photo to editorial travel print, photo to Baroque gallery poster, landmark postcard, character turnaround sheet, storyboard sheet and low-res to clean upscale, each credited to its author. Use when someone asks for GPT Image 2.6, gpt-image-2.6, Flare or Sunburst, wants an infographic, poster, art print, character sheet or storyboard with readable text, or asks how to prompt, size or price this model. Not for looping GIFs (gpt-image-gif), sticker packs (gpt-image-sticker-pack), game sprite sheets (gpt-image-sprite-sheet), circle-and-arrow edits (gpt-image-markup-edit) or video (varg-ai).","hashgraph-online\u002Fawesome-codex-plugins","hashgraph-online","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160371962?v=4","01M6CNB6NRJVNNGN14TR01Q6D3","HOL (Hashgraph Online)","01M6JT1HSKKG9V68KQAQGBA7XP",1575,"MIT","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fgpt-image-2-6\u002FSKILL.md",[18,23,26],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":27,"categoryName":28,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50],"image","gpt","gpt image 2 6","gpt image 2","when","MCP","prices","people","how to","shared","sticker","infographic","clean","Art","fal","model","text","Bash","Video","api","SET","2026-11-10 10:12:30",false,"---\nname: gpt-image-2-6\ndescription: >-\n  Guide to OpenAI's GPT Image 2.6 on varg (gpt_image_2_6) and the entry point to the GPT Image 2.6\n  skill set: Flare vs Sunburst, quality vs reasoning_effort, sizes and aspect presets, what fal\n  rejects (xhigh and max effort, SVG, over 16 GIF frames), measured prices, failure modes, the exact varg MCP and REST calls, and prompt recipes for the\n  text-heavy layouts people shared on X: infographic, product launch poster, photo to editorial\n  travel print, photo to Baroque gallery poster, landmark postcard, character turnaround sheet,\n  storyboard sheet and low-res to clean upscale, each credited to its author. Use when someone asks\n  for GPT Image 2.6, gpt-image-2.6, Flare or Sunburst, wants an infographic, poster, art print,\n  character sheet or storyboard with readable text, or asks how to prompt, size or price this model.\n  Not for looping GIFs (gpt-image-gif), sticker packs (gpt-image-sticker-pack), game sprite sheets\n  (gpt-image-sprite-sheet), circle-and-arrow edits (gpt-image-markup-edit) or video (varg-ai).\nlicense: MIT\nmetadata:\n  author: vargHQ\n  version: \"1.0.0\"\n  openclaw:\n    requires:\n      anyBins:\n        - curl\n    homepage: https:\u002F\u002Fvarg.ai\u002Fhow-to\ncompatibility: >-\n  Needs a VARG_API_KEY with curl (see the varg-ai skill) or the varg MCP connection\n  (https:\u002F\u002Fmcp.varg.ai\u002Fmcp). One image costs 3-6 credits on varg (measured 2026-11-05).\nallowed-tools: Bash(curl:*) Bash(jq:*) Read Write Edit\n---\n\n# GPT Image 2.6 on varg\n\nOpenAI released GPT Image 2.6 on 2026-11-04: animated GIF output, two API models (Flare and Sunburst)\nthat \"generate images 50% faster than before\", image markup, SVG export and a complexity control\n([@OpenAIDevs](https:\u002F\u002Fx.com\u002FOpenAIDevs\u002Fstatus\u002F2118124753340756055),\n[@OpenAI](https:\u002F\u002Fx.com\u002FOpenAI\u002Fstatus\u002F2118124964197114039)). The token price is the same as 2.5: $30 per\nmillion image output tokens, $8 per million image input tokens, $5 per million text input tokens\n([@dotey](https:\u002F\u002Fx.com\u002Fdotey\u002Fstatus\u002F2118127825186177270)). On varg it is `gpt_image_2_6`, live since\n2026-11-04.\n\nOn the LMArena boards on launch night, Sunburst (medium) was #2 in text-to-image (1409) and #3 in\nimage edit (1476); Flare (medium) was #4 (1384) and #5 (1462)\n([@arena](https:\u002F\u002Fx.com\u002Farena\u002Fstatus\u002F2118139063345787124)).\n\nThis skill is the model guide. The other four skills in the set:\n\n| Skill | For |\n|---|---|\n| [gpt-image-gif](..\u002Fgpt-image-gif\u002F) | A still, mascot, logo or prompt → a looping GIF; the sprite-sheet pixel budget; GIF → WebP\u002FMP4 |\n| [gpt-image-sticker-pack](..\u002Fgpt-image-sticker-pack\u002F) | A photo or character → 6-8 animated stickers for Telegram, WhatsApp, LINE, WeChat, Discord, Slack |\n| [gpt-image-sprite-sheet](..\u002Fgpt-image-sprite-sheet\u002F) | Game sprite sheets → frames, GIF and a JSON atlas for Phaser or Godot |\n| [gpt-image-markup-edit](..\u002Fgpt-image-markup-edit\u002F) | Circles, arrows and notes on a transparent layer → an edit that touches only the marked places |\n\n## 1. Flare or Sunburst\n\n| | Flare (default) | Sunburst |\n|---|---|---|\n| `model` | `gpt_image_2_6` (text only → `fal:openai\u002Fgpt-image-2.6\u002Fflare\u002Ftext-to-image`; with `files` → `...\u002Fflare\u002Fedit`) | pin `fal:openai\u002Fgpt-image-2.6\u002Fsunburst\u002Ftext-to-image` or `fal:openai\u002Fgpt-image-2.6\u002Fsunburst\u002Fedit` |\n| Time | ~10 s (measured 2026-11-05 on varg) | ~49 s (measured 2026-11-05 on varg) |\n| Price | same as Sunburst | same as Flare |\n| OpenAI says | \"Flare also improves layout quality for posters, product imagery, and other professional visuals\" ([OpenAI blog, quoted by @TheRealAdamG](https:\u002F\u002Fx.com\u002FTheRealAdamG\u002Fstatus\u002F2118128332025836030)) | \"At medium or high quality, Sunburst keeps details more consistent from one edit to the next\" ([@OpenAIDevs](https:\u002F\u002Fx.com\u002FOpenAIDevs\u002Fstatus\u002F2118124753340756055)) |\n| Use it for | Drafts, posters, product shots, most stills, GIFs | A chain of edits on one image; the final pass of a dense layout once Flare has the layout right |\n\nFlare is the default. Pin Sunburst only when you will edit the same image again and again. Edits take\nup to 16 reference images (fal: \"A maximum of 16 images are allowed\").\n\n## 2. quality and reasoning_effort are two different dials\n\n- **`quality`** (`low`, `medium`, `high`, `auto`; varg default `high`) sets render detail and price.\n- **`reasoning_effort`** (`low`, `medium`, `high`) is how long the model plans before drawing; OpenAI\n  calls it complexity. OpenAI: \"Lower complexity can suit focused edits, such as changing a background\n  or a sign. Higher complexity can help with dense text, complex layouts, and relationships between\n  objects\" ([OpenAI image guide](https:\u002F\u002Fdevelopers.openai.com\u002Fapi\u002Fdocs\u002Fguides\u002Fimage-generation)).\n  fal: \"Higher settings increase detail, latency, and token usage.\" `xhigh` and `max` are in the\n  schema, but fal rejected both (measured 2026-11-05 on varg). We did not measure whether effort\n  changes the varg price.\n\n| Job | quality | reasoning_effort |\n|---|---|---|\n| Draft, layout test | `low` (3 credits) | `low` |\n| Poster, product shot, postcard | `high` | `medium` |\n| Infographic, storyboard, character sheet (many labels) | `high` | `high` |\n| One focused edit (swap a sign, a background) | `high` | `low` (OpenAI's advice for edits, [@OpenAIDevs](https:\u002F\u002Fx.com\u002FOpenAIDevs\u002Fstatus\u002F2118124761867845847)) |\n\nBoth go in `provider_options.fal`.\n\n## 3. Sizes and aspect ratios\n\n| `aspect_ratio` | fal preset | Size we got |\n|---|---|---|\n| `4:3` (default) | landscape_4_3 | 1024×768 |\n| `1:1` | square_hd | 1024×1024 |\n| `3:4` | portrait_4_3 | 768×1024 |\n| `16:9` | landscape_16_9 (1024×576) | 1088×608 |\n| `9:16` | portrait_16_9 | not measured |\n\nSizes from our 2026-11-05 outputs on varg. 16:9 came back as 1088×608, likely because 1024×576\n(589,824 px) is under the 655,360 px floor. For any other size, pass\n`provider_options.fal.image_size: {\"width\": W, \"height\": H}`: both sides multiples of 16, longest edge\n≤ 3840, total 655,360-8,294,400 px (fal schema). Bigger images cost more: fal billed 10.7¢ for one\n2048×2048 high image (measured 2026-11-05), so price it with `POST \u002Fv2\u002Festimate` before you go above\n1024. In ChatGPT a 16:9 GIF request came back square for\n[@joseamijares](https:\u002F\u002Fx.com\u002Fjoseamijares\u002Fstatus\u002F2118166783500980721); in the API, always set the\nsize yourself.\n\n## 4. What works and what fal rejects\n\n| Option | Status (measured 2026-11-05 on varg unless noted) |\n|---|---|\n| `output_format`: `png`, `jpeg`, `webp` | works |\n| `output_format: \"gif\"` | works on text-to-image and edit; 2-16 frames; see [gpt-image-gif](..\u002Fgpt-image-gif\u002F) |\n| `output_format: \"svg\"` | in the schema, but fal rejected every SVG prompt at launch. For vector logos use `ideogram_vector` (varg-ai models list) |\n| `reasoning_effort`: `xhigh`, `max` | in the schema, rejected. Use `high` |\n| `frame_count` above 16 | schema allows 64, rejected |\n| GIF with `aspect_ratio: \"1:1\"` (1024×1024 frames) | rejected for every frame count we tried (6, 8, 9, 12): the sprite sheet would pass 3840 px or the pixel budget |\n| `background: \"transparent\"` | works for PNG, WebP and GIF (our GIF stickers came back 54-62% transparent pixels) |\n| `markup_image_url` | works on the edit route; see [gpt-image-markup-edit](..\u002Fgpt-image-markup-edit\u002F) |\n| `markup_image_url` together with `mask_url` | not allowed (fal docs) |\n| `num_images` 1-10 | for GIFs, \"all frames of all outputs share the request's pixel budget\" (fal) |\n\nEvery PNG and GIF the model returned in our tests carried a C2PA content-credentials block (17 files,\nchecked 2026-11-05). None of the files made by this set's scripts kept it (checked the same day); keep\nthe original if you need the provenance.\n\n## 5. Prices (measured 2026-11-05 on varg)\n\n| Request | varg credits | fal billed varg |\n|---|---|---|\n| 1 image, `quality: low` | 3 | 2.50¢ (1024²) |\n| 1 image, `quality: medium` | 5 | 4.37¢ (1024²) |\n| 1 image, `quality: high` (default) | 6 | 5.30¢ (1024²), 3.64¢ (1024×768) |\n| Edit | the above + 1 per reference image | |\n| GIF | the same as one image at that quality: 6-7 at high (7 on the edit route with one reference), 3 at low (12 frames of 768²) | 4.78¢ (9 frames, high) |\n| 2048×2048, high | estimate first | 10.7¢ |\n| Failed job | 0 | |\n\nCheck any request before you run it: `POST https:\u002F\u002Fapi.varg.ai\u002Fv2\u002Festimate` with the same body, or\n`estimate_cost` on the MCP. Follow the spend rules in the varg-ai skill (a cap, approved models,\nestimate before every paid call).\n\n## 6. The calls\n\n**MCP** (`https:\u002F\u002Fmcp.varg.ai\u002Fmcp`, OAuth, no key):\n\n```json\ncall_tool({\n  \"tool\": \"image\",\n  \"input\": {\n    \"model\": \"gpt_image_2_6\",\n    \"prompt\": \"…\",\n    \"aspect_ratio\": \"3:4\",\n    \"provider_options\": {\"fal\": {\"quality\": \"high\", \"reasoning_effort\": \"medium\"}}\n  },\n  \"wait\": true\n})\n```\n\nIt returns `url`, `job_id` and `cost_credits`. An edit adds `\"files\": [{\"url\": \"https:\u002F\u002Fs3.varg.ai\u002F…\"}]`\nto `input`. To use a local file, upload it first: `create_upload({\"media_type\": \"image\u002Fpng\", \"size\":\n\u003Cbytes>})`, then `curl -X PUT -H \"Content-Type: application\u002Foctet-stream\" --data-binary @photo.png\n\"https:\u002F\u002Fapi.varg.ai$PROXY_URL\"` with the `proxy_url` it returned; the answer has the file's\n`public_url`.\n\n**REST** (needs `$VARG_API_KEY`, see the varg-ai skill):\n\n```bash\n# upload a local image -> {\"url\": \"https:\u002F\u002Fs3.varg.ai\u002F...\", ...}\ncurl -s -X POST https:\u002F\u002Fapi.varg.ai\u002Fv2\u002Ffiles -H \"Authorization: Bearer $VARG_API_KEY\" \\\n  -H \"Content-Type: image\u002Fpng\" --data-binary @photo.png\n\n# text to image (Flare)\ncurl -s -X POST https:\u002F\u002Fapi.varg.ai\u002Fv2\u002Fimage -H \"Authorization: Bearer $VARG_API_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" -d '{\n  \"model\": \"gpt_image_2_6\",\n  \"prompt\": \"…\",\n  \"aspect_ratio\": \"3:4\",\n  \"provider_options\": {\"fal\": {\"quality\": \"high\", \"reasoning_effort\": \"medium\"}}\n}'\n\n# edit on Sunburst, custom size\ncurl -s -X POST https:\u002F\u002Fapi.varg.ai\u002Fv2\u002Fimage -H \"Authorization: Bearer $VARG_API_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" -d '{\n  \"model\": \"fal:openai\u002Fgpt-image-2.6\u002Fsunburst\u002Fedit\",\n  \"prompt\": \"…\",\n  \"files\": [{\"url\": \"https:\u002F\u002Fs3.varg.ai\u002Ffiles\u002F…\u002Fphoto.png\"}],\n  \"provider_options\": {\"fal\": {\"quality\": \"high\", \"image_size\": {\"width\": 1536, \"height\": 864}}}\n}'\n\n# each image call answers 202 with {\"id\": \"job_…\"}; poll until \"completed\"; the image is output.outputs[0].url\ncurl -s https:\u002F\u002Fapi.varg.ai\u002Fv2\u002Fjobs\u002FJOB_ID -H \"Authorization: Bearer $VARG_API_KEY\"\n```\n\nModel spec with every option: https:\u002F\u002Fvarg.ai\u002Fmodels\u002Fgpt_image_2_6.md. JSON schema (no key):\nhttps:\u002F\u002Fapi.varg.ai\u002Fv2\u002Ftools\u002Fimage?model=gpt_image_2_6.\n\n## 7. Prompting text-heavy layouts\n\nWhat the recipes below have in common:\n\n- Put every word that must appear in quotes, and keep each one short (\"Bright citrus\", not a sentence).\n- Name the layout before the content: \"3×2 grid\", \"top 75% \u002F bottom 25%\", \"sidebar on the left\".\n- Name the label words you want (\"FRONT, 3\u002F4 VIEW, SIDE VIEW…\") and say \"minimal clean labels\".\n- End with what to leave out (\"no other text\", \"no logos\", \"no photorealistic background\").\n- For dense pages use `reasoning_effort: \"high\"`; for a photo restyle `medium` is enough.\n- Read every word in the output before you use it. Fix one wrong word with a markup edit\n  ([gpt-image-markup-edit](..\u002Fgpt-image-markup-edit\u002F)), not a full regeneration.\n\n## 8. Recipes\n\nFull prompt templates, settings and notes: [references\u002Frecipes.md](references\u002Frecipes.md). Most community\nprompts were written for GPT Image 2.5; our examples show each one on 2.6. Examples were made on varg\non 2026-11-04\u002F05 with `gpt_image_2_6`.\n\n| Recipe | Prompt by | Our example | Settings |\n|---|---|---|---|\n| Infographic (field-guide page) | [@iamsofiaijaz](https:\u002F\u002Fx.com\u002Fiamsofiaijaz\u002Fstatus\u002F2113510238846672945) | [Red Fox](https:\u002F\u002Fs3.varg.ai\u002Ffiles\u002F194b94d0-58ff-4e8b-91de-4f1959d04013\u002Ffile_99da5c60e85b.png) | 4:3, high, effort high |\n| Product launch poster | varg (written for this skill) | [SUMMIT ROAST](https:\u002F\u002Fs3.varg.ai\u002Ffiles\u002F194b94d0-58ff-4e8b-91de-4f1959d04013\u002Ffile_143c5129c4b7.png) (fictional brand) | 3:4, high |\n| Photo → editorial travel print | [@Naiknelofar788](https:\u002F\u002Fx.com\u002FNaiknelofar788\u002Fstatus\u002F2101161664892829838) | [photo](https:\u002F\u002Fs3.varg.ai\u002Ffiles\u002F194b94d0-58ff-4e8b-91de-4f1959d04013\u002Ffile_de945fe48c84.png) → [LISBON print](https:\u002F\u002Fs3.varg.ai\u002Ffiles\u002F194b94d0-58ff-4e8b-91de-4f1959d04013\u002Ffile_c1beb16c718f.png) | edit, 3:4 |\n| Photo → Baroque gallery poster | [@Goodmanprotocol](https:\u002F\u002Fx.com\u002FGoodmanprotocol\u002Fstatus\u002F2118193088128745875) | [photo](https:\u002F\u002Fs3.varg.ai\u002Ffiles\u002F194b94d0-58ff-4e8b-91de-4f1959d04013\u002Ffile_17855ee4e472.png) → [poster](https:\u002F\u002Fs3.varg.ai\u002Ffiles\u002F194b94d0-58ff-4e8b-91de-4f1959d04013\u002Ffile_d55052e95ef9.png) | edit, 3:4 |\n| Landmark postcard | [@Maercihh](https:\u002F\u002Fx.com\u002FMaercihh\u002Fstatus\u002F2117592215602233781) | [bridge in fog](https:\u002F\u002Fs3.varg.ai\u002Ffiles\u002F194b94d0-58ff-4e8b-91de-4f1959d04013\u002Ffile_4671ad66f76a.png) | 16:9, high |\n| Character turnaround sheet | [@EvoLinkAi](https:\u002F\u002Fx.com\u002FEvoLinkAi\u002Fstatus\u002F2107436379575840895) | [Mara](https:\u002F\u002Fs3.varg.ai\u002Ffiles\u002F194b94d0-58ff-4e8b-91de-4f1959d04013\u002Ffile_92817f364ac7.png) | 16:9, high, effort high |\n| Storyboard sheet | varg, idea by [@EHuanglu](https:\u002F\u002Fx.com\u002FEHuanglu\u002Fstatus\u002F2098411370815643837) | [THE LAST LIGHT](https:\u002F\u002Fs3.varg.ai\u002Ffiles\u002F194b94d0-58ff-4e8b-91de-4f1959d04013\u002Ffile_d505f9aceadb.png) | 16:9, high, effort high |\n| Low-res → clean upscale | [@k_matsumaru](https:\u002F\u002Fx.com\u002Fk_matsumaru\u002Fstatus\u002F2097506834659893340) | [272×152 noisy](https:\u002F\u002Fs3.varg.ai\u002Ffiles\u002F194b94d0-58ff-4e8b-91de-4f1959d04013\u002Ffile_f395c2486a58.jpg) → [1536×864](https:\u002F\u002Fs3.varg.ai\u002Ffiles\u002F194b94d0-58ff-4e8b-91de-4f1959d04013\u002Ffile_39f3af099f61.png) | edit, `image_size` 1536×864 |\n\n## 9. Failure → fix\n\n| What you see | Fix |\n|---|---|\n| A face changes from the second edit on; saturation drifts ([@k_matsumaru](https:\u002F\u002Fx.com\u002Fk_matsumaru\u002Fstatus\u002F2118186638228816322)); edit wear shows from about the third edit ([@NeneneAI](https:\u002F\u002Fx.com\u002FNeneneAI\u002Fstatus\u002F2118165875979407628)) | Edit from the original each time, put all changes in one pass (markup helps). Measured on a face (2026-11-05): five chained edits fell from 0.74 to 0.48 face similarity on Flare and from 0.73 to 0.29 on Sunburst with `reasoning_effort: low`; fresh calls from the character sheet averaged 0.77. Pinning Sunburst did not cure the chain: [character-passport\u002Freferences\u002Fgpt-image.md](..\u002Fcharacter-passport\u002Freferences\u002Fgpt-image.md) |\n| Sepia wash, muddy noise ([@PJaccetturo](https:\u002F\u002Fx.com\u002FPJaccetturo\u002Fstatus\u002F2118146909340868789)) | Not fixed by a setting we know of. Compare with `nano_banana_2_1` for that shot |\n| \"Pretty doll faces\", a 2015 Tumblr look next to Nano Banana's camera-roll realism ([@flowersslop](https:\u002F\u002Fx.com\u002Fflowersslop\u002Fstatus\u002F2118140335687930256)) | For casual phone-photo realism use `nano_banana_2_1` |\n| Pencil and other media looks are cleaner but less like the medium than 2.5 ([@munou_ac](https:\u002F\u002Fx.com\u002Fmunou_ac\u002Fstatus\u002F2118194696757424613)) | Try `gpt_image_2_5` for hand-made texture |\n| Pixel art fails ([@Angaisb_](https:\u002F\u002Fx.com\u002FAngaisb_\u002Fstatus\u002F2118126997855674470)) | Ask for flat cartoon art and pixelate it yourself, or use another model |\n| A misspelled or extra word | Shorter quoted text, `reasoning_effort: \"high\"`, then fix single words with a markup edit |\n| SVG, `xhigh`, `max`, more than 16 frames, square 1024 GIF frames | Rejected by fal (section 4) |\n| A dance prompt blocked by output moderation ([@KakiponzuX](https:\u002F\u002Fx.com\u002FKakiponzuX\u002Fstatus\u002F2118183717512306775)) | Reword the motion; a waving prompt passed in the same test |\n\n## Tested\n\nMeasured on varg on 2026-11-05: route times (Flare ~10 s, Sunburst ~49 s), the prices in section 5,\nthe rejections in section 4, 16:9 at 1088×608, and every example linked above (made with this skill's\nrecipes; we did not keep the exact filled-in prompts).\n\n## Related skills\n\n`gpt-image-gif`, `gpt-image-sticker-pack`, `gpt-image-sprite-sheet`, `gpt-image-markup-edit` (this set);\n`varg-ai` (setup, keys, every model and price); `varg-character-design` and `character-passport`\n(character sheets for video); `kling-4-prompting` (stills as key frames for video).\n","# GPT Image 2.6 on varg\n\nOpenAI released GPT Image 2.6 on 2026-11-04: animated GIF output, two API models (Flare and Sunburst)\nthat \"generate images 50% faster than before\", image markup, SVG export and a complexity control\n([@OpenAIDevs](https:\u002F\u002Fx.com\u002FOpenAIDevs\u002Fstatus\u002F2118124753340756055),\n[@OpenAI](https:\u002F\u002Fx.com\u002FOpenAI\u002Fstatus\u002F2118124964197114039)). The token price is the same as 2.5: $30 per\nmillion image output tokens, $8 per million image input tokens, $5 per million text input tokens\n([@dotey](https:\u002F\u002Fx.com\u002Fdotey\u002Fstatus\u002F2118127825186177270)). On varg it is `gpt_image_2_6`, live since\n2026-11-04.\n\nOn the LMArena boards on launch night, Sunburst (medium) was #2 in text-to-image (1409) and #3 in\nimage edit (1476); Flare (medium) was #4 (1384) and #5 (1462)\n([@arena](https:\u002F\u002Fx.com\u002Farena\u002Fstatus\u002F2118139063345787124)).\n\nThis skill is the model guide. The other four skills in the set:\n\n| Skill | For |\n|---|---|\n| [gpt-image-gif](..\u002Fgpt-image-gif\u002F) | A still, mascot, logo or prompt → a looping GIF; the sprite-sheet pixel budget; GIF → WebP\u002FMP4 |\n| [gpt-image-sticker-pack](..\u002Fgpt-image-sticker-pack\u002F) | A photo or character → 6-8 animated stickers for Telegram, WhatsApp, LINE, WeChat, Discord, Slack |\n| [gpt-image-sprite-sheet](..\u002Fgpt-image-sprite-sheet\u002F) | Game sprite sheets → frames, GIF and a JSON atlas for Phaser or Godot |\n| [gpt-image-markup-edit](..\u002Fgpt-image-markup-edit\u002F) | Circles, arrows and notes on a transparent layer → an edit that touches only the marked places |\n\n## 1. Flare or Sunburst\n\n| | Flare (default) | Sunburst |\n|---|---|---|\n| `model` | `gpt_image_2_6` (text only → `fal:openai\u002Fgpt-image-2.6\u002Fflare\u002Ftext-to-image`; with `files` → `...\u002Fflare\u002Fedit`) | pin `fal:openai\u002Fgpt-image-2.6\u002Fsunburst\u002Ftext-to-image` or `fal:openai\u002Fgpt-image-2.6\u002Fsunburst\u002Fedit` |\n| Time | ~10 s (measured 2026-11-05 on varg) | ~49 s (measured 2026-11-05 on varg) |\n| Price | same as Sunburst | same as Flare |\n| OpenAI says | \"Flare also improves layout quality for posters, product imagery, and other professional visuals\" ([OpenAI blog, quoted by @TheRealAdamG](https:\u002F\u002Fx.com\u002FTheRealAdamG\u002Fstatus\u002F2118128332025836030)) | \"At medium or high quality, Sunburst keeps details more consistent from one edit to the next\" ([@OpenAIDevs](https:\u002F\u002Fx.com\u002FOpenAIDevs\u002Fstatus\u002F2118124753340756055)) |\n| Use it for | Drafts, posters, product shots, most stills, GIFs | A chain of edits on one image; the final pass of a dense layout once Flare has the layout right |\n\nFlare is the default. Pin Sunburst only when you will edit the same image again and again. Edits take\nup to 16 reference images (fal: \"A maximum of 16 images are allowed\").\n\n## 2. quality and reasoning_effort are two different dials\n\n- **`quality`** (`low`, `medium`, `high`, `auto`; varg default `high`) sets render detail and price.\n- **`reasoning_effort`** (`low`, `medium`, `high`) is how long the model plans before drawing; OpenAI\n  calls it complexity. OpenAI: \"Lower complexity can suit focused edits, such as changing a background\n  or a sign. Higher complexity can help with dense text, complex layouts, and relationships between\n  objects\" ([OpenAI image guide](https:\u002F\u002Fdevelopers.openai.com\u002Fapi\u002Fdocs\u002Fguides\u002Fimage-generation)).\n  fal: \"Higher settings increase detail, latency, and token usage.\" `xhigh` and `max` are in the\n  schema, but fal rejected both (measured 2026-11-05 on varg). We did not measure whether effort\n  changes the varg price.\n\n| Job | quality | reasoning_effort |\n|---|---|---|\n| Draft, layout test | `low` (3 credits) | `low` |\n| Poster, product shot, postcard | `high` | `medium` |\n| Infographic, storyboard, character sheet (many labels) | `high` | `high` |\n| One focused edit (swap a sign, a background) | `high` | `low` (OpenAI's advice for edits, [@OpenAIDevs](https:\u002F\u002Fx.com\u002FOpenAIDevs\u002Fstatus\u002F2118124761867845847)) |\n\nBoth go in `provider_options.fal`.\n\n## 3. Sizes and aspect ratios\n\n| `aspect_ratio` | fal preset | Size we got |\n|---|---|---|\n| `4:3` (default) | landscape_4_3 | 1024×768 |\n| `1:1` | square_hd | 1024×1024 |\n| `3:4` | portrait_4_3 | 768×1024 |\n| `16:9` | landscape_16_9 (1024×576) | 1088×608 |\n| `9:16` | portrait_16_9 | not measured |\n\nSizes from our 2026-11-05 outputs on varg. 16:9 came back as 1088×608, likely because 1024×576\n(589,824 px) is under the 655,360 px floor. For any other size, pass\n`provider_options.fal.image_size: {\"width\": W, \"height\": H}`: both sides multiples of 16, longest edge\n≤ 3840, total 655,360-8,294,400 px (fal schema). Bigger images cost more: fal billed 10.7¢ for one\n2048×2048 high image (measured 2026-11-05), so price it with `POST \u002Fv2\u002Festimate` before you go above\n1024. In ChatGPT a 16:9 GIF request came back square for\n[@joseamijares](https:\u002F\u002Fx.com\u002Fjoseamijares\u002Fstatus\u002F2118166783500980721); in the API, always set the\nsize yourself.\n\n## 4. What works and what fal rejects\n\n| Option | Status (measured 2026-11-05 on varg unless noted) |\n|---|---|\n| `output_format`: `png`, `jpeg`, `webp` | works |\n| `output_format: \"gif\"` | works on text-to-image and edit; 2-16 frames; see [gpt-image-gif](..\u002Fgpt-image-gif\u002F) |\n| `output_format: \"svg\"` | in the schema, but fal rejected every SVG prompt at launch. For vector logos use `ideogram_vector` (varg-ai models list) |\n| `reasoning_effort`: `xhigh`, `max` | in the schema, rejected. Use `high` |\n| `frame_count` above 16 | schema allows 64, rejected |\n| GIF with `aspect_ratio: \"1:1\"` (1024×1024 frames) | rejected for every frame count we tried (6, 8, 9, 12): the sprite sheet would pass 3840 px or the pixel budget |\n| `background: \"transparent\"` | works for PNG, WebP and GIF (our GIF stickers came back 54-62% transparent pixels) |\n| `markup_image_url` | works on the edit route; see [gpt-image-markup-edit](..\u002Fgpt-image-markup-edit\u002F) |\n| `markup_image_url` together with `mask_url` | not allowed (fal docs) |\n| `num_images` 1-10 | for GIFs, \"all frames of all outputs share the request's pixel budget\" (fal) |\n\nEvery PNG and GIF the model returned in our tests carried a C2PA content-credentials block (17 files,\nchecked 2026-11-05). None of the files made by this set's scripts kept it (checked the same day); keep\nthe original if you need the provenance.\n\n## 5. Prices (measured 2026-11-05 on varg)\n\n| Request | varg credits | fal billed varg |\n|---|---|---|\n| 1 image, `quality: low` | 3 | 2.50¢ (1024²) |\n| 1 image, `quality: medium` | 5 | 4.37¢ (1024²) |\n| 1 image, `quality: high` (default) | 6 | 5.30¢ (1024²), 3.64¢ (1024×768) |\n| Edit | the above + 1 per reference image | |\n| GIF | the same as one image at that quality: 6-7 at high (7 on the edit route with one reference), 3 at low (12 frames of 768²) | 4.78¢ (9 frames, high) |\n| 2048×2048, high | estimate first | 10.7¢ |\n| Failed job | 0 | |\n\nCheck any request before you run it: `POST https:\u002F\u002Fapi.varg.ai\u002Fv2\u002Festimate` with the same body, or\n`estimate_cost` on the MCP. Follow the spend rules in the varg-ai skill (a cap, approved models,\nestimate before every paid call).\n\n## 6. The calls\n\n**MCP** (`https:\u002F\u002Fmcp.varg.ai\u002Fmcp`, OAuth, no key):\n\n```json\ncall_tool({\n  \"tool\": \"image\",\n  \"input\": {\n    \"model\": \"gpt_image_2_6\",\n    \"prompt\": \"…\",\n    \"aspect_ratio\": \"3:4\",\n    \"provider_options\": {\"fal\": {\"quality\": \"high\", \"reasoning_effort\": \"medium\"}}\n  },\n  \"wait\": true\n})\n```\n\nIt returns `url`, `job_id` and `cost_credits`. An edit adds `\"files\": [{\"url\": \"https:\u002F\u002Fs3.varg.ai\u002F…\"}]`\nto `input`. To use a local file, upload it first: `create_upload({\"media_type\": \"image\u002Fpng\", \"size\":\n\u003Cbytes>})`, then `curl -X PUT -H \"Content-Type: application\u002Foctet-stream\" --data-binary @photo.png\n\"https:\u002F\u002Fapi.varg.ai$PROXY_URL\"` with the `proxy_url` it returned; the answer has the file's\n`public_url`.\n\n**REST** (needs `$VARG_API_KEY`, see the varg-ai skill):\n\n```bash\n# upload a local image -> {\"url\": \"https:\u002F\u002Fs3.varg.ai\u002F...\", ...}\ncurl -s -X POST https:\u002F\u002Fapi.varg.ai\u002Fv2\u002Ffiles -H \"Authorization: Bearer $VARG_API_KEY\" \\\n  -H \"Content-Type: image\u002Fpng\" --data-binary @photo.png\n\n# text to image (Flare)\ncurl -s -X POST https:\u002F\u002Fapi.varg.ai\u002Fv2\u002Fimage -H \"Authorization: Bearer $VARG_API_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" -d '{\n  \"model\": \"gpt_image_2_6\",\n  \"prompt\": \"…\",\n  \"aspect_ratio\": \"3:4\",\n  \"provider_options\": {\"fal\": {\"quality\": \"high\", \"reasoning_effort\": \"medium\"}}\n}'\n\n# edit on Sunburst, custom size\ncurl -s -X POST https:\u002F\u002Fapi.varg.ai\u002Fv2\u002Fimage -H \"Authorization: Bearer $VARG_API_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" -d '{\n  \"model\": \"fal:openai\u002Fgpt-image-2.6\u002Fsunburst\u002Fedit\",\n  \"prompt\": \"…\",\n  \"files\": [{\"url\": \"https:\u002F\u002Fs3.varg.ai\u002Ffiles\u002F…\u002Fphoto.png\"}],\n  \"provider_options\": {\"fal\": {\"quality\": \"high\", \"image_size\": {\"width\": 1536, \"height\": 864}}}\n}'\n\n# each image call answers 202 with {\"id\": \"job_…\"}; poll until \"completed\"; the image is output.outputs[0].url\ncurl -s https:\u002F\u002Fapi.varg.ai\u002Fv2\u002Fjobs\u002FJOB_ID -H \"Authorization: Bearer $VARG_API_KEY\"\n```\n\nModel spec with every option: https:\u002F\u002Fvarg.ai\u002Fmodels\u002Fgpt_image_2_6.md. JSON schema (no key):\nhttps:\u002F\u002Fapi.varg.ai\u002Fv2\u002Ftools\u002Fimage?model=gpt_image_2_6.\n\n## 7. Prompting text-heavy layouts\n\nWhat the recipes below have in common:\n\n- Put every word that must appear in quotes, and keep each one short (\"Bright citrus\", not a sentence).\n- Name the layout before the content: \"3×2 grid\", \"top 75% \u002F bottom 25%\", \"sidebar on the left\".\n- Name the label words you want (\"FRONT, 3\u002F4 VIEW, SIDE VIEW…\") and say \"minimal clean labels\".\n- End with what to leave out (\"no other text\", \"no logos\", \"no photorealistic background\").\n- For dense pages use `reasoning_effort: \"high\"`; for a photo restyle `medium` is enough.\n- Read every word in the output before you use it. Fix one wrong word with a markup edit\n  ([gpt-image-markup-edit](..\u002Fgpt-image-markup-edit\u002F)), not a full regeneration.\n\n## 8. Recipes\n\nFull prompt templates, settings and notes: [references\u002Frecipes.md](references\u002Frecipes.md). Most community\nprompts were written for GPT Image 2.5; our examples show each one on 2.6. Examples were made on varg\non 2026-11-04\u002F05 with `gpt_image_2_6`.\n\n| Recipe | Prompt by | Our example | Settings |\n|---|---|---|---|\n| Infographic (field-guide page) | [@iamsofiaijaz](https:\u002F\u002Fx.com\u002Fiamsofiaijaz\u002Fstatus\u002F2113510238846672945) | [Red Fox](https:\u002F\u002Fs3.varg.ai\u002Ffiles\u002F194b94d0-58ff-4e8b-91de-4f1959d04013\u002Ffile_99da5c60e85b.png) | 4:3, high, effort high |\n| Product launch poster | varg (written for this skill) | [SUMMIT ROAST](https:\u002F\u002Fs3.varg.ai\u002Ffiles\u002F194b94d0-58ff-4e8b-91de-4f1959d04013\u002Ffile_143c5129c4b7.png) (fictional brand) | 3:4, high |\n| Photo → editorial travel print | [@Naiknelofar788](https:\u002F\u002Fx.com\u002FNaiknelofar788\u002Fstatus\u002F2101161664892829838) | [photo](https:\u002F\u002Fs3.varg.ai\u002Ffiles\u002F194b94d0-58ff-4e8b-91de-4f1959d04013\u002Ffile_de945fe48c84.png) → [LISBON print](https:\u002F\u002Fs3.varg.ai\u002Ffiles\u002F194b94d0-58ff-4e8b-91de-4f1959d04013\u002Ffile_c1beb16c718f.png) | edit, 3:4 |\n| Photo → Baroque gallery poster | [@Goodmanprotocol](https:\u002F\u002Fx.com\u002FGoodmanprotocol\u002Fstatus\u002F2118193088128745875) | [photo](https:\u002F\u002Fs3.varg.ai\u002Ffiles\u002F194b94d0-58ff-4e8b-91de-4f1959d04013\u002Ffile_17855ee4e472.png) → [poster](https:\u002F\u002Fs3.varg.ai\u002Ffiles\u002F194b94d0-58ff-4e8b-91de-4f1959d04013\u002Ffile_d55052e95ef9.png) | edit, 3:4 |\n| Landmark postcard | [@Maercihh](https:\u002F\u002Fx.com\u002FMaercihh\u002Fstatus\u002F2117592215602233781) | [bridge in fog](https:\u002F\u002Fs3.varg.ai\u002Ffiles\u002F194b94d0-58ff-4e8b-91de-4f1959d04013\u002Ffile_4671ad66f76a.png) | 16:9, high |\n| Character turnaround sheet | [@EvoLinkAi](https:\u002F\u002Fx.com\u002FEvoLinkAi\u002Fstatus\u002F2107436379575840895) | [Mara](https:\u002F\u002Fs3.varg.ai\u002Ffiles\u002F194b94d0-58ff-4e8b-91de-4f1959d04013\u002Ffile_92817f364ac7.png) | 16:9, high, effort high |\n| Storyboard sheet | varg, idea by [@EHuanglu](https:\u002F\u002Fx.com\u002FEHuanglu\u002Fstatus\u002F2098411370815643837) | [THE LAST LIGHT](https:\u002F\u002Fs3.varg.ai\u002Ffiles\u002F194b94d0-58ff-4e8b-91de-4f1959d04013\u002Ffile_d505f9aceadb.png) | 16:9, high, effort high |\n| Low-res → clean upscale | [@k_matsumaru](https:\u002F\u002Fx.com\u002Fk_matsumaru\u002Fstatus\u002F2097506834659893340) | [272×152 noisy](https:\u002F\u002Fs3.varg.ai\u002Ffiles\u002F194b94d0-58ff-4e8b-91de-4f1959d04013\u002Ffile_f395c2486a58.jpg) → [1536×864](https:\u002F\u002Fs3.varg.ai\u002Ffiles\u002F194b94d0-58ff-4e8b-91de-4f1959d04013\u002Ffile_39f3af099f61.png) | edit, `image_size` 1536×864 |\n\n## 9. Failure → fix\n\n| What you see | Fix |\n|---|---|\n| A face changes from the second edit on; saturation drifts ([@k_matsumaru](https:\u002F\u002Fx.com\u002Fk_matsumaru\u002Fstatus\u002F2118186638228816322)); edit wear shows from about the third edit ([@NeneneAI](https:\u002F\u002Fx.com\u002FNeneneAI\u002Fstatus\u002F2118165875979407628)) | Edit from the original each time, put all changes in one pass (markup helps). Measured on a face (2026-11-05): five chained edits fell from 0.74 to 0.48 face similarity on Flare and from 0.73 to 0.29 on Sunburst with `reasoning_effort: low`; fresh calls from the character sheet averaged 0.77. Pinning Sunburst did not cure the chain: [character-passport\u002Freferences\u002Fgpt-image.md](..\u002Fcharacter-passport\u002Freferences\u002Fgpt-image.md) |\n| Sepia wash, muddy noise ([@PJaccetturo](https:\u002F\u002Fx.com\u002FPJaccetturo\u002Fstatus\u002F2118146909340868789)) | Not fixed by a setting we know of. Compare with `nano_banana_2_1` for that shot |\n| \"Pretty doll faces\", a 2015 Tumblr look next to Nano Banana's camera-roll realism ([@flowersslop](https:\u002F\u002Fx.com\u002Fflowersslop\u002Fstatus\u002F2118140335687930256)) | For casual phone-photo realism use `nano_banana_2_1` |\n| Pencil and other media looks are cleaner but less like the medium than 2.5 ([@munou_ac](https:\u002F\u002Fx.com\u002Fmunou_ac\u002Fstatus\u002F2118194696757424613)) | Try `gpt_image_2_5` for hand-made texture |\n| Pixel art fails ([@Angaisb_](https:\u002F\u002Fx.com\u002FAngaisb_\u002Fstatus\u002F2118126997855674470)) | Ask for flat cartoon art and pixelate it yourself, or use another model |\n| A misspelled or extra word | Shorter quoted text, `reasoning_effort: \"high\"`, then fix single words with a markup edit |\n| SVG, `xhigh`, `max`, more than 16 frames, square 1024 GIF frames | Rejected by fal (section 4) |\n| A dance prompt blocked by output moderation ([@KakiponzuX](https:\u002F\u002Fx.com\u002FKakiponzuX\u002Fstatus\u002F2118183717512306775)) | Reword the motion; a waving prompt passed in the same test |\n\n## Tested\n\nMeasured on varg on 2026-11-05: route times (Flare ~10 s, Sunburst ~49 s), the prices in section 5,\nthe rejections in section 4, 16:9 at 1088×608, and every example linked above (made with this skill's\nrecipes; we did not keep the exact filled-in prompts).\n\n## Related skills\n\n`gpt-image-gif`, `gpt-image-sticker-pack`, `gpt-image-sprite-sheet`, `gpt-image-markup-edit` (this set);\n`varg-ai` (setup, keys, every model and price); `varg-character-design` and `character-passport`\n(character sheets for video); `kling-4-prompting` (stills as key frames for video).\n",{"name":5,"license":15,"metadata":56,"description":7,"allowed-tools":64,"compatibility":65},{"author":57,"version":58,"openclaw":59},"vargHQ","1.0.0",{"homepage":60,"requires":61},"https:\u002F\u002Fvarg.ai\u002Fhow-to",{"anyBins":62},[63],"curl","Bash(curl:*) Bash(jq:*) Read Write Edit","Needs a VARG_API_KEY with curl (see the varg-ai skill) or the varg MCP connection (https:\u002F\u002Fmcp.varg.ai\u002Fmcp). One image costs 3-6 credits on varg (measured 2026-11-05).","main","e70ab1d8b0e24fbf8d3f58f35d71702abf856cfc","plugins\u002FvargHQ\u002Fskills\u002Fgpt-image-2-6",491,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins","https:\u002F\u002Fhol.org\u002Fplugins\u002Fbest-codex-plugins","https:\u002F\u002Fgithub.com\u002Fhashgraph-online","https:\u002F\u002Fhol.org","Open-source standards and developer tools for interoperable AI agents: discovery, identity, communication, payments, privacy and security.","2026-11-14 14:06:13",{"source":8,"skillName":5,"commands":77,"prompt":87,"zipAvailable":88},[78,81,84],{"tool":79,"command":80},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill gpt-image-2-6",{"tool":82,"command":83},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill gpt-image-2-6",{"tool":85,"command":86},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill gpt-image-2-6","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fgpt-image-2-6\u002FSKILL.md",true,[90],{"path":91,"resourceType":92,"resourceTypeDesc":93,"sizeBytes":94,"sourceHtmlUrl":95},"references\u002Frecipes.md","REFERENCE","参考文档",16524,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fgpt-image-2-6\u002Freferences\u002Frecipes.md",[97,106,114,122,130,138],{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":101,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":105},"01M7DV332YQMGD8WTRJ9DZQXTB","worktable-review-with-annotations","Create, inspect, reply to, update, or resolve situated Worktable annotations. Use when feedback belongs to a Doc section, block, text range, or HTML Doc, or when the user asks to address existing review feedback and coordinate a requested artifact edit.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":110,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":105},"01M7DV2YGHCZVBEB1AHYB6CGHE","worktable-find-and-synthesize-context","Find, assess, and synthesize context from Worktable Docs and Records. Use when the user asks what a workspace contains, wants workspace-backed research, needs current facts reconciled across artifacts, or requests a cited synthesis without changing workspace state.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FSKILL.md",[],[],{"skillNo":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":118,"sourceHtmlUrl":119,"categories":120,"keywords":121,"publishedAt":105},"01M7DV2TQN1H11ME2SAF9MXN7V","worktable-create-or-update-docs","Create, edit, rename, or maintain narrative Worktable Docs. Use for plans, decisions, briefs, notes, research syntheses, and other durable prose when the user requests a new artifact or a safe update to an existing one.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FSKILL.md",[],[],{"skillNo":123,"name":124,"nameZh":6,"description":125,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":126,"sourceHtmlUrl":127,"categories":128,"keywords":129,"publishedAt":105},"01M7DV2NE452NEA8TXATKSNAJH","worktable-create-or-manage-records","Organize repeated structured information as durable Worktable Records. Use for research datasets, inventories, directories, pipelines, trackers, and other collections whose items need identity, fields, filtering, links, validation, or individual updates.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FSKILL.md",[],[],{"skillNo":131,"name":132,"nameZh":6,"description":133,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":134,"sourceHtmlUrl":135,"categories":136,"keywords":137,"publishedAt":105},"01M7DV2HENRBR2KSCVM064WH0Y","worktable-create-or-manage-interactive-html","Create or improve durable visual and interactive artifacts in Worktable. Use for dashboards, trackers, calculators, mini apps, slide presentations, and other requests that benefit from a polished HTML Doc.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FSKILL.md",[],[],{"skillNo":139,"name":140,"nameZh":6,"description":141,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":142,"sourceHtmlUrl":143,"categories":144,"keywords":145,"publishedAt":105},"01M7DV2CADR5R7RQFFYPNAGR9Y","worktable-collaborate-threads","Read, answer, and hand off messages through durable Worktable threads with users or other authenticated participants. Use when the user asks to check addressed messages, reply to a participant, continue a thread, request another agent's help, wait briefly for a response, or watch for comments and messages sent to the agent.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FSKILL.md",[],[]]