[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EP5GFG36C2VZTHWD9BJ792":3,"skill-same:01M7EP5GFG36C2VZTHWD9BJ792":166},{"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":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":28,"commitSha":29,"skillDirectory":30,"forksCount":31,"repositoryHtmlUrl":32,"repositoryHomepageUrl":6,"ownerHtmlUrl":33,"ownerBlogUrl":34,"ownerDescription":6,"updatedAt":35,"install":36,"resources":49},"01M7EP5GFG36C2VZTHWD9BJ792","higgsfield-brandkit",null,"Create and extend complete visual brand systems through the Higgsfield CLI and bundled deterministic local tooling: palettes, SVG logo marks, typography, mockups, social graphics, packaging, signage, merchandise, posters, presentation decks, and editable PPTX\u002FPDF brandbooks. Preserves official supplied assets, persists approvals locally, and regenerates only dependent outputs. Use when: \"create a brand kit\", \"make a visual identity\", \"design a logo and brandbook\", \"apply this logo to branded assets\", \"make packaging or signage\", or \"extend our existing branding\". Chain with higgsfield-generate for general image production and Marketing Studio brand-kits when importing website metadata for ads. NOT for unbranded image generation (use higgsfield-generate), product catalog photography (use higgsfield-product-photoshoot), website implementation (use higgsfield-websites), or native Figma\u002FCanva\u002FPSD\u002FAI delivery.","TanNhatCMS\u002Fjarvis","TanNhatCMS","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F113796420?v=4","01M753MV17KG5CD3152G3WQEQY","KietNT","01M7EKEDYVYQ6PWVJJMZ911VMX",0,"MIT","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-imp-higgsfield-brandkit\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nversion: 0.13.0\nname: higgsfield-brandkit\ndescription: |\n  Create and extend complete visual brand systems through the Higgsfield CLI and bundled deterministic local tooling: palettes, SVG logo marks, typography, mockups, social graphics, packaging, signage, merchandise, posters, presentation decks, and editable PPTX\u002FPDF brandbooks. Preserves official supplied assets, persists approvals locally, and regenerates only dependent outputs. Use when: \"create a brand kit\", \"make a visual identity\", \"design a logo and brandbook\", \"apply this logo to branded assets\", \"make packaging or signage\", or \"extend our existing branding\". Chain with higgsfield-generate for general image production and Marketing Studio brand-kits when importing website metadata for ads. NOT for unbranded image generation (use higgsfield-generate), product catalog photography (use higgsfield-product-photoshoot), website implementation (use higgsfield-websites), or native Figma\u002FCanva\u002FPSD\u002FAI delivery.\nargument-hint: \"[brand brief or existing assets] [requested deliverables]\"\nallowed-tools: Bash\n---\n\n# Higgsfield Brandkit\n\nBuild a coherent identity and its requested applications. Treat supplied brand facts and official assets as fixed constraints.\n\n## Bootstrap\n\n1. Resolve `SKILL_ROOT` to this skill's installed directory and create a durable project directory:\n\n   ```bash\n   BRANDKIT_WORKDIR=\"${PWD}\u002Fbrandkit\"\n   BRANDKIT_STATE=\"${BRANDKIT_WORKDIR}\u002Fstate.json\"\n   mkdir -p \"${BRANDKIT_WORKDIR}\"\n   ```\n\n2. Read [prerequisites](references\u002Fprerequisites.md). Check tools before the stage that needs them. Never install system packages without the user's permission.\n3. If `higgsfield` is missing, install it only after permission:\n\n   ```bash\n   curl -fsSL https:\u002F\u002Fraw.githubusercontent.com\u002Fhiggsfield-ai\u002Fcli\u002Fmain\u002Finstall.sh | sh\n   ```\n\n4. If `higgsfield account status` fails with an authentication or workspace error, ask the user to run `higgsfield auth login` or select a workspace, then wait.\n5. Inspect live model contracts before paid generation:\n\n   ```bash\n   higgsfield model get recraft_v4_1 --json\n   higgsfield model get seedream_v5_pro --json\n   higgsfield model get gpt_image_2 --json\n   ```\n\n## CLI mapping\n\n| Operation | Command |\n|---|---|\n| Discover a model | `higgsfield model get \u003Cmodel> --json` |\n| Generate and poll | `higgsfield generate create \u003Cmodel> ... --wait --json` |\n| Resume a job | `higgsfield generate wait \u003Cjob_id> --json` |\n| Upload a local asset | `higgsfield upload create \u003Cpath> --json` |\n| Import website metadata | `higgsfield marketing-studio brand-kits fetch --url \u003Curl> --wait --json` |\n| Read\u002Fwrite approval state | `python3 \"$SKILL_ROOT\u002Fscripts\u002Fbrandkit.py\" state ...` |\n| Render review boards | `python3 \"$SKILL_ROOT\u002Fscripts\u002Fbrandkit.py\" preview ...` |\n| Inspect selected logo | `python3 \"$SKILL_ROOT\u002Fscripts\u002Fbrandkit.py\" logo-inspect ...` |\n| Export logo files | `python3 \"$SKILL_ROOT\u002Fscripts\u002Fbrandkit.py\" logo-export ...` |\n| Build a Brandbook | `python3 \"$SKILL_ROOT\u002Fscripts\u002Fbrandkit.py\" brandbook-build ...` |\n\nLocal image paths passed with `--image` are auto-uploaded. Keep HTML, SVG, PPTX, and PDF deliverables as local project files unless the user explicitly needs a hosted copy.\n\n## User-facing behavior\n\n- Match the user's language. Keep Design Brain reasoning, prompts, state mechanics, scripts, model lookup, and QA internals private.\n- Send at most one short status sentence per visible generation batch, then stay quiet until the result is ready.\n- Ask one compact set of only unresolved blocking questions. Never repeat facts or force a complete identity questionnaire for a partial task.\n- After each palette, logo, typography, or downstream review, stop and wait for ordinary user feedback.\n- Never infer approval from silence, successful generation, or your own preference.\n- Preserve exact user copy. Never invent positioning, values, claims, ingredients, prices, certifications, statistics, or regulatory content.\n\n## Core workflow\n\n1. **Classify the request.**\n   - `apply-existing`: use supplied official assets without redesigning them.\n   - `extend-partial`: create only missing slots required by the requested output.\n   - `create-identity`: create a new logo or identity only when explicitly requested.\n2. **Read state.** Run:\n\n   ```bash\n   python3 \"$SKILL_ROOT\u002Fscripts\u002Fbrandkit.py\" state \\\n     --state-file \"$BRANDKIT_STATE\" --action get_status\n   ```\n\n   Local state is durable. Never paste, hand-edit, or recreate approvals when the state file exists.\n3. **Run intake and asset analysis.** Read [intake](references\u002Fintake.md), [asset analysis](references\u002Fasset-analysis.md), [state routing](references\u002Fhandoff.md), and [exact state payloads](references\u002Fstate-payloads.md). Lock every user-declared official logo, palette, and typography slot immediately.\n4. **Create the Brand Lock.** Read [Brand Lock](references\u002Fbrand-lock.md). Record exact spelling, official assets, colors, fonts, layout\u002Fshape rules, requested outputs, and forbidden treatments.\n5. **Require only the slots the output uses.**\n   - logo-only → palette + logo for a new mark; official logo alone for an existing mark\n   - palette-only → palette\n   - typography-only → typography\n   - copy-free mockup\u002Fmerch → logo; add palette only when color\u002Fapplication requires it\n   - text-bearing social\u002Fpackaging\u002Fposter\u002Fsignage → logo + palette + typography\n   - Brandbook\u002Fdeck → logo + palette + typography\n6. **Build missing foundation slots.** Read [Design Brain](references\u002Fbrandkit-design-brain.md), [concept boards](references\u002Fconcept-boards.md), [inline reviews](references\u002Finline-widgets.md), and only the needed [palette](references\u002Fpalette.md), [logo](references\u002Flogo.md), or [typography](references\u002Ftypography.md) module.\n7. **Continue the original request** as soon as its required slots are approved. Never ask the user to choose scope again.\n8. **Load only the requested production module:**\n   - [mockups](references\u002Fmockups.md)\n   - [social graphics](references\u002Fsocial-templates.md)\n   - [posters\u002Fbanners](references\u002Fposters-banners.md)\n   - [packaging](references\u002Fpackaging.md)\n   - [signage](references\u002Fsignage.md)\n   - [merchandise](references\u002Fmerchandise.md)\n   - [presentation decks](references\u002Fpresentation-deck.md)\n   - [Brandbooks](references\u002Fbrandbook.md)\n9. **QA and approval.** Read [QA and iteration](references\u002Fqa-and-iteration.md). Repair only the failing output. Save a downstream element only after explicit approval with its exact foundation dependencies.\n\n## New identity sequence\n\n### 1. Palette\n\nRender 2–3 exact palette options as deterministic HTML using [preview payloads](references\u002Fpreview-payloads.md). Show PNG screenshots plus editable HTML files and wait. Persist the selected palette with `approve_palette` before logo generation.\n\n### 2. SVG logo marks\n\nRead [logo prompt enhancer](references\u002Flogo-prompt-enhancer.md). Produce exactly three distinct symbol-only mechanisms and one Recraft prompt for each. Write each long prompt to a file and submit separately:\n\n```bash\nhiggsfield generate create recraft_v4_1 \\\n  --model_type vector \\\n  --colors @\"${BRANDKIT_WORKDIR}\u002Flogo-colors.json\" \\\n  --background_color '#F7F7F5' \\\n  --aspect_ratio 1:1 \\\n  --resolution 2k \\\n  --wait --json \u003C \"${BRANDKIT_WORKDIR}\u002Flogo-candidate-1.txt\"\n```\n\nUse the returned SVG URLs directly for review. After selection, inspect the exact SVG without altering it:\n\n```bash\npython3 \"$SKILL_ROOT\u002Fscripts\u002Fbrandkit.py\" logo-inspect \\\n  --source \"\u003Cselected Recraft SVG URL or absolute local path>\"\n```\n\nPersist the exact job ID, SVG URL, name, palette revision, and returned canonical geometry fingerprint with `approve_logo`.\n\n### 3. Typography\n\nPropose 2–3 unique display\u002Fbody pairs using supplied fonts or verified Google Fonts. Render the real brand name and sample copy through the preview script. Persist only the selected pair with `approve_typography`.\n\nInteractive flows always stop for palette, logo, and typography selections. Explicit no-question mode may choose and persist a palette, but it still shows all three SVG logo candidates and stops for the user's logo selection; exact brand marks are never self-approved.\n\n## Consistency invariants\n\n- Reuse the same approved logo source everywhere. Never redraw an official or selected SVG when deterministic placement\u002Fexport is possible.\n- A generated logo depends on the palette revision used to create it. Changing that palette invalidates the generated logo and its dependents; changing typography does not invalidate the symbol mark.\n- Changing a foundation slot invalidates only downstream elements that list that slot in `required_slots`.\n- Copy the same Brand Lock values into every related generation prompt: exact hex, font roles, shape language, placement, clear space, composition, and forbidden treatments.\n- Use Recraft V4.1 vector mode only for new logo marks.\n- Use Seedream as the primary photoreal mockup generator. Use GPT Image 2 only for the controlled stage that adds readable text or exact graphic details.\n- Use local deterministic SVG\u002FPPTX\u002FHTML construction for exact copy and editable layouts. Do not ask an image model to fake editable files.\n- Do not promise native Figma, Canva, PSD, AI, or EPS files.\n\n## Deterministic scripts\n\nCreate JSON input files under `\"$BRANDKIT_WORKDIR\"`; never interpolate user text directly into shell arguments.\n\n```bash\npython3 \"$SKILL_ROOT\u002Fscripts\u002Fbrandkit.py\" preview \\\n  --input \"$BRANDKIT_WORKDIR\u002Freviews.json\" \\\n  --output-dir \"$BRANDKIT_WORKDIR\u002Freviews\"\n\npython3 \"$SKILL_ROOT\u002Fscripts\u002Fbrandkit.py\" logo-export \\\n  --input \"$BRANDKIT_WORKDIR\u002Flogo-export.json\" \\\n  --output-dir \"$BRANDKIT_WORKDIR\u002Flogo\"\n\npython3 \"$SKILL_ROOT\u002Fscripts\u002Fbrandkit.py\" brandbook-build \\\n  --state-file \"$BRANDKIT_STATE\" \\\n  --input \"$BRANDKIT_WORKDIR\u002Fbrandbook.json\" \\\n  --output-dir \"$BRANDKIT_WORKDIR\u002Fbrandbook\"\n```\n\nFor logo export, load [logo export payloads](references\u002Flogo-export-payloads.md). For Brandbooks, use the bundled builder only; never substitute an improvised PowerPoint or PDF generator after a deterministic contract failure.\n\n## Failure policy\n\n- Retry a failed Recraft or image-generation request once with the same locked concept and corrected contract. Stop after the second equivalent failure.\n- If preview or logo export fails twice, report the concrete error; never replace it with ad-hoc SVG rewriting.\n- If the Brandbook template, font, or conversion contract fails, stop immediately. Do not produce a visually different fallback and call it canonical.\n- If exact typography or official-logo fidelity cannot be preserved, disclose the limitation instead of claiming completion.\n- Never expose raw auth tokens or credentials in files, logs, or chat.\n\n## Delivery\n\nFor Brandbooks, follow the strict response contract in [brandbook](references\u002Fbrandbook.md): PPTX link\u002Fpath, PDF link\u002Fpath, and font-install warning only.\n\nFor other outputs return:\n\n1. The requested visual files and previews.\n2. A compact Brand Lock summary.\n3. Editable versus flattened format labels.\n4. Required-font\u002Fimport limitations.\n5. Stable variant names for targeted revisions.\n\n## Reference index\n\n- [Prerequisites](references\u002Fprerequisites.md) — stage-specific local dependencies and install commands.\n- [Intake](references\u002Fintake.md) — minimal questions and input routing.\n- [Asset analysis](references\u002Fasset-analysis.md) — official\u002Freference classification and measurement.\n- [State routing](references\u002Fhandoff.md) and [state payloads](references\u002Fstate-payloads.md) — persistent approvals.\n- [Brand Lock](references\u002Fbrand-lock.md) — canonical visual constraints.\n- [Design Brain](references\u002Fbrandkit-design-brain.md) — private art direction.\n- [Concept boards](references\u002Fconcept-boards.md), [preview payloads](references\u002Fpreview-payloads.md), and [inline reviews](references\u002Finline-widgets.md) — selection stages.\n- [Logo](references\u002Flogo.md), [logo prompt enhancer](references\u002Flogo-prompt-enhancer.md), and [logo export payloads](references\u002Flogo-export-payloads.md) — SVG generation and deterministic variants.\n- [Palette](references\u002Fpalette.md) and [typography](references\u002Ftypography.md) — foundation slots.\n- [Mockups](references\u002Fmockups.md), [social graphics](references\u002Fsocial-templates.md), [posters\u002Fbanners](references\u002Fposters-banners.md), [packaging](references\u002Fpackaging.md), [signage](references\u002Fsignage.md), and [merchandise](references\u002Fmerchandise.md) — applications.\n- [Presentation decks](references\u002Fpresentation-deck.md) and [Brandbooks](references\u002Fbrandbook.md) — editable documents.\n- [QA and iteration](references\u002Fqa-and-iteration.md) — preflight, repair, approval, and delivery manifest.\n","# Higgsfield Brandkit\n\nBuild a coherent identity and its requested applications. Treat supplied brand facts and official assets as fixed constraints.\n\n## Bootstrap\n\n1. Resolve `SKILL_ROOT` to this skill's installed directory and create a durable project directory:\n\n   ```bash\n   BRANDKIT_WORKDIR=\"${PWD}\u002Fbrandkit\"\n   BRANDKIT_STATE=\"${BRANDKIT_WORKDIR}\u002Fstate.json\"\n   mkdir -p \"${BRANDKIT_WORKDIR}\"\n   ```\n\n2. Read [prerequisites](references\u002Fprerequisites.md). Check tools before the stage that needs them. Never install system packages without the user's permission.\n3. If `higgsfield` is missing, install it only after permission:\n\n   ```bash\n   curl -fsSL https:\u002F\u002Fraw.githubusercontent.com\u002Fhiggsfield-ai\u002Fcli\u002Fmain\u002Finstall.sh | sh\n   ```\n\n4. If `higgsfield account status` fails with an authentication or workspace error, ask the user to run `higgsfield auth login` or select a workspace, then wait.\n5. Inspect live model contracts before paid generation:\n\n   ```bash\n   higgsfield model get recraft_v4_1 --json\n   higgsfield model get seedream_v5_pro --json\n   higgsfield model get gpt_image_2 --json\n   ```\n\n## CLI mapping\n\n| Operation | Command |\n|---|---|\n| Discover a model | `higgsfield model get \u003Cmodel> --json` |\n| Generate and poll | `higgsfield generate create \u003Cmodel> ... --wait --json` |\n| Resume a job | `higgsfield generate wait \u003Cjob_id> --json` |\n| Upload a local asset | `higgsfield upload create \u003Cpath> --json` |\n| Import website metadata | `higgsfield marketing-studio brand-kits fetch --url \u003Curl> --wait --json` |\n| Read\u002Fwrite approval state | `python3 \"$SKILL_ROOT\u002Fscripts\u002Fbrandkit.py\" state ...` |\n| Render review boards | `python3 \"$SKILL_ROOT\u002Fscripts\u002Fbrandkit.py\" preview ...` |\n| Inspect selected logo | `python3 \"$SKILL_ROOT\u002Fscripts\u002Fbrandkit.py\" logo-inspect ...` |\n| Export logo files | `python3 \"$SKILL_ROOT\u002Fscripts\u002Fbrandkit.py\" logo-export ...` |\n| Build a Brandbook | `python3 \"$SKILL_ROOT\u002Fscripts\u002Fbrandkit.py\" brandbook-build ...` |\n\nLocal image paths passed with `--image` are auto-uploaded. Keep HTML, SVG, PPTX, and PDF deliverables as local project files unless the user explicitly needs a hosted copy.\n\n## User-facing behavior\n\n- Match the user's language. Keep Design Brain reasoning, prompts, state mechanics, scripts, model lookup, and QA internals private.\n- Send at most one short status sentence per visible generation batch, then stay quiet until the result is ready.\n- Ask one compact set of only unresolved blocking questions. Never repeat facts or force a complete identity questionnaire for a partial task.\n- After each palette, logo, typography, or downstream review, stop and wait for ordinary user feedback.\n- Never infer approval from silence, successful generation, or your own preference.\n- Preserve exact user copy. Never invent positioning, values, claims, ingredients, prices, certifications, statistics, or regulatory content.\n\n## Core workflow\n\n1. **Classify the request.**\n   - `apply-existing`: use supplied official assets without redesigning them.\n   - `extend-partial`: create only missing slots required by the requested output.\n   - `create-identity`: create a new logo or identity only when explicitly requested.\n2. **Read state.** Run:\n\n   ```bash\n   python3 \"$SKILL_ROOT\u002Fscripts\u002Fbrandkit.py\" state \\\n     --state-file \"$BRANDKIT_STATE\" --action get_status\n   ```\n\n   Local state is durable. Never paste, hand-edit, or recreate approvals when the state file exists.\n3. **Run intake and asset analysis.** Read [intake](references\u002Fintake.md), [asset analysis](references\u002Fasset-analysis.md), [state routing](references\u002Fhandoff.md), and [exact state payloads](references\u002Fstate-payloads.md). Lock every user-declared official logo, palette, and typography slot immediately.\n4. **Create the Brand Lock.** Read [Brand Lock](references\u002Fbrand-lock.md). Record exact spelling, official assets, colors, fonts, layout\u002Fshape rules, requested outputs, and forbidden treatments.\n5. **Require only the slots the output uses.**\n   - logo-only → palette + logo for a new mark; official logo alone for an existing mark\n   - palette-only → palette\n   - typography-only → typography\n   - copy-free mockup\u002Fmerch → logo; add palette only when color\u002Fapplication requires it\n   - text-bearing social\u002Fpackaging\u002Fposter\u002Fsignage → logo + palette + typography\n   - Brandbook\u002Fdeck → logo + palette + typography\n6. **Build missing foundation slots.** Read [Design Brain](references\u002Fbrandkit-design-brain.md), [concept boards](references\u002Fconcept-boards.md), [inline reviews](references\u002Finline-widgets.md), and only the needed [palette](references\u002Fpalette.md), [logo](references\u002Flogo.md), or [typography](references\u002Ftypography.md) module.\n7. **Continue the original request** as soon as its required slots are approved. Never ask the user to choose scope again.\n8. **Load only the requested production module:**\n   - [mockups](references\u002Fmockups.md)\n   - [social graphics](references\u002Fsocial-templates.md)\n   - [posters\u002Fbanners](references\u002Fposters-banners.md)\n   - [packaging](references\u002Fpackaging.md)\n   - [signage](references\u002Fsignage.md)\n   - [merchandise](references\u002Fmerchandise.md)\n   - [presentation decks](references\u002Fpresentation-deck.md)\n   - [Brandbooks](references\u002Fbrandbook.md)\n9. **QA and approval.** Read [QA and iteration](references\u002Fqa-and-iteration.md). Repair only the failing output. Save a downstream element only after explicit approval with its exact foundation dependencies.\n\n## New identity sequence\n\n### 1. Palette\n\nRender 2–3 exact palette options as deterministic HTML using [preview payloads](references\u002Fpreview-payloads.md). Show PNG screenshots plus editable HTML files and wait. Persist the selected palette with `approve_palette` before logo generation.\n\n### 2. SVG logo marks\n\nRead [logo prompt enhancer](references\u002Flogo-prompt-enhancer.md). Produce exactly three distinct symbol-only mechanisms and one Recraft prompt for each. Write each long prompt to a file and submit separately:\n\n```bash\nhiggsfield generate create recraft_v4_1 \\\n  --model_type vector \\\n  --colors @\"${BRANDKIT_WORKDIR}\u002Flogo-colors.json\" \\\n  --background_color '#F7F7F5' \\\n  --aspect_ratio 1:1 \\\n  --resolution 2k \\\n  --wait --json \u003C \"${BRANDKIT_WORKDIR}\u002Flogo-candidate-1.txt\"\n```\n\nUse the returned SVG URLs directly for review. After selection, inspect the exact SVG without altering it:\n\n```bash\npython3 \"$SKILL_ROOT\u002Fscripts\u002Fbrandkit.py\" logo-inspect \\\n  --source \"\u003Cselected Recraft SVG URL or absolute local path>\"\n```\n\nPersist the exact job ID, SVG URL, name, palette revision, and returned canonical geometry fingerprint with `approve_logo`.\n\n### 3. Typography\n\nPropose 2–3 unique display\u002Fbody pairs using supplied fonts or verified Google Fonts. Render the real brand name and sample copy through the preview script. Persist only the selected pair with `approve_typography`.\n\nInteractive flows always stop for palette, logo, and typography selections. Explicit no-question mode may choose and persist a palette, but it still shows all three SVG logo candidates and stops for the user's logo selection; exact brand marks are never self-approved.\n\n## Consistency invariants\n\n- Reuse the same approved logo source everywhere. Never redraw an official or selected SVG when deterministic placement\u002Fexport is possible.\n- A generated logo depends on the palette revision used to create it. Changing that palette invalidates the generated logo and its dependents; changing typography does not invalidate the symbol mark.\n- Changing a foundation slot invalidates only downstream elements that list that slot in `required_slots`.\n- Copy the same Brand Lock values into every related generation prompt: exact hex, font roles, shape language, placement, clear space, composition, and forbidden treatments.\n- Use Recraft V4.1 vector mode only for new logo marks.\n- Use Seedream as the primary photoreal mockup generator. Use GPT Image 2 only for the controlled stage that adds readable text or exact graphic details.\n- Use local deterministic SVG\u002FPPTX\u002FHTML construction for exact copy and editable layouts. Do not ask an image model to fake editable files.\n- Do not promise native Figma, Canva, PSD, AI, or EPS files.\n\n## Deterministic scripts\n\nCreate JSON input files under `\"$BRANDKIT_WORKDIR\"`; never interpolate user text directly into shell arguments.\n\n```bash\npython3 \"$SKILL_ROOT\u002Fscripts\u002Fbrandkit.py\" preview \\\n  --input \"$BRANDKIT_WORKDIR\u002Freviews.json\" \\\n  --output-dir \"$BRANDKIT_WORKDIR\u002Freviews\"\n\npython3 \"$SKILL_ROOT\u002Fscripts\u002Fbrandkit.py\" logo-export \\\n  --input \"$BRANDKIT_WORKDIR\u002Flogo-export.json\" \\\n  --output-dir \"$BRANDKIT_WORKDIR\u002Flogo\"\n\npython3 \"$SKILL_ROOT\u002Fscripts\u002Fbrandkit.py\" brandbook-build \\\n  --state-file \"$BRANDKIT_STATE\" \\\n  --input \"$BRANDKIT_WORKDIR\u002Fbrandbook.json\" \\\n  --output-dir \"$BRANDKIT_WORKDIR\u002Fbrandbook\"\n```\n\nFor logo export, load [logo export payloads](references\u002Flogo-export-payloads.md). For Brandbooks, use the bundled builder only; never substitute an improvised PowerPoint or PDF generator after a deterministic contract failure.\n\n## Failure policy\n\n- Retry a failed Recraft or image-generation request once with the same locked concept and corrected contract. Stop after the second equivalent failure.\n- If preview or logo export fails twice, report the concrete error; never replace it with ad-hoc SVG rewriting.\n- If the Brandbook template, font, or conversion contract fails, stop immediately. Do not produce a visually different fallback and call it canonical.\n- If exact typography or official-logo fidelity cannot be preserved, disclose the limitation instead of claiming completion.\n- Never expose raw auth tokens or credentials in files, logs, or chat.\n\n## Delivery\n\nFor Brandbooks, follow the strict response contract in [brandbook](references\u002Fbrandbook.md): PPTX link\u002Fpath, PDF link\u002Fpath, and font-install warning only.\n\nFor other outputs return:\n\n1. The requested visual files and previews.\n2. A compact Brand Lock summary.\n3. Editable versus flattened format labels.\n4. Required-font\u002Fimport limitations.\n5. Stable variant names for targeted revisions.\n\n## Reference index\n\n- [Prerequisites](references\u002Fprerequisites.md) — stage-specific local dependencies and install commands.\n- [Intake](references\u002Fintake.md) — minimal questions and input routing.\n- [Asset analysis](references\u002Fasset-analysis.md) — official\u002Freference classification and measurement.\n- [State routing](references\u002Fhandoff.md) and [state payloads](references\u002Fstate-payloads.md) — persistent approvals.\n- [Brand Lock](references\u002Fbrand-lock.md) — canonical visual constraints.\n- [Design Brain](references\u002Fbrandkit-design-brain.md) — private art direction.\n- [Concept boards](references\u002Fconcept-boards.md), [preview payloads](references\u002Fpreview-payloads.md), and [inline reviews](references\u002Finline-widgets.md) — selection stages.\n- [Logo](references\u002Flogo.md), [logo prompt enhancer](references\u002Flogo-prompt-enhancer.md), and [logo export payloads](references\u002Flogo-export-payloads.md) — SVG generation and deterministic variants.\n- [Palette](references\u002Fpalette.md) and [typography](references\u002Ftypography.md) — foundation slots.\n- [Mockups](references\u002Fmockups.md), [social graphics](references\u002Fsocial-templates.md), [posters\u002Fbanners](references\u002Fposters-banners.md), [packaging](references\u002Fpackaging.md), [signage](references\u002Fsignage.md), and [merchandise](references\u002Fmerchandise.md) — applications.\n- [Presentation decks](references\u002Fpresentation-deck.md) and [Brandbooks](references\u002Fbrandbook.md) — editable documents.\n- [QA and iteration](references\u002Fqa-and-iteration.md) — preflight, repair, approval, and delivery manifest.\n",{"name":5,"version":24,"description":25,"allowed-tools":26,"argument-hint":27},"0.13.0","Create and extend complete visual brand systems through the Higgsfield CLI and bundled deterministic local tooling: palettes, SVG logo marks, typography, mockups, social graphics, packaging, signage, merchandise, posters, presentation decks, and editable PPTX\u002FPDF brandbooks. Preserves official supplied assets, persists approvals locally, and regenerates only dependent outputs. Use when: \"create a brand kit\", \"make a visual identity\", \"design a logo and brandbook\", \"apply this logo to branded assets\", \"make packaging or signage\", or \"extend our existing branding\". Chain with higgsfield-generate for general image production and Marketing Studio brand-kits when importing website metadata for ads. NOT for unbranded image generation (use higgsfield-generate), product catalog photography (use higgsfield-product-photoshoot), website implementation (use higgsfield-websites), or native Figma\u002FCanva\u002FPSD\u002FAI delivery.\n","Bash","[brand brief or existing assets] [requested deliverables]","main","af388a77c2fe5e0b4fd879cca4300a0ffa9a6579","skills\u002Fams-imp-higgsfield-brandkit",1,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis","https:\u002F\u002Fgithub.com\u002FTanNhatCMS","https:\u002F\u002Fmrkiet.name.vn","2026-11-07 14:23:08",{"source":8,"skillName":5,"commands":37,"prompt":47,"zipAvailable":48},[38,41,44],{"tool":39,"command":40},"npx","npx skills add TanNhatCMS\u002Fjarvis --skill higgsfield-brandkit",{"tool":42,"command":43},"bunx","bunx skills add TanNhatCMS\u002Fjarvis --skill higgsfield-brandkit",{"tool":45,"command":46},"pnpm","pnpm dlx skills add TanNhatCMS\u002Fjarvis --skill higgsfield-brandkit","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-imp-higgsfield-brandkit\u002FSKILL.md",true,[50,56,60,64,68,72,76,80,84,88,92,96,100,104,108,112,116,120,124,128,132,136,140,144,148,152,158,162],{"path":51,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":54,"sourceHtmlUrl":55},"agents\u002Fopenai.yaml","REFERENCE","参考文档",231,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-imp-higgsfield-brandkit\u002Fagents\u002Fopenai.yaml",{"path":57,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fasset-analysis.md",7656,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-imp-higgsfield-brandkit\u002Freferences\u002Fasset-analysis.md",{"path":61,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Fbrand-lock.md",6245,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-imp-higgsfield-brandkit\u002Freferences\u002Fbrand-lock.md",{"path":65,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":66,"sourceHtmlUrl":67},"references\u002Fbrandbook.md",4942,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-imp-higgsfield-brandkit\u002Freferences\u002Fbrandbook.md",{"path":69,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":70,"sourceHtmlUrl":71},"references\u002Fbrandkit-design-brain.md",8236,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-imp-higgsfield-brandkit\u002Freferences\u002Fbrandkit-design-brain.md",{"path":73,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":74,"sourceHtmlUrl":75},"references\u002Fconcept-boards.md",7255,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-imp-higgsfield-brandkit\u002Freferences\u002Fconcept-boards.md",{"path":77,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":78,"sourceHtmlUrl":79},"references\u002Fhandoff.md",3839,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-imp-higgsfield-brandkit\u002Freferences\u002Fhandoff.md",{"path":81,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":82,"sourceHtmlUrl":83},"references\u002Finline-widgets.md",2723,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-imp-higgsfield-brandkit\u002Freferences\u002Finline-widgets.md",{"path":85,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":86,"sourceHtmlUrl":87},"references\u002Fintake.md",3375,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-imp-higgsfield-brandkit\u002Freferences\u002Fintake.md",{"path":89,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":90,"sourceHtmlUrl":91},"references\u002Flogo-export-payloads.md",709,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-imp-higgsfield-brandkit\u002Freferences\u002Flogo-export-payloads.md",{"path":93,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":94,"sourceHtmlUrl":95},"references\u002Flogo-prompt-enhancer.md",9773,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-imp-higgsfield-brandkit\u002Freferences\u002Flogo-prompt-enhancer.md",{"path":97,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":98,"sourceHtmlUrl":99},"references\u002Flogo.md",10386,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-imp-higgsfield-brandkit\u002Freferences\u002Flogo.md",{"path":101,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":102,"sourceHtmlUrl":103},"references\u002Fmerchandise.md",1060,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-imp-higgsfield-brandkit\u002Freferences\u002Fmerchandise.md",{"path":105,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":106,"sourceHtmlUrl":107},"references\u002Fmockups.md",11120,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-imp-higgsfield-brandkit\u002Freferences\u002Fmockups.md",{"path":109,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":110,"sourceHtmlUrl":111},"references\u002Fpackaging.md",1311,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-imp-higgsfield-brandkit\u002Freferences\u002Fpackaging.md",{"path":113,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":114,"sourceHtmlUrl":115},"references\u002Fpalette.md",1051,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-imp-higgsfield-brandkit\u002Freferences\u002Fpalette.md",{"path":117,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":118,"sourceHtmlUrl":119},"references\u002Fposters-banners.md",1093,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-imp-higgsfield-brandkit\u002Freferences\u002Fposters-banners.md",{"path":121,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":122,"sourceHtmlUrl":123},"references\u002Fprerequisites.md",2940,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-imp-higgsfield-brandkit\u002Freferences\u002Fprerequisites.md",{"path":125,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":126,"sourceHtmlUrl":127},"references\u002Fpresentation-deck.md",1601,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-imp-higgsfield-brandkit\u002Freferences\u002Fpresentation-deck.md",{"path":129,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":130,"sourceHtmlUrl":131},"references\u002Fpreview-payloads.md",2927,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-imp-higgsfield-brandkit\u002Freferences\u002Fpreview-payloads.md",{"path":133,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":134,"sourceHtmlUrl":135},"references\u002Fqa-and-iteration.md",6921,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-imp-higgsfield-brandkit\u002Freferences\u002Fqa-and-iteration.md",{"path":137,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":138,"sourceHtmlUrl":139},"references\u002Fsignage.md",1001,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-imp-higgsfield-brandkit\u002Freferences\u002Fsignage.md",{"path":141,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":142,"sourceHtmlUrl":143},"references\u002Fsocial-templates.md",4415,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-imp-higgsfield-brandkit\u002Freferences\u002Fsocial-templates.md",{"path":145,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":146,"sourceHtmlUrl":147},"references\u002Fstate-payloads.md",3130,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-imp-higgsfield-brandkit\u002Freferences\u002Fstate-payloads.md",{"path":149,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":150,"sourceHtmlUrl":151},"references\u002Ftypography.md",4398,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-imp-higgsfield-brandkit\u002Freferences\u002Ftypography.md",{"path":153,"resourceType":154,"resourceTypeDesc":155,"sizeBytes":156,"sourceHtmlUrl":157},"scripts\u002Fbrandkit.py","SCRIPT","脚本",56116,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-imp-higgsfield-brandkit\u002Fscripts\u002Fbrandkit.py",{"path":159,"resourceType":154,"resourceTypeDesc":155,"sizeBytes":160,"sourceHtmlUrl":161},"scripts\u002Fbuild_brandbook.py",37748,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-imp-higgsfield-brandkit\u002Fscripts\u002Fbuild_brandbook.py",{"path":163,"resourceType":154,"resourceTypeDesc":155,"sizeBytes":164,"sourceHtmlUrl":165},"scripts\u002Frender_brandbook_pdf.py",5313,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-imp-higgsfield-brandkit\u002Fscripts\u002Frender_brandbook_pdf.py",[167,174,182,189,196,203],{"skillNo":168,"name":169,"nameZh":6,"description":170,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":171,"categories":172,"keywords":173,"publishedAt":19},"01M7EWYJR0J8DARY7E59Z6Y9MV","web-scrape","Turn web pages into LLM-ready markdown via the Firecrawl API (renders JS, anti-bot handling). Use when browser_open\u002Ffetch fails on JS-heavy pages, or when you need clean markdown\u002Fstructured extraction from a site. Requires FIRECRAWL_API_KEY.","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fweb-scrape\u002FSKILL.md",[],[],{"skillNo":175,"name":176,"nameZh":6,"description":177,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":178,"sourceHtmlUrl":179,"categories":180,"keywords":181,"publishedAt":19},"01M7EWYBN5P6F2AJG3FR24T9BP","design-taste-frontend","tasteskill v2, the anti-slop frontend skill. Art direction for websites, distilled from a study of 247 curated gallery sites (One Page Love, Awwwards Sites of the Day). Deals researched directions (idea, composition, type, palette, photographs, section blueprints) from a library, enforces a strict no-slop house style with a real-browser inspector, and runs a look-and-fix loop on screenshots. Use this whenever you build, design, redesign, restyle, polish or review a landing page, marketing site, portfolio, product page, one-pager, hero or any public-facing web page, in any stack (HTML\u002FCSS, React, Next.js, Vue, Svelte, Astro, Tailwind) — also when the user says a page looks generic, templated, \"AI-made\", sloppy, or asks to make it look designed, premium, award-level or less like every other site. Not for dashboards or app screens.","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Ftaste-design\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Ftaste-design\u002FSKILL.md",[],[],{"skillNo":183,"name":184,"nameZh":6,"description":185,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":186,"categories":187,"keywords":188,"publishedAt":19},"01M7EWY8FQFNQ2GB7NZZWGSSDX","test-driven-development","Use when implementing any feature or bugfix, before writing implementation code","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fsuperpowers-tdd\u002FSKILL.md",[],[],{"skillNo":190,"name":191,"nameZh":6,"description":192,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":193,"categories":194,"keywords":195,"publishedAt":19},"01M7EWY5SHBFRH1HDHVWM9K7TV","systematic-debugging","Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fsuperpowers-debugging\u002FSKILL.md",[],[],{"skillNo":197,"name":198,"nameZh":6,"description":199,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":200,"categories":201,"keywords":202,"publishedAt":19},"01M7EWY3NM0Z0JAKS7HDZ24K66","requesting-code-review","Use when completing tasks, implementing major features, or before merging to verify work meets requirements","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fsuperpowers-code-review\u002FSKILL.md",[],[],{"skillNo":204,"name":205,"nameZh":6,"description":206,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":207,"categories":208,"keywords":209,"publishedAt":19},"01M7EWY0WRMWX4M9ZFY0WKC593","brainstorming","You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation).","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fsuperpowers-brainstorming\u002FSKILL.md",[],[]]