img-gen-taste

Tinjau · 67
Diindeks di Registry

Develop art direction for image generation with curated style cards distilled from Open Image Prompts. Use when choosing or comparing visual directions, improving an existing generation prompt, or translating a subject, use case, or supplied image into a compact creative spec. Us

Verified installs0
Star224
Versi1.0.0
Kualitas71/100 · Kuat
Kepercayaan67/100 · Hanya sandbox
Audit81/100 · Perlu ditinjau

Profil aset

Riset dan pekerjaan pengetahuan

Deep research, source comparison, literature review, RAG, knowledge search, and reports.

Lihat kategori

Skenario

Agent riset

I need my agent to research a topic, compare sources, and produce a concise report.

Kecocokan Agent

Claude Code + CLI + Codex

Cocok untuk Codex, Claude Code, Cursor, CLI, atau Agent khusus.

Pasang

Siap

npx skills add NanmiCoder/open-image-prompts --skill img-gen-taste

Pemeliharaan

Terkini

Diperbarui hari ini

Risiko

Perlu ditinjau

Financial research output is not financial advice; require human review before any live investment decision

Kualitas GitHub

224

71/100 Kualitas · 75/100 Kepercayaan

Tag cakupan

RisetAgent risetagent-skill

Catatan ulasan

Financial research output is not financial advice; require human review before any live investment decision · The skill references another skill `$img-gen-prompts` for real-reference requests, but its availability and interface are not documented within this skill. This creates a dependency that may not be present in all environments.

Kartu adopsi Agent

Kepercayaan, audit, dan kesiapan pemasangan dalam sekali lihat

Skor ini menggabungkan metadata repositori publik, sinyal ulasan OpenAgentSkill, kebaruan pemeliharaan, dan kesiapan pemasangan. Ini adalah sinyal shortlist, bukan pengganti peninjauan manusia.

Kualitas

Kuat
71

Solid option that is likely worth shortlisting for production workflows.

Kepercayaan

Hanya sandbox
67

Kandidat berguna dengan sinyal kepercayaan yang kurang atau bercampur. Gunakan di ruang kerja terisolasi hingga loop hasil membuktikan kecocokan tugas.

Audit

Perlu ditinjau
81

Tinjauan yang dapat dibaca mesin tentang kesiapan pemasangan, metadata keamanan, pemeliharaan, dan risiko adopsi.

Trust Score OpenAgentSkill v5

Tinjauan manusia sebelum pemasangan

Jalankan hanya dalam sandbox dan bandingkan alternatif terdekat sebelum digunakan untuk kerja nyata.

CodexClaude CodeCursorOpenAgentSkill CLI

Star

224 star GitHub

Aktivitas repositori

224 star dan 30 fork

Pemeliharaan

Diperbarui hari ini

Lisensi

MIT

Pasang

npx skills add NanmiCoder/open-image-prompts --skill img-gen-taste

Keamanan pemasangan

Jalur pemasangan paket atau runtime standar

Cakupan izin

Tidak ada cakupan izin berisiko tinggi dalam metadata publik

Hasil Agent

Belum ada data hasil Agent

Dokumentasi

Konteks README/SKILL.md kuat

Ringkasan risiko

Tinjau sebelum produksi

  • The skill references another skill `$img-gen-prompts` for real-reference requests, but its availability and interface are not documented within this skill. This creates a dependency that may not be present in all environments.
  • Financial research output is not financial advice; require human review before any live investment decision.
  • Quality score needs review
  • Stars/forks activity: 224 stars, 30 forks; issue activity unavailable in current metadata

Kesiapan pemasangan

Jalur pemasangan tersedia

  • Jalur pemasangan tersedia
  • Bukti repositori tersedia
  • Lisensi dinyatakan
  • Belum ada bukti hasil Agent-Proven

Metadata yang dapat dibaca Agent

Data keputusan yang dapat dibaca mesin untuk skill ini.

Gunakan blok ini atau JSON tersemat untuk memutuskan apakah Agent perlu memasang skill ini, memilih alternatif, atau meminta tinjauan manusia terlebih dahulu.

Buka JSON

Tugas yang sesuai

  • Alur kerja Agent riset
  • Tim Claude Code
  • builders willing to evaluate younger projects
  • Sumber pencarian

Agent yang sesuai

CodexClaude CodeCursorOpenAgentSkill CLICLI

Keputusan pemasangan

Perintah
npx skills add NanmiCoder/open-image-prompts --skill img-gen-taste
Kebijakan
Tinjau
Tinjauan manusia
Ya

Kepercayaan dan risiko

Kepercayaan
67/100
Audit
81/100
Tingkat risiko
Perlu ditinjau

Lingkar hasil

Endpoint
/api/agent/outcome
ID event
resolve
Hasil
5

Perintah pemasangan

npx skills add NanmiCoder/open-image-prompts --skill img-gen-taste

Jangan gunakan ketika

  • Tim yang membutuhkan SLA dengan dukungan vendor
  • production agents without a repository review
  • The skill references another skill `$img-gen-prompts` for real-reference requests, but its availability and interface are not documented within this skill. This creates a dependency that may not be present in all environments.
  • No OpenAgentSkill engagement data yet
  • Financial research output is not financial advice; require human review before any live investment decision

Keamanan Agent v2

65/100 · Tinjau sebelum memasang

Ditinjau dengan catatan izinTinjau

Kandidat yang dapat digunakan, tetapi Agent harus menampilkan catatan izin dan audit sebelum memasang.

Memerlukan persetujuan manusia sebelum memasang ke workspace nyata.

Selesaikan via API

Sedang

Akses jaringan

Skill kemungkinan mengambil halaman jarak jauh, API, repositori, atau layanan eksternal.

Sedang

Akses sistem file

Skill dapat membaca atau menulis file proyek, dokumen, artefak yang dihasilkan, atau status workspace lokal.

  • Financial research output is not financial advice; require human review before any live investment decision

Target pemasangan

Pasang skill ini di alur Agent Anda

Gunakan endpoint publik untuk mengambil perintah, checklist keamanan, prompt target, dan tautan kanonis.

skill install

OpenAgentSkill CLI

Resolve policy, run the source installer safely, and report a verified install receipt.

$ npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install nanmicoder-img-gen-taste

Rencana resolusi Agent

Biarkan Agent memverifikasi kecocokan sebelum memasang.

API Resolve mengembalikan skill utama, alternatif, kebijakan keamanan, catatan audit, target pemasangan, dan prompt siap pakai.

Buka rencana teks

Agent harus memeriksa

  • Task fit and alternatives from Resolve API.
  • Audit score, trust score, and safety policy warnings.
  • Install target compatibility for Codex, Claude Code, Cursor, or CLI.

Salin prompt

Task: Use img-gen-taste in this workspace.
Resolve first: https://www.openagentskill.com/api/agent/resolve?task=Use%20img-gen-taste%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Review install handoff: https://www.openagentskill.com/api/skills/nanmicoder-img-gen-taste/install
Install command: npx skills add NanmiCoder/open-image-prompts --skill img-gen-taste
Before running it, summarize audit warnings, required permissions, and the fallback skill if install is risky.

Serah-terima Agent

Berikan jalur pemasangan kepada Agent, bukan direktori lain.

Gunakan endpoint publik untuk mengambil perintah, checklist keamanan, prompt target, dan tautan kanonis.

Buka API pemasangan

Prompt Agent

Use img-gen-taste for this task. Review https://www.openagentskill.com/api/skills/nanmicoder-img-gen-taste/install, then install with: npx skills add NanmiCoder/open-image-prompts --skill img-gen-taste

Metadata Registry

Profil yang dapat dibaca Agent untuk pemilihan skill otomatis.

API Registry menyediakan sinyal keputusan, kepercayaan, audit, use case, dan pemasangan tanpa mengikis UI.

Buka Manifest

Kecocokan Agent

70/100

Agent riset

Platform

Claude Code

Laporan audit

Perlu ditinjau · 81/100

Tinjauan yang dapat dibaca mesin tentang kesiapan pemasangan, metadata keamanan, pemeliharaan, dan risiko adopsi.

Lihat laporan auditLihat laporan evaluasi

Panel keputusan Agent

Fallback candidate for Research agents

Prototype with this skill first; keep a fallback candidate ready.

70
Kesiapan
Prototipe
Tahap

Peran di stack

Kandidat cadangan

Kecocokan utama

Agent riset

Label kepercayaan

Buat prototipe dulu

Jalur pemasangan

Perintah siap

Gunakan saat

  • Alur kerja Agent riset
  • Tim Claude Code
  • builders willing to evaluate younger projects

Bukti

  • recent repository activity
  • install command or GitHub repo available
  • profil kualitas 71/100

tinjau dulu

  • The skill references another skill `$img-gen-prompts` for real-reference requests, but its availability and interface are not documented within this skill. This creates a dependency that may not be present in all environments.
  • No OpenAgentSkill engagement data yet

Jalur implementasi

  1. 1Pasang di Agent sandbox dan jalankan satu tugas Agent riset dari awal hingga akhir.
  2. 2Compare output quality, latency, and failure behavior against at least one alternative.
  3. 3Promote it into production only after reviewing repository permissions, license, and maintenance signals.

Profil kepercayaan

Hanya sandbox

Kandidat berguna dengan sinyal kepercayaan yang kurang atau bercampur. Gunakan di ruang kerja terisolasi hingga loop hasil membuktikan kecocokan tugas.

67
Trust Score OpenAgentSkill

Adopsi GitHub

Info

224 star GitHub

Aktivitas star/fork

Periksa

224 star dan 30 fork; aktivitas issue tidak tersedia dalam metadata saat ini

Pemeliharaan terbaru

Lulus

Diperbarui hari ini

Kejelasan lisensi

Lulus

MIT

Sinyal positif

  • Tinjauan AI disetujui
  • Jalur pemasangan tersedia
  • Bukti repositori tersedia
  • Repositori yang baru dipelihara
  • Perintah pemasangan tidak memiliki pola berisiko tinggi yang jelas
  • Loop hasil siap tetapi membutuhkan eksekusi Agent nyata pertama

Tinjau sebelum memasang

  • The skill references another skill `$img-gen-prompts` for real-reference requests, but its availability and interface are not documented within this skill. This creates a dependency that may not be present in all environments.
  • Financial research output is not financial advice; require human review before any live investment decision.
  • Quality score needs review
  • Stars/forks activity: 224 stars, 30 forks; issue activity unavailable in current metadata
  • Belum ada laporan hasil Agent nyata
  • Tinjauan manusia diperlukan sebelum pemasangan tanpa pengawasan

Tindakan yang disarankan

Jalankan hanya dalam sandbox dan bandingkan alternatif terdekat sebelum digunakan untuk kerja nyata.

Profil kualitas

Kuat kandidat untuk alur kerja Agent

Solid option that is likely worth shortlisting for production workflows.

71
Star GitHub
224
Keterkinian
Hari ini
Siap dipasang
Ya
Lisensi
MIT
Tinjau sebelum memasang: The skill references another skill `$img-gen-prompts` for real-reference requests, but its availability and interface are not documented within this skill. This creates a dependency that may not be present in all environments.

Kecocokan alur kerja

Gunakan skill ini pada skenario berikut

Kecocokan alur kerja

Tambahkan ke alur kerja lengkap

Daftar alternatif

Bandingkan sebelum memasang

Similar skills that may fit this task.

Bandingkan semua

Ringkasan

--- name: img-gen-taste description: Develop art direction for image generation with curated style cards distilled from Open Image Prompts. Use when choosing or comparing visual directions, improving an existing generation prompt, or translating a subject, use case, or supplied image into a compact creative spec. Use img-gen-prompts for real archive examples, exact source prompts, or gallery browsing. ---

# Img Gen Taste

Act as the art-direction layer before generation. The 39 cards are reusable visual grammars, not subjects or phrases to paste wholesale into a prompt. Load only the reference needed for the request.

## Route the request

Identify the literal subject, intended use, mood, hard constraints, and aspect ratio. Ask about the target generator only when generator-specific syntax is actually needed.

| Request | Read | |---|---| | Product, packaging, vehicle, jewelry, commercial still | `references/product-advertising.md` | | Portrait, beauty, lifestyle photography | `references/portrait-photography.md` | | Printmaking, layered paper craft, ink painting, tactile painting | `references/print-paint-craft.md` | | Food and drink | `references/food-drink.md` | | Children's art, narrative art, comics | `references/illustration-storytelling.md` | | Poster, cover, typography-led composition | `references/poster-cover.md` | | Architecture or interior | `references/architecture-interior.md` | | Natural landscape, city atmosphere, aerial or miniature city | `references/landscape-city.md` | | Fantasy, science fiction, game concept | `references/sci-fi-fantasy.md` | | Abstract, 3D, graphic or web-hero visual | `references/graphic-abstract.md` |

Read at most two references for a genuinely cross-domain request. If no card fits, compose from first principles and say that no card was used. Route by the requested visual grammar: a tattoo, car, or bottle is a subject, not a style.

Every card carries an explicit id bullet, written as ``- `id`: `card-id` ``. Take `style_card_id` from that bullet only — some files use the id as the section heading and others use a prose title, so a heading is not a reliable id.

## Work in two phases

1. **Explore when direction is unclear.** Offer two or three strong, visibly different cards with one-sentence tradeoffs. Do not force a weak third option. Wait for the user's choice before writing a long prompt. 2. **Commit when direction is clear or chosen.** Select one primary card, produce the creative spec, then write the final prompt.

User constraints always override card defaults, including aspect ratio, text, people, product geometry, brand elements, and forbidden content. A card may shape composition, material, light, palette, and mood; it must not silently add story content, locations, props, or decorative metaphors. Treat `Avoid` as hard guidance. Offer `experimental-corpus-reviewed` cards only as disclosed alternatives alongside a non-experimental direction.

## Return the hand-off contract

Use this exact key and field structure so `$img-gen-prompts` can consume the result without reinterpretation:

```yaml creative_spec: style_card_id: <one card id or null> subject: <literal user subject> use: <deliverable> composition: <framing and hierarchy> material_texture: <relevant physical cues> lighting: <motivated source and contrast> palette: <restrained color relationship> mood: <one or two precise qualities> invariants: [<must keep>] avoid: [<failure modes>] aspect_ratio: <ratio or unspecified> ```

After the spec, provide a copyable English prompt and Simplified Chinese for a Chinese-speaking user. Keep required in-image text quoted and exact. Do not add technical-looking details that the direction does not require.

## Hand off real-reference requests

When the user asks to see examples, compare images, inspect original prompts, find similar archive records, or browse a gallery, invoke `$img-gen-prompts` with the original request and `creative_spec`. Preserve source prompts exactly; write improvements as separate derived prompts. Do not send a mixed bundle of retrieved images to a generator automatically—use only coherent references the user selected or that provide uniquely relevant visual evidence.

Treat `corpus-reviewed / generation-pending` as reviewed archive evidence, not proof of a measured generation-quality improvement.

Detail teknis

Versi
1.0.0
Lisensi
MIT
Pembaruan terakhir
22 Agu 2026
Diterbitkan
22 Agu 2026

Ringkasan keputusan

Kandidat cadangan

70
Siap
Prototipe
Tahap

recent repository activity

Audit

Tinjauan pemasangan

Tinjauan pemasangan dan adopsi

81
Perlu ditinjau
Keamanan
83/100
Pemeliharaan
100/100
Pasang
92/100
Buka audit lengkapLihat laporan evaluasi

Bukti tervalidasi Agent

Bukti tervalidasi Agent

Laporan hasil setelah resolve, tinjau, pasang, dan satu eksekusi terbatas.

0
Terbukti
Needs first agent runPasang otomatis: tinjau duluTerakhir: Tidak diketahui
Tingkat sukses
Kegagalan terbaru
Hasil
0
Kualitas output
Gagal
0
Tidak relevan
0
Pemasangan
0
Diblokir risiko
0
Perlu penyiapan
0
Produksi
0

Belum ada data hasil Agent. Eksekusi pertama dapat melaporkan keberhasilan, kebutuhan setup, blok risiko, kegagalan, atau tidak relevan melalui /api/agent/outcome.

Pasang

Tambahkan ke alur Agent

Gratis dan sumber terbuka. Tinjau laporan sebelum memasang pada Agent produksi.

Siklus pertumbuhan

Kit berbagi

X

Draf berbasis skenario untuk img-gen-taste, siap untuk posting manual di X.

Catatan kurator
img-gen-taste: Develop art direction for image generation with curated style cards distilled from Open Image...

224 stars

https://www.openagentskill.com/skills/nanmicoder-img-gen-taste?ref=x
Buka draf X
Balasan opsional dengan perintah pemasangan
Listing + install path for img-gen-taste:
https://www.openagentskill.com/skills/nanmicoder-img-gen-taste?ref=x

Install: npx skills add NanmiCoder/open-image-prompts --skill img-gen-taste
Buka draf balasan

Sumber listing

Diindeks Registry

Dapat diklaim

Listing ini diindeks dari sumber publik dan belum ditandai resmi hingga klaim pemelihara disetujui.

Kreator
NanmiCoder
Diindeks oleh
Indeks komunitas OpenAgentSkill

Atribusi menautkan ke repositori publik atau profil kreator. Kreator dapat mengklaim listing untuk memperbarui sinyal kepemilikan.

Klaim skill ini

Klaim pemilik

Klaim listing skill ini

Listing Diindeks Registry ini dikaitkan dengan NanmiCoder, tetapi belum ditandai resmi. Klaim untuk menambahkan sinyal pemilik terverifikasi dan membuat pembaruan peluncuran, pemasangan, serta audit berikutnya lebih tepercaya.

Kit backlink kreator

Tambahkan badge bukti ke README Anda

Tampilkan listing kanonis, sinyal kepercayaan dan audit saat ini, serta bukti Agent-Proven nyata di tempat pengembang mengevaluasi repositori.

[![Listed on OpenAgentSkill](https://www.openagentskill.com/api/badge/nanmicoder-img-gen-taste?metric=listed&label=Listed)](https://www.openagentskill.com/skills/nanmicoder-img-gen-taste)
[![OpenAgentSkill Trust](https://www.openagentskill.com/api/badge/nanmicoder-img-gen-taste?metric=trust&label=Trust)](https://www.openagentskill.com/skills/nanmicoder-img-gen-taste)
[![OpenAgentSkill Audit](https://www.openagentskill.com/api/badge/nanmicoder-img-gen-taste?metric=audit&label=Audit)](https://www.openagentskill.com/skills/nanmicoder-img-gen-taste/audit)
[![Agent Proven](https://www.openagentskill.com/api/badge/nanmicoder-img-gen-taste?metric=proven&label=Agent%20Proven)](https://www.openagentskill.com/skills/nanmicoder-img-gen-taste)

Penulis

N

NanmiCoder

@nanmicoder

Kecocokan platform

Sinyal kesehatan

Star GitHub
224
Skor kualitas
40/100
Push GitHub terakhir
22 Agu 2026
Petunjuk framework
Tidak diketahui
Tampilan OpenAgentSkill
0
Salinan pemasangan
0
Klik keluar
0

Sinyal komunitas

Bagikan apakah skill ini bermanfaat untuk alur kerja Agent Anda. Masukan gabungan meningkatkan peringkat dari waktu ke waktu.

Kepercayaan & keamanan

Hanya sandbox

67
  • Adopsi GitHub224 star GitHubInfo
  • Aktivitas star/fork224 star dan 30 fork; aktivitas issue tidak tersedia dalam metadata saat iniPeriksa
  • Pemeliharaan terbaruDiperbarui hari iniLulus
  • Kejelasan lisensiMITLulus
  • Kelengkapan README/SKILL.mdMetadata memuat konteks penggunaan dan alur kerja yang cukupLulus
  • Risiko dependensi/runtimeTidak ada petunjuk risiko dependensi besar dalam metadata publikLulus