Execute qualquer Skill no Manus
com um clique

Execute qualquer Skill no Manus com um clique

spring-ai-movie-poster-copywriter

Estrelas218

Forks45

Atualizado2 de março de 2026 às 09:19

Build a movie-poster one-line recommendation pipeline that takes movie title and description, gathers context from Douban and encyclopedia pages, and generates 3-5 Chinese recommendation lines with exactly 12 Chinese characters each. Use when Codex needs to implement crawler-to-prompt workflows, output validation, and recommendation generation APIs.

Instalação

Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.

Executar no Manus

Fonte

microwind

microwind/design-patterns

Abrir repositório GitHub Ver repositórios do creator

Download

Executar no Manus

Ocupações relacionadasSOC

Baseado na classificação ocupacional SOC

Desenvolvedores de softwareInformática e Matemática·SOC 15-1252

Explorador de arquivos

6 arquivos

SKILL.md

readonly

name	spring-ai-movie-poster-copywriter
description	Build a movie-poster one-line recommendation pipeline that takes movie title and description, gathers context from Douban and encyclopedia pages, and generates 3-5 Chinese recommendation lines with exactly 12 Chinese characters each. Use when Codex needs to implement crawler-to-prompt workflows, output validation, and recommendation generation APIs.

Spring AI Movie Poster Copywriter

Workflow

Collect request payload:

Require movieTitle and movieDescription.
Accept optional year, genre, and tone.

Retrieve context:

Query Douban and encyclopedia pages using search first, then fetch detail pages.
Extract only concise facts: genre, setting, themes, cast keywords, awards, and plot hooks.
Ignore user-generated long comments and spoiler-heavy content.

Normalize context:

Convert raw HTML into a compact context block under 1200 Chinese characters.
Keep only deduplicated facts and keywords.
Store retrieval source URLs for traceability.

Generate candidates:

Load prompt templates from references/prompt-template.md.
Ask model to generate 8-10 candidates first.
Keep temperature moderate (0.6 to 0.8) to balance creativity and control.

Validate and filter:

Run scripts/validate_slogans.py against candidate lines.
Keep final 3-5 lines that satisfy length and uniqueness checks.
If fewer than 3 survive, regenerate with stricter prompt constraints.

Return API response:

Follow references/output-schema.json.
Return final lines plus evidence URLs from Douban/encyclopedia retrieval.

Guardrails

Respect robots and rate limits; cache page fetches by URL.
Avoid sensitive, discriminatory, or explicit wording in slogans.
Keep language punchy and cinematic; avoid spoilers and plot twists.
Always validate line length in code, not by model assumption.

Resources

references/prompt-template.md: system/user prompt templates.
references/source-extraction.md: context extraction field rules.
references/output-schema.json: API output contract.
scripts/validate_slogans.py: strict 12-Chinese-character validator.

Mais deste repositório

mesmo repositório

spring-ai-boot4-project-starter

microwind/design-patterns

Bootstrap and standardize Spring Boot 4.0.3 + Spring AI backend projects for new implementations. Use when Codex needs to initialize a project, set Maven dependencies/BOM, define package and module layout, configure environment profiles, or create baseline API/AI/database scaffolding.

2026-03-02218

spring-ai-rag-media-pgvector

microwind/design-patterns

Build RAG pipelines for media-asset knowledge bases using Spring AI and PostgreSQL pgvector. Use when Codex needs to design database schema, ingestion/chunking/embedding workflow, and retrieval logic that prioritizes internal media knowledge before falling back to general model knowledge.

2026-03-02218

name	spring-ai-movie-poster-copywriter
description	Build a movie-poster one-line recommendation pipeline that takes movie title and description, gathers context from Douban and encyclopedia pages, and generates 3-5 Chinese recommendation lines with exactly 12 Chinese characters each. Use when Codex needs to implement crawler-to-prompt workflows, output validation, and recommendation generation APIs.

Spring AI Movie Poster Copywriter

Workflow

Collect request payload:

Require movieTitle and movieDescription.
Accept optional year, genre, and tone.

Retrieve context:

Query Douban and encyclopedia pages using search first, then fetch detail pages.
Extract only concise facts: genre, setting, themes, cast keywords, awards, and plot hooks.
Ignore user-generated long comments and spoiler-heavy content.

Normalize context:

Convert raw HTML into a compact context block under 1200 Chinese characters.
Keep only deduplicated facts and keywords.
Store retrieval source URLs for traceability.

Generate candidates:

Load prompt templates from references/prompt-template.md.
Ask model to generate 8-10 candidates first.
Keep temperature moderate (0.6 to 0.8) to balance creativity and control.

Validate and filter:

Run scripts/validate_slogans.py against candidate lines.
Keep final 3-5 lines that satisfy length and uniqueness checks.
If fewer than 3 survive, regenerate with stricter prompt constraints.

Return API response:

Follow references/output-schema.json.
Return final lines plus evidence URLs from Douban/encyclopedia retrieval.

Guardrails

Respect robots and rate limits; cache page fetches by URL.
Avoid sensitive, discriminatory, or explicit wording in slogans.
Keep language punchy and cinematic; avoid spoilers and plot twists.
Always validate line length in code, not by model assumption.

Resources

references/prompt-template.md: system/user prompt templates.
references/source-extraction.md: context extraction field rules.
references/output-schema.json: API output contract.
scripts/validate_slogans.py: strict 12-Chinese-character validator.