菜单
Guide research methodology and source selection for content topics. Use when the user asks to "research topics", "find trending news", "scan for content ideas", "verify sources", or needs guidance on which sources to trust, how to evaluate source quality, or where to find market-specific data.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | research-sources |
| description | Guide research methodology and source selection for content topics. Use when the user asks to "research topics", "find trending news", "scan for content ideas", "verify sources", or needs guidance on which sources to trust, how to evaluate source quality, or where to find market-specific data. |
| version | 0.2.0 |
Guide for finding, evaluating, and citing sources for blog content. All source lists are loaded from config/project.json → research_sources and regulatory.agencies.
Load from config/project.json → regulatory.agencies. Use for:
Load from config/project.json → research_sources.front_pages and business_sections. Use for:
Load from config/project.json → research_sources.macro_economic. Use for:
Load from config/project.json → research_sources:
platform_sources): e-commerce reports, delivery insights, professional network dataindustry_associations): federation surveys, SME reportsresearch_firms): bank SME surveys, consumer researchconfig/project.json → research_sources.search_keywordsIs the topic about government policy, compliance, or official programs?
YES → Government portals + official news → Tier 1
NO → Is it about market trends, platforms, or industry data?
YES → Platform data + industry associations → Tier 2
MIXED → Use both source categories → Choose tier by primary angle
Load from config/project.json → research_sources.search_keywords:
base: core industry keywordsfinancing: funding and financing keywordscompliance: regulatory and compliance keywordsindustry: sector-specific keywordsAlways append the current year to search queries for freshness.
config/project.json → market.trusted_news_domainsUse hybrid citation style:
[a][a][a] Source Name - URLIf WebFetch is denied for a URL:
Activates during any ads-visual-fs command workflow when a structured user decision is needed. Provides the 4-section conversational format (Context, Explanation, Suggestion, Cost) and reusable patterns (Platform Selection, Visual Elements, Concept Selection, Next Action, Style Presets). This is a shared UX protocol, not a user-facing workflow.
Activates when generating creative concept variations at multiple conceptual levels (SAFE/BOLD/EXPERIMENTAL) for ad campaigns. Produces titles, rationales, and image generation prompts. This is a shared creative capability, not a user-facing workflow.
Activates during /create and /campaign workflows when the user needs to choose a visual style for ad creation. Provides 4 predefined styles (Warm Showcase, Bold Professional, Tech Forward, Aspirational Shadow) plus Custom. Each style defines required visual elements, composition, layout, and mood.
Activates after image generation to evaluate the output against brand compliance and brief alignment. Runs as step 5b in the standard workflow — between Generate and Review. Auto-retries on gross brand failures; advisory-only for fine-grained issues.
Activates during any ad creative work for Funding Societies — generation, refinement, resizing, or review. Enforces FS brand colors, typography, tone, logo usage, and regulatory compliance. This is a shared compliance capability that enhances all workflows.
Activates when analyzing a competitor ad for transferable creative strategies — extracting layout architecture, visual metaphor, color psychology, typography approach, imagery style, emotional appeal, messaging strategy, and attention mechanics, then mapping each to FS brand equivalents. This is a shared analysis capability, not a user-facing workflow.