Skills Plugins MCP Prompt Model 博客 我的中心
内容创作 #video #design #api

insta-master

Plan and create Instagram content, improve profiles, diagnose distribution from account evidence, and design scoped growth or monetization experiments. Use for Instagram-specific content and strategy; not video editing, API uploads, or other platforms.

DeepseekModel 官方收录技能 质量 优秀 · 90 v1.0.0

获取

https://deepseekmodel.com/api/download.php?id=pedronauck-skills-skills-mine-insta-master-skill-md&format=skill
下载 .skill 标准格式,含 system_prompt 与 model_config,导入任意 Agent 框架即可使用
.skill 文件中 system_prompt 字段的实际内容。
name insta-master description Plan and create Instagram content, improve profiles, diagnose distribution from account evidence, and design scoped growth or monetization experiments. Use for Instagram-specific content and strategy; not video editing, API uploads, or other platforms. metadata {"author":"Pedro Nauck","github":"https://github.com/pedronauck","repository":"https://github.com/pedronauck/skills"} Instagram Content and Strategy Create or improve the requested Instagram content, profile, distribution experiment, or monetization plan. Use the founder/creator's existing audience, voice, goals, and observations. A caption or Reel does not require rebuilding the profile, a COCA matrix, and a monetization strategy first. Use the matching reference sections: Profile/niche: references/perfil-nicho-autoridade.md . Reels: references/reels.md ; Stories/cadence: references/stories-e-cadencia.md . Distribution diagnosis: references/algoritmo-e-distribuicao.md . Creator monetization: references/monetizacao-creator.md ; client/service work: references/social-media-negocio.md . Publication inspection: references/checklist-publicacao.md . Consult other bundled references only for a question they resolve. Quantitative retention thresholds, posting/hashtag counts, content frameworks, and historical creator methods are hypotheses to test against the account's data, not platform guarantees. Verify current platform behavior/policies and commercial facts when they affect a recommendation. Do not infer a shadowban from weak reach alone. Draft the requested artifact with a clear purpose, audience, format, main message, and CTA when useful. Use assets/briefing-conteudo.template.md for a substantial brief; for a single item, the existing context is often enough. Generate a small useful set of options before expanding, and diagnose available data with stated sample limits instead of demanding a month of posts. Before authorized publication, check factual claims, originality/rights, consent and applicable AI disclosures, legibility, and working destinations. Reuse account-specific evidence; no mandatory first-hour/30-day reporting or fixed daily engagement quota. Publishing, outreach, paid promotion, and purchases require explicit authorization. Never substitute spam or manufactured engagement for evidence of audience value.
Agent 识别该技能的关键词,点击任意一个即可复制。

该技能未提供触发词。

下载的 .skill 包内含以下字段。
字段 说明
format格式标识(skill/v1)
skill_id技能唯一 ID
name技能名称
version版本号
description技能描述
category所属分类(数组)
trigger_words触发词列表
tags标签列表
source来源标识
source_url来源链接(本页地址)
exported_at导出时间(每次下载生成)
system_prompt系统提示词正文
model_config模型参数:provider / model / temperature / max_tokens / top_p
examples示例
install_guide各平台导入说明(Coze / Dify / Claude / 自定义框架)
同一份技能可按不同平台格式导出。
.skill 标准格式,含 system_prompt 与 model_config,导入任意 Agent 框架即可使用 下载
.skillpro 增强格式,额外含脚本 / 工具 / 依赖 / 钩子占位 下载
.json 纯 JSON 导出,只含 system_prompt 与模型参数 下载
Coze 带 frontmatter 的 Markdown,Coze 平台导入用 下载
Dify Dify DSL,创建应用后直接导入 下载

每日精选 Skill 推荐,免费送到你邮箱

输入邮箱,每天接收一个精选 AI Agent 技能推荐。完全免费,持续更新。

验证码 --

提交后我们会发送一封确认邮件,点击邮件里的链接才会开始收信。

完全免费,取消任意时间。我们不会发送垃圾邮件。