marketing-brief

审查 · 57
已收录

Use when the user wants to generate a marketing brief from a GitHub PR, git ref comparison, codebase feature, or freeform description of a feature or product change

Verified installs0
Stars39
版本1.0.0
质量57/100 · 有潜力
信任57/100 · Do not auto-install
审计70/100 · 需审查

供给资产档案

编程与开发 Agent

代码审查、仓库分析、测试、CI、GitHub、DevOps 与开发工作流 Skill。

浏览赛道

场景

GitHub automation

I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.

适配 Agent

Claude Code + CLI + Codex

适用于 Codex、Claude Code、Cursor、CLI 或自定义 Agent。

安装

就绪

npx skills add AlemTuzlak/skills --skill marketing-brief

维护状态

新鲜

距上次推送 4 天

风险

需审查

许可证不清晰

GitHub 质量

39

57/100 质量 · 65/100 信任

覆盖标签

编程GitHub automation编程 Agentagent-skill

审查说明

许可证不清晰 · Dependency or permission surface needs review

Agent 采用评分卡

一眼查看信任、审计与安装准备度

这些分数综合公开仓库元数据、OpenAgentSkill 审查信号、维护新鲜度与安装准备度。它用于候选筛选,不替代人工审查。

质量

有潜力
57

有用的候选项,但采用前应与替代方案比较。

信任

Do not auto-install
57

Trust Score v5 found insufficient evidence for agent installation. Treat this as discovery material, not an executable recommendation.

审计

需审查
70

对安装准备度、安全元数据、维护情况与采用风险的机器可读审查。

OpenAgentSkill 信任评分 v5

安装前需人工审查

Choose a stronger alternative or inspect the source manually before any install attempt.

CodexClaude CodeCursorOpenAgentSkill CLI

Stars

39 个 GitHub Stars

仓库活跃度

39 个 Star,0 个 Fork

维护状态

距上次推送 4 天

许可证

未知

安装

npx skills add AlemTuzlak/skills --skill marketing-brief

安装安全性

标准软件包或运行时安装路径

权限范围

shell or command execution, filesystem or document access

Agent 结果

暂未有 Agent 结果数据

文档

README/SKILL.md 上下文充分

风险摘要

生产前审查

  • Repository license is unknown; consider adding an explicit open-source license to clarify usage rights.
  • Financial research output is not financial advice; require human review before any live investment decision.
  • 许可证不清晰
  • Low GitHub adoption signal

安装准备度

安装路径可用

  • 安装路径可用
  • 仓库证据可用
  • 许可证不清晰
  • 暂无 Agent 验证结果证据

Agent 可读元数据

这个 Skill 的机器可读决策数据。

使用此区块或内嵌 JSON 判断 Agent 是否应安装该 Skill、选择替代方案,或先请求人工审查。

打开 JSON

适用任务

  • 研究 Agent 工作流
  • Claude Code 团队
  • builders willing to evaluate younger projects
  • 检索来源

适用 Agent

CodexClaude CodeCursorOpenAgentSkill CLICLI

安装决策

命令
npx skills add AlemTuzlak/skills --skill marketing-brief
策略
阻止
人工审查

信任与风险

信任
57/100
审计
70/100
风险级别
需审查

结果闭环

端点
/api/agent/outcome
事件 ID
resolve
结果
5

安装命令

npx skills add AlemTuzlak/skills --skill marketing-brief

不适用场景

  • 需要厂商支持 SLA 的团队
  • production agents without a repository review
  • Low GitHub adoption signal
  • Repository license is unknown; consider adding an explicit open-source license to clarify usage rights.
  • 高风险权限提示:Shell or command execution, Secrets or environment access

Agent 安全 v2

26/100 · 避免自动安装

Blocked for auto-install阻止

This skill should not be selected by an agent without explicit human security review.

Do not auto-install. Inspect the source, dependencies, and permission surface first.

通过 API 解析

Shell 或命令执行

Skill 元数据引用了终端、CLI、Shell、子进程或命令执行工作流。

网络访问

Skill 可能访问远程页面、API、仓库或外部服务。

文件系统访问

Skill 可能读取或写入项目文件、文档、生成产物或本地工作区状态。

Secrets or environment access

Skill metadata references credentials, tokens, environment variables, or secret-bearing workflows.

  • 高风险权限提示:Shell or command execution, Secrets or environment access
  • 许可证不清晰

安装目标

在你的 Agent 工作流中安装此 Skill

通过公开安装端点获取命令、安全清单、目标提示词和该 Skill 的规范链接。

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 alemtuzlak-marketing-brief

Agent 解析计划

让 Agent 在安装前验证匹配度。

Resolve API 返回首选 Skill、替代方案、安全策略、审计说明、安装目标和可直接执行的提示词,无需抓取此页面。

打开文本计划

Agent 应检查

  • 从 Resolve API 检查任务匹配与替代方案。
  • 检查审计评分、信任评分和安全策略警告。
  • 检查 Codex、Claude Code、Cursor 或 CLI 的安装目标兼容性。

复制提示词

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

Agent 交接

把安装路径交给 Agent,而不是再给一个目录页。

通过公开安装端点获取命令、安全清单、目标提示词和该 Skill 的规范链接。

打开安装 API

Agent 提示词

Use marketing-brief for this task. Review https://www.openagentskill.com/api/skills/alemtuzlak-marketing-brief/install, then install with: npx skills add AlemTuzlak/skills --skill marketing-brief

Registry 元数据

用于自动选择 Skill 的 Agent 可读档案。

本页通过 Registry API 提供相同的决策、信任、审计、场景和安装信号,让 Agent 无需抓取界面即可排序。

打开 Manifest

适配 Agent

57/100

研究 Agent

平台

Claude Code

审计报告

需审查 · 70/100

对安装准备度、安全元数据、维护情况与采用风险的机器可读审查。

查看审计报告查看评估报告

Agent 决策面板

Needs validation for Research agents

在将它加入 Agent 工作流前先人工审查仓库。

57
就绪度
审查
阶段

栈中角色

需要验证

主要匹配

研究 Agent

信任标签

需要人工审查

安装路径

命令已就绪

适用场景

  • 研究 Agent 工作流
  • Claude Code 团队
  • builders willing to evaluate younger projects

证据

  • 仓库近期活跃
  • 已提供安装命令或 GitHub 仓库
  • 57/100 质量档案
  • 2 个 OpenAgentSkill 交互事件

先审查

  • Low GitHub adoption signal
  • Repository license is unknown; consider adding an explicit open-source license to clarify usage rights.

实施路径

  1. 1在沙盒 Agent 中安装它,并端到端完成一次研究 Agent任务。
  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.

信任档案

Do not auto-install

Trust Score v5 found insufficient evidence for agent installation. Treat this as discovery material, not an executable recommendation.

57
OpenAgentSkill 信任评分

GitHub 采用度

检查

39 个 GitHub Stars

Star/Fork 活跃度

检查

39 个 Star,0 个 Fork; 当前元数据中没有议题活跃度信息

近期维护

通过

距上次推送 4 天

许可证清晰度

检查

未知

积极信号

  • AI 审查已通过
  • 安装路径可用
  • 仓库证据可用
  • 近期维护的仓库
  • 安装命令未发现明显高风险模式
  • 结果闭环已就绪,但需要首次真实 Agent 运行

安装前审查

  • Repository license is unknown; consider adding an explicit open-source license to clarify usage rights.
  • Financial research output is not financial advice; require human review before any live investment decision.
  • 许可证不清晰
  • Low GitHub adoption signal
  • Quality score needs review
  • Permission surface needs review: shell or command execution, filesystem or document access
  • GitHub adoption: 39 GitHub stars
  • Stars/forks activity: 39 stars, 0 forks; issue activity unavailable in current metadata
  • License clarity: Unknown
  • Dependency/runtime risk: command execution surface, network or browser surface
  • 暂未有真实 Agent 结果报告
  • 无人值守安装前需要人工审查

建议操作

Choose a stronger alternative or inspect the source manually before any install attempt.

质量档案

有潜力 适用于 Agent 工作流的候选

有用的候选项,但采用前应与替代方案比较。

57
GitHub Stars
39
新鲜度
4 天前
安装就绪
许可证
未知
安装前审查: Low GitHub adoption signal · Repository license is unknown; consider adding an explicit open-source license to clarify usage rights.

工作流匹配

在这些场景使用此 Skill

工作流匹配

加入完整工作流

替代方案短名单

安装前对比

可能适合该任务的相近 Skill。

对比全部

概览

--- name: marketing-brief description: Use when the user wants to generate a marketing brief from a GitHub PR, git ref comparison, codebase feature, or freeform description of a feature or product change ---

# Marketing Brief Generator

Generate structured marketing briefs from code changes. Designed for non-marketers who need professional-quality briefs.

## Input Resolution

Resolve the argument (if provided) in this order:

1. Matches GitHub URL or `#\d+` pattern → **PR** 2. Contains `...` or `..` → **git ref range** 3. Resolves to existing file/directory → **codebase feature** 4. Otherwise → **freeform text**

If no argument is provided, ask: "What should I analyze? You can provide a PR URL/number, a git ref range (e.g. v1.0...v2.0), a file/directory path, or just describe the feature."

If multiple interpretations match, confirm with the user.

## Process Flow

```dot digraph marketing_brief { rankdir=TB; "Resolve input" [shape=box]; "Phase 1: Discovery" [shape=box]; "Understanding confirmed?" [shape=diamond]; "Sensitive items?" [shape=diamond]; "Get framing approval" [shape=box]; "Phase 2: Configure" [shape=box]; "Phase 3: Generate" [shape=box]; "Phase 4: Output" [shape=box];

"Resolve input" -> "Phase 1: Discovery"; "Phase 1: Discovery" -> "Understanding confirmed?"; "Understanding confirmed?" -> "Phase 1: Discovery" [label="no, revise"]; "Understanding confirmed?" -> "Sensitive items?" [label="yes"]; "Sensitive items?" -> "Get framing approval" [label="yes"]; "Sensitive items?" -> "Phase 2: Configure" [label="no"]; "Get framing approval" -> "Phase 2: Configure"; "Phase 2: Configure" -> "Phase 3: Generate"; "Phase 3: Generate" -> "Phase 4: Output"; } ```

**Do NOT skip phases.** Ask questions at a natural pace. Don't overwhelm, but don't artificially slow things down either. If the user answers multiple questions at once, accept their bundled answers and skip ahead.

If the user says "just pick defaults", "you choose", or similar, pick reasonable defaults based on context, state what you chose, and ask for a single confirmation before proceeding.

Never make assumptions without confirming with the user. Be conversational and guide them through the process.

## Phase 1: Discovery

### Step 1 — Analyze the input

| Input type | What to read | |---|---| | PR | Diff, PR description, review comments, commit messages (`gh pr view`, `gh pr diff`). For large PRs (20+ files), focus on user-facing changes. | | Git refs | `git diff` and `git log` between the two refs. For large ranges, prioritize commit messages and user-facing changes. | | Codebase feature | Read the specified files/directories. | | Freeform text | Parse the user's description. If it lacks specifics (no feature name, no value prop, no context), ask the user to provide more detail or point to a specific file/PR. Fall back to open-ended questions only if they can't. |

**User-facing changes** include: new features, UI changes, API changes, performance improvements, bug fixes, and documentation updates. **Internal changes** include: refactors, test additions, CI changes, and dependency bumps. When uncertain, list what you found and ask the user which are relevant.

**Error handling:** - `gh` not installed/authenticated → inform user, suggest `gh auth login`, offer alternative input type - Invalid PR number or git ref → tell user it wasn't found, ask to verify - File/directory not found → tell user, ask for correct path

### Step 2 — Read broader product context

Read these if they exist: README, docs/, package.json (or equivalent), any marketing/landing page references.

Goal: understand what the product is, who it's for, what it does.

If none of these exist, ask the user: "I couldn't find product context in the repo. Can you give me a brief description of the product — what it is and who it's for?"

### Step 3 — Present understanding

Present a structured summary:

> "Here's what I understand was built:" > > - [ ] Feature A — short description > - [ ] Feature B — short description > - [ ] Feature C — short description > > "Please confirm, correct, add, or remove items. Which of these should be included in the brief?"

Ask clarifying questions for anything ambiguous. Do NOT proceed until the user confirms the feature scope.

### Step 4 — Flag sensitive items

Scan for: breaking changes, deprecations, security fixes, migration requirements, removed features, controversial decisions.

If found, flag each one:

> "I detected some items that need careful framing:" > > - **Breaking change:** `oldMethod()` was removed > - **Deprecation:** v1 API endpoints marked deprecated > > "How would you like each of these framed in the brief?"

Do NOT proceed to Phase 2 until framing is agreed upon for every sensitive item.

## Phase 2: Brief Configuration

Ask these questions:

**Q1 — Audience:** "Who will read this brief?" (you personally, marketing team, designer, stakeholders, other)

**Q2 — Detail level:** "How detailed should the brief be?" (concise/scannable, moderate, or detailed/prose). The detail level influences depth and tone, not hard word limits. Concise means short punchy sections. Detailed means full prose with depth.

**Q3 — Competitors:** "Are there any competitors you want me to position against? I'll also do my own web research."

**Q4 — Conditional sections:** Evaluate which optional sections are relevant based on the feature context. Present all relevant proposals in a single message, and let the user approve or decline each:

> "I think **[section]** would be useful here because [reason]. Want me to include it?"

Optional sections and when to propose them:

| Section | Propose when | |---|---| | Tone & Voice Guidance | Audience is marketing team or designer who will produce copy | | Visual/Asset Suggestions | Feature has UI component or is visually demonstrable | | Timeline/Launch Window | Change is part of a larger release or has coordination needs | | Success Metrics/KPIs | Audience is stakeholders or marketing team measuring impact | | Risks/Sensitivities | Breaking changes, deprecations, or migrations detected |

Only propose sections you genuinely believe add value. Do not propose all of them every time.

## Phase 3: Brief Generation

### Always-included sections

Write all of these in order:

1. **Executive Summary** — one-paragraph TL;DR of the feature/change 2. **Problem Statement** — what pain point this solves, why it matters 3. **Solution Overview** — what was built, how it works (non-technical, accessible language) 4. **Technical Summary** — what was built, how it works (technical detail). If audience is non-technical, shorten to key implementation details only. 5. **Target Audience** — who benefits, persona descriptions tailored to the product 6. **Value Proposition** — why the audience should care, the key benefit 7. **Competitive Positioning** — comparison to alternatives. Combine user-named competitors with independent web research (use WebSearch). If WebSearch is unavailable, rely on user-provided competitors and your own knowledge. If no competitors found by either source, ask the user: replace with a Market Landscape section describing the category, or omit entirely for internal-only features. If the feature is clearly internal (CI pipeline, admin tool, dev tooling, infrastructure), ask the user: "This looks like an internal change. Skip competitive positioning?" and omit if they confirm. 8. **Key Messages** — 3-5 punchy, ready-to-use talking points 9. **Suggested Channels** — where to distribute (blog, social media, newsletter, documentation, etc.) 10. **Call to Action** — what the reader should do after learning about this 11. **SEO Keywords** — relevant search terms to target

### Conditionally-included sections

Include only those approved in Phase 2, Q4.

### Adaptation rules

- **Depth, tone, and emphasis** adapt to the stated audience and detail level - Both Solution Overview and Technical Summary are always present (briefs may be forwarded to mixed audiences) - Key Messages should be directly usable as copy — not vague summaries

## Phase 4: Output

**Default:** save as `docs/marketing/brief-<feature-slug>.md` in the repo AND print to terminal. Create the `docs/marketing/` directory if it does not exist.

Before saving, ask: "I'll save this to `docs/marketing/brief-<slug>.md`. Want it somewhere else, or should I skip saving and just print it?"

**Feature slug source:**

| Input type | Slug derived from | |---|---| | PR | PR title | | Git refs | Tag/ref name | | Codebase feature | Directory name | | Freeform text | Ask the user |

Slug rules: kebab-case, max 50 characters, alphanumeric and hyphens only.

**If file already exists:** ask whether to overwrite or create a versioned copy (e.g. `brief-dark-mode-v2.md`).

## What this skill does NOT do

- Generate draft marketing copy (tweets, blog posts, emails) - Publish or distribute anything - Create design assets

技术详情

版本
1.0.0
许可证
Unknown
最近更新
2026年8月19日
发布时间
2026年8月19日

决策摘要

需要验证

57
就绪
审查
阶段

仓库近期活跃

审计

安装审查

安装与采用审查

70
需审查
安全性
65/100
维护状态
100/100
安装
92/100
打开完整审计查看评估报告

Agent 验证证据

Agent 验证证据

来自解析、审查、安装和一次小范围运行后的结果报告。

0
已验证
Needs first agent run自动安装: 先审查最近: 未知
成功率
近期失败
结果
0
输出质量
失败
0
不相关
0
安装次数
0
风险拦截
0
需要配置
0
生产环境
0

暂时没有 Agent 结果数据。首次 Agent 执行可以通过 /api/agent/outcome 报告成功、需要设置、风险拦截、失败或不相关。

安装

加入 Agent 工作流

免费且开源. 在生产 Agent 中安装前请先审查报告。

增长闭环

分享工具包

X

为 marketing-brief 准备的场景化草稿,可手动发布到 X。

策展说明
A practical pick for market research:

marketing-brief: Use when the user wants to generate a marketing brief from a GitHub PR, git ref comparison, codebase feature, or freeform d...

39 stars

https://www.openagentskill.com/skills/alemtuzlak-marketing-brief?ref=x
打开 X 草稿
可选:带安装命令的回复
Listing + install path for marketing-brief:
https://www.openagentskill.com/skills/alemtuzlak-marketing-brief?ref=x

Install: npx skills add AlemTuzlak/skills --skill marketing-brief
打开回复草稿

收录来源

Registry 收录

可认领

此列表来自公开来源,维护者认领获批前不会标记为官方。

创作者
AlemTuzlak
收录方
OpenAgentSkill 社区索引

归属链接指向公开仓库或创作者主页。创作者可认领列表以更新所有权信号。

认领此 Skill

所有者认领

认领此 Skill 页面

这条 Registry 收录 列表归属于 AlemTuzlak,但尚未标记为官方。认领后可增加已验证所有者信号,使后续发布、安装和审计更新更值得信赖。

创作者外链工具包

将证据徽章加入你的 README

在开发者评估仓库的位置展示规范页面、当前信任与审计信号,以及真实的 Agent 验证证据。

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

作者

A

AlemTuzlak

@alemtuzlak

平台适配

健康信号

GitHub Stars
39
质量评分
34/100
最近 GitHub 推送
2026年8月19日
框架提示
未知
OpenAgentSkill 浏览量
2
复制安装命令
0
跳转点击
0

社区信号

告诉我们这个 Skill 是否对你的 Agent 工作流有帮助。汇总反馈会持续改善排序。

信任与安全

Do not auto-install

57
  • GitHub 采用度39 个 GitHub Stars检查
  • Star/Fork 活跃度39 个 Star,0 个 Fork; 当前元数据中没有议题活跃度信息检查
  • 近期维护距上次推送 4 天通过
  • 许可证清晰度未知检查
  • README/SKILL.md 完整度元数据包含足够的用法与工作流上下文通过
  • 依赖与运行时风险command execution surface, network or browser surface检查