outline

审查 · 68
已收录

Turn a vague idea into a tight, format-specific outline through structured interrogation. Use when the user is stuck on structure, does not know what to write, or has a topic but no angle. Works for newsletters, sales pages, posts, scenes, and scripts.

Verified installs0
Stars28
版本1.0.0
质量61/100 · 有潜力
信任68/100 · 仅限沙盒
审计78/100 · 需审查

供给资产档案

研究与知识工作

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

浏览赛道

场景

研究 Agent

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

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 Deupaxx/EveryDay-Writer --skill outline

维护状态

新鲜

距上次推送 2 天

风险

需审查

The skill depends on external files (core/anti-ai-rules.md, core/ai_slop_commandments.md, core/voice-profile.md) that are not included in the skill directory. This may cause failures if the skill is used outside the full repository context.

GitHub 质量

28

61/100 质量 · 76/100 信任

覆盖标签

研究研究 Agentagent-skill

审查说明

The skill depends on external files (core/anti-ai-rules.md, core/ai_slop_commandments.md, core/voice-profile.md) that are not included in the skill directory. This may cause failures if the skill is used outside the full repository context. · Low GitHub adoption signal

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
61

有用的候选项,但采用前应与替代方案比较。

信任

仅限沙盒
68

有用但信任信号不足或混杂的候选项。在结果闭环证明任务匹配前,请保持在隔离工作区内使用。

审计

需审查
78

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

仅在沙盒中运行,并在用于真实工作前比较接近的替代方案。

CodexClaude CodeCursorOpenAgentSkill CLI

Stars

28 个 GitHub Stars

仓库活跃度

28 个 Star,5 个 Fork

维护状态

距上次推送 2 天

许可证

MIT

安装

npx skills add Deupaxx/EveryDay-Writer --skill outline

安装安全性

标准软件包或运行时安装路径

权限范围

公开元数据中未发现高风险权限范围

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

  • The skill depends on external files (core/anti-ai-rules.md, core/ai_slop_commandments.md, core/voice-profile.md) that are not included in the skill directory. This may cause failures if the skill is used outside the full repository context.
  • Low GitHub adoption signal
  • Quality score needs review
  • GitHub adoption: 28 GitHub stars

安装准备度

安装路径可用

  • 安装路径可用
  • 仓库证据可用
  • 已声明许可证
  • 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 Deupaxx/EveryDay-Writer --skill outline
策略
审查
人工审查

信任与风险

信任
68/100
审计
78/100
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 Deupaxx/EveryDay-Writer --skill outline

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
  • The skill depends on external files (core/anti-ai-rules.md, core/ai_slop_commandments.md, core/voice-profile.md) that are not included in the skill directory. This may cause failures if the skill is used outside the full repository context.
  • Quality score needs review

Agent 安全 v2

62/100 · 安装前审查

已审查并附权限说明审查

可用候选,但 Agent 在安装前应展示权限与审计说明。

在真实工作区安装前需要人工批准。

通过 API 解析

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。

  • The skill depends on external files (core/anti-ai-rules.md, core/ai_slop_commandments.md, core/voice-profile.md) that are not included in the skill directory. This may cause failures if the skill is used outside the full repository context.

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 deupaxx-outline

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 outline in this workspace.
Resolve first: https://www.openagentskill.com/api/agent/resolve?task=Use%20outline%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Review install handoff: https://www.openagentskill.com/api/skills/deupaxx-outline/install
Install command: npx skills add Deupaxx/EveryDay-Writer --skill outline
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 outline for this task. Review https://www.openagentskill.com/api/skills/deupaxx-outline/install, then install with: npx skills add Deupaxx/EveryDay-Writer --skill outline

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

61/100

研究 Agent

平台

Claude Code

审计报告

需审查 · 78/100

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

Fallback candidate for Research agents

先用此 Skill 做原型验证,并保留备选方案。

61
就绪度
原型验证
阶段

栈中角色

备选候选

主要匹配

研究 Agent

信任标签

先做原型验证

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
  • 61/100 质量档案
  • 2 个 OpenAgentSkill 交互事件

先审查

  • Low GitHub adoption signal
  • The skill depends on external files (core/anti-ai-rules.md, core/ai_slop_commandments.md, core/voice-profile.md) that are not included in the skill directory. This may cause failures if the skill is used outside the full repository context.

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

仅限沙盒

有用但信任信号不足或混杂的候选项。在结果闭环证明任务匹配前,请保持在隔离工作区内使用。

68
OpenAgentSkill 信任评分

GitHub 采用度

检查

28 个 GitHub Stars

Star/Fork 活跃度

检查

28 个 Star,5 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 2 天

许可证清晰度

通过

MIT

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

  • The skill depends on external files (core/anti-ai-rules.md, core/ai_slop_commandments.md, core/voice-profile.md) that are not included in the skill directory. This may cause failures if the skill is used outside the full repository context.
  • Low GitHub adoption signal
  • Quality score needs review
  • GitHub adoption: 28 GitHub stars
  • Stars/forks activity: 28 stars, 5 forks; issue activity unavailable in current metadata
  • 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

仅在沙盒中运行,并在用于真实工作前比较接近的替代方案。

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。

61
GitHub Stars
28
新鲜度
2 天前
安装就绪
许可证
MIT
安装前审查: Low GitHub adoption signal · The skill depends on external files (core/anti-ai-rules.md, core/ai_slop_commandments.md, core/voice-profile.md) that are not included in the skill directory. This may cause failures if the skill is used outside the full repository context.

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: outline description: | Turn a vague idea into a tight, format-specific outline through structured interrogation. Use when the user is stuck on structure, does not know what to write, or has a topic but no angle. Works for newsletters, sales pages, posts, scenes, and scripts. license: MIT metadata: version: "0.3.0" ---

# EW Skill — Idea-to-Outline Engine

**Dependency chain. Read these in order before writing anything:**

1. `core/anti-ai-rules.md` (read fully; Section 0 sets the standard, 0.1 sets precedence, 0.2 forbids fabrication, 9 and 10 stop over-correction) 2. `core/ai_slop_commandments.md` (mechanism reference and diagnostic checklist) 3. `core/voice-profile.md` (this writer's voice fingerprint; if `Completed: No`, stop and run onboarding) 4. Any `.md` files the user has dropped in `references/`

This chain applies on direct invocation (`/ew:outline`) exactly as it does on dispatch through `/ew`. Direct invocation skips routing, not constraints.

---

## WHAT THIS SKILL IS FOR

A structured interrogation that takes a vague idea and produces a tight outline before a single word of prose is written. Writers don't just struggle with writing — they struggle with starting, because they don't know what they're actually trying to say.

This skill fixes that. The interrogation is short. The outline is specific. When the outline is done, the writer knows what every section is for and what it must accomplish.

A newsletter outline looks nothing like a sales page outline. This skill generates format-specific outlines.

---

## THE INTERROGATION PROCESS

### Phase 1: Identify the format

If the user hasn't specified a format, ask:

> "What format is this — newsletter, sales page, LinkedIn post, tweet thread, short story, screenplay, or something else?"

Wait for the answer before proceeding. Do not guess the format from the idea.

### Phase 2: Identify the core claim

Ask this question, one question only:

> "What's the one thing you want the reader to walk away knowing or feeling? Not the topic — the point."

This is the hardest question in writing. If the user can't answer it, the idea isn't ready to outline. If they give a vague answer ("I want them to feel inspired"), press once: "Inspired to do what, specifically?"

The answer to this question is the spine of the outline. Every section must serve it.

### Phase 3: Format-specific interrogation

Run the question set for the identified format. Ask one question at a time. Do not ask all questions at once.

---

#### NEWSLETTER (creative/story-led)

1. "What's the ordinary world — what's the situation before the thing you're about to describe happened?" 2. "What's the inciting incident — the specific event or moment that made the ordinary world impossible to go back to?" 3. "What did you try that didn't work, or what's the conventional wisdom that gets this wrong?" 4. "What's the key insight — the thing you now know that you didn't know before, stated in one sentence?" 5. "What does the new equilibrium look like — what's true now that wasn't true before?"

Skip any question the user has already answered in their idea description. Don't ask for information you have.

---

#### NEWSLETTER (technical/analytical)

1. "What's the problem — stated as specifically as possible, not as a category but as a concrete instance?" 2. "What's the key insight that most people get wrong or don't know?" 3. "What's the evidence or mechanism that proves the insight — data, example, analogy?" 4. "What should the reader do or think differently after reading this?"

---

#### SALES PAGE

1. "Who is this for — describe the specific person, not a demographic. What are they doing right now that this product replaces or improves?" 2. "What have they already tried that didn't work? What makes those attempts fail?" 3. "What is the mechanism — why does this work where other solutions don't? One sentence." 4. "What does life look like after — specific outcome, not transformation language." 5. "What's the main objection the buyer will have at the moment they're about to click buy?"

---

#### LINKEDIN POST

1. "What's the hook — the one observation, counterintuitive claim, or specific scene that makes someone stop scrolling?" 2. "What's the turn — where does the post change direction or reveal the point?" 3. "What do you want the reader to take from this — an action, a reframe, a question?"

---

#### TWEET / X THREAD

Single tweet: 1. "State the idea in one sentence. Don't explain it — state it." 2. "What's the sharpest version of that sentence — fewer words, stronger verb?"

Thread: 1. "What's the full claim — what are you arguing across the whole thread?" 2. "What are the 3–5 distinct points that build the argument? Each one should advance, not restate." 3. "What's the last tweet — the sharpest thing you have, the thing the reader should screenshot?"

---

#### SHORT STORY / FICTION SCENE

1. "What does the POV character want in this scene — the surface want, stated as an action they take?" 2. "What force opposes that want — a person, a circumstance, or an internal conflict?" 3. "What changes between the opening and the closing of the scene — knowledge, position, relationship, or understanding?" 4. "What's the last beat — the image or line the scene ends on?"

---

#### SCREENPLAY / SCRIPT

1. "What is the protagonist's external goal — what are they actively pursuing?" 2. "What is their internal need — what do they actually require that they can't name yet?" 3. "What is the inciting incident — the specific event that makes the ordinary world impossible to continue?" 4. "What is the protagonist's darkest moment — the point where they have lost or believe they have?" 5. "How does the protagonist resolve the story — through an active choice, not a rescue?"

---

### Phase 4: Generate the outline

Once all relevant questions are answered, produce the outline. Format:

---

**[TITLE PLACEHOLDER — working title or description of what it's about]**

**Core claim:** [The one-sentence answer from Phase 2]

**Format:** [Newsletter / Sales page / LinkedIn / etc.]

**Outline:**

[Section name — what this section accomplishes in the piece] - [Specific content: what goes here, stated as precisely as possible] - [Key line or image if identified during the interrogation]

[Section name] - [Specific content] - [Key line or image]

[Continue for each section]

**The stakes:** [One sentence on what the reader gains if they read to the end — the payoff contract]

**What to write first:** [The single hardest or most important section — start here, not at the beginning]

---

## WHAT THIS SKILL DOES NOT DO

- Does not write the piece — the outline is the output - Does not ask more questions than necessary — if the user's idea already answers a question, skip it - Does not produce generic outlines that could apply to any piece on this topic — the outline must be specific to this writer's idea and voice

---

## POST-OUTLINE CHECK

Before presenting the outline, verify: - [ ] The core claim is specific enough that only this piece could fulfill it - [ ] Every section serves the core claim — no section exists just because this format "usually has" that section - [ ] The "What to write first" recommendation is genuinely the hardest or most generative section, not just section 1 - [ ] The outline is tight enough that the writer can start immediately — no more interrogation needed

技术详情

版本
1.0.0
许可证
MIT
最近更新
2026年8月20日
发布时间
2026年8月20日

决策摘要

备选候选

61
就绪
原型验证
阶段

仓库近期活跃

审计

安装审查

安装与采用审查

78
需审查
安全性
82/100
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 outline 准备的场景化草稿,可手动发布到 X。

策展说明
A practical pick for a web workflow:

outline: Turn a vague idea into a tight, format-specific outline through structured interrogation. Use when the user is stuck on str...

28 stars

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

Install: npx skills add Deupaxx/EveryDay-Writer --skill outline
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
Deupaxx
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 Deupaxx,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/deupaxx-outline?metric=listed&label=Listed)](https://www.openagentskill.com/skills/deupaxx-outline)
[![OpenAgentSkill Trust](https://www.openagentskill.com/api/badge/deupaxx-outline?metric=trust&label=Trust)](https://www.openagentskill.com/skills/deupaxx-outline)
[![OpenAgentSkill Audit](https://www.openagentskill.com/api/badge/deupaxx-outline?metric=audit&label=Audit)](https://www.openagentskill.com/skills/deupaxx-outline/audit)
[![Agent Proven](https://www.openagentskill.com/api/badge/deupaxx-outline?metric=proven&label=Agent%20Proven)](https://www.openagentskill.com/skills/deupaxx-outline)

作者

D

Deupaxx

@deupaxx

平台适配

健康信号

GitHub Stars
28
质量评分
34/100
最近 GitHub 推送
2026年8月20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

仅限沙盒

68
  • GitHub 采用度28 个 GitHub Stars检查
  • Star/Fork 活跃度28 个 Star,5 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 2 天通过
  • 许可证清晰度MIT通过
  • 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
  • 依赖与运行时风险公开元数据中未发现主要依赖风险提示通过