viral-title

Q: How do I install viral-title?

Run npx skills add https://github.com/kangarooking/kangarooking-skills --skill viral-title in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/viral-title/ (personal) or .claude/skills/viral-title/ (project).

Q: Which AI agents can use viral-title?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Q: Is viral-title safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Q: Who maintains viral-title?

It is published by kangarooking in kangarooking/kangarooking-skills. It has 70 recorded installs.

by kangarookingMarketing & SEO

Generate high-potential viral title candidates for content across WeChat public account articles, X/Twitter posts, YouTube videos, Bilibili videos, and similar content platforms. Use when the user needs headline/title ideation, batch title generation, platform-specific title adaptation, title-library reuse, title selection, title scoring, or a reusable title workflow based on universal formulas plus separated platform methods such as 公众号, X, YouTube, and B站.

Installs: 70
Last 24h: —
Trending rank: —
Security: Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/kangarooking/kangarooking-skills --skill viral-title

01
Install
Run the command in your project. The CLI asks which agents to install for.
02
Describe the task
Ask your agent for something this skill covers. It loads viral-title automatically when relevant.
03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

Viral Title

Overview

Use this skill to generate and select viral title candidates. The current version implements Phase 1 universal methodology, WeChat public-account title reuse, X/Twitter hook generation, YouTube title-thumbnail packaging, Bilibili title-cover-tag packaging, and a lightweight evolution loop.

Phase 1 must generate 30 titles: 10 universal formulas x 3 variants per formula. Then score the candidates and recommend the single best title.

Workflow

Clarify only if the content is too vague to title.
Identify the core material:
- topic or content summary
- target audience
- platform if provided
- strongest value, conflict, novelty, or emotional hook
- hard facts, numbers, names, examples, and constraints that must remain true
Read references/phase1-universal-methodology.md.
If the user names a platform, load the matching platform reference from references/platforms/.
Read references/evolution/promoted-rules.md and references/evolution/anti-patterns.md.
Generate exactly 3 titles for each of the 10 Phase 1 formulas.
If a platform reference is implemented, generate platform-tuned candidates after the universal batch when the user asks for platform-specific titles.
If the user asks to reuse proven titles or says "套用标题库", retrieve relevant examples instead of loading full libraries.
Score the candidate pool with the Phase 1 scoring rubric plus any platform-specific rules.
Select one best title and briefly explain why.
End every substantial title-generation response with the feedback prompt from Feedback Hook.
If the user replies with a selected title, edit, rating, or critique, log it with scripts/log_feedback.py.

Platform Routing

Use one platform file at a time:

User says	Platform file	Status
公众号, 微信公众号, WeChat article	`references/platforms/wechat-public-account.md`	Implemented
X, Twitter, 推特	`references/platforms/x.md`	Implemented
YouTube, 油管	`references/platforms/youtube.md`	Implemented
B站, Bilibili	`references/platforms/bilibili.md`	Implemented

For title-library reuse, load only the current platform's library:

references/title-library/wechat-public-account-hot-titles.md for summary and examples.
references/title-library/wechat-ai-curated-hot-titles.md for user-curated AI/tech viral title patterns and hotspot-dependent examples.
references/title-library/wechat-public-account-hot-titles.json only when many source titles are needed for matching or adaptation.
references/title-library/x-hot-hooks.md for X/Twitter hook skeletons and reusable mechanisms.
references/title-library/youtube-hot-titles.md for YouTube title-thumbnail packaging skeletons.
references/title-library/bilibili-hot-titles.md for B站 title-cover-tag packaging skeletons.

For token-efficient retrieval, prefer:

python3 scripts/retrieve_title_examples.py --platform <wechat|x|youtube|bilibili> --query "<topic words>" --mechanism "<optional mechanism>" --limit 10

Evolution Loop

Use the loop only when logging, feedback, review, or evaluation is useful. Do not load historical logs during ordinary title generation.

Need	Command
Log a title session	`python3 scripts/log_title_session.py --platform <platform> --topic "..." --recommended-title "..."`
Log user feedback	`python3 scripts/log_feedback.py --session-id "..." --platform <platform> --selected-title "..." --user-edit "..." --rating 5 --feedback "..."`
Retrieve title examples	`python3 scripts/retrieve_title_examples.py --platform <wechat
Review recent learning	`python3 scripts/analyze_feedback.py --recent 20`
Run seed evals	`python3 scripts/run_title_evals.py --evals references/evals/bilibili-ai-title-evals.json --case-id agent-speed-step37-bilibili --titles-json titles.json`

Follow meta/RULES.md: append logs automatically, but require user confirmation before modifying core methodology or promoting rules.

Feedback Hook

After every substantial title-generation response, append exactly one short feedback prompt:

**反馈一下**
你最终会用哪个标题？如果你改了标题，把最终版发我；也可以给 1-5 分。我会用这次反馈优化下次标题。

Do not ask for feedback after pure research, implementation, explanation, or tiny one-off edits.

When feedback arrives:

Treat a chosen title, edited title, rating, or critique as evolution feedback.
Log feedback with the current platform when known.
Prefer user_edit over selected_title when both are provided.
Store titles, platform, rating, tags, and concise feedback only. Do not store full unpublished drafts by default.
After every 5-20 feedback records, run scripts/analyze_feedback.py --recent 20 and summarize learning candidates.
Do not promote candidate observations into methodology files without user confirmation.

Phase 1 Output Format

Use this structure:

**内容判断**
核心对象：
目标人群：
主要点击理由：
真实约束：

**第一阶段：通用方法论标题池**

1. 结果承诺型
- ...
- ...
- ...

2. 问题解决型
- ...
- ...
- ...

[continue through all 10 formulas]

**最佳标题**
标题：
理由：

**备选 Top 3**
1. ...
2. ...
3. ...

**反馈一下**
你最终会用哪个标题？如果你改了标题，把最终版发我；也可以给 1-5 分。我会用这次反馈优化下次标题。

Quality Rules

Generate exactly 30 Phase 1 candidates unless the user explicitly asks for fewer.
Each formula must contribute exactly 3 titles.
Do not fabricate unsupported facts, names, numbers, or results.
Prefer concrete nouns, visible stakes, and reader-facing benefits over abstract claims.
Keep titles platform-neutral in Phase 1. Do not overfit to WeChat, X, YouTube, or Bilibili unless the user asks.
Use Chinese titles by default when the user writes in Chinese. Use English when the source content or user request is English.
Avoid empty hype such as "震惊", "必看", "全网最强", unless the user's style explicitly asks for it.
Make the final recommendation decisive. Do not say "it depends" after scoring.

Future Extension Points

Add deeper live-sampled libraries for each platform as more user-approved data sources become available.
Split Bilibili libraries by partition if a single library becomes too broad.
Load only the platform or library reference needed for the current user request.

FAQ

What does the viral-title skill do?

How do I install viral-title?

Run npx skills add https://github.com/kangarooking/kangarooking-skills --skill viral-title in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/viral-title/ (personal) or .claude/skills/viral-title/ (project).

Which AI agents can use viral-title?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is viral-title safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains viral-title?

It is published by kangarooking in kangarooking/kangarooking-skills. It has 70 recorded installs.

Source

kangarooking/kangarooking-skills $View on skills.sh

Works with

Claude CodeCodexCursorGitHub CopilotGemini CLIWindsurfClineOpenCodeRoo CodeGooseAmpKiro

Files 28 · 410.1 KB

SKILL.md7.0 KB
agents/openai.yaml238 B
meta/RULES.md1.7 KB
references/evals/bilibili-ai-title-evals.json933 B
references/evals/wechat-ai-title-evals.json2.1 KB
references/evals/x-ai-hook-evals.json881 B
references/evals/youtube-ai-title-evals.json915 B
references/evolution/anti-patterns.md621 B
references/evolution/learning-candidates.md277 B
references/evolution/promoted-rules.md550 B
references/mechanisms.json3.6 KB
references/phase1-universal-methodology.md5.9 KB
references/platforms/bilibili.md6.2 KB
references/platforms/wechat-public-account.md5.0 KB
references/platforms/x.md4.9 KB
references/platforms/youtube.md6.2 KB
references/title-library/bilibili-hot-titles.md3.7 KB
references/title-library/wechat-ai-curated-hot-titles.md11.4 KB
references/title-library/wechat-public-account-hot-titles.json290.7 KB
references/title-library/wechat-public-account-hot-titles.md24.8 KB
references/title-library/x-hot-hooks.md5.1 KB
references/title-library/youtube-hot-titles.md3.4 KB
scripts/analyze_feedback.py6.2 KB
scripts/log_feedback.py1.7 KB

+4 more files