Skills

Pull the people who liked or commented on any LinkedIn post and segment them by ICP fit (peer / aspirational / prospect / other).

Reverse-engineer the hook formula from a viral LinkedIn post URL.

Remove AI tells from LinkedIn posts/comments: 2026 vocabulary density, reveal bridges, staccato fragments, stacked triads, performed sincerity.

Draft a new LinkedIn post from scratch using one of 20 2026 hook formulas (anaphora, R.I.P., time-anchor, curiosity-gap, contrarian, controlled A/B…

Audit and rewrite a LinkedIn profile end-to-end for 2026: headline, About 7-step, Featured, banner, photo, Experience metrics, Skills, custom URL…

Draft a reply to one LinkedIn comment from its URL, or sweep a whole thread from just the post URL and draft a reply to every comment worth answering, in one…

Track which of your LinkedIn comments earned author replies.

Replace an exact, unique string in an existing file.

满配示例技能包：SKILL.md + scripts/、references/、assets/ 等可选目录；验证 Eino skill 与 HTTP 包内路径（仅授权安全测试与教学）。

Cluster keywords by SERP overlap and design hub-and-spoke content architecture with internal links.

Analyze ecommerce SEO across product pages, product schema, Shopping visibility, marketplace signals, and keyword gaps.

Detect, validate, or generate Schema.org JSON-LD for a supplied page or entity.

Detect privilege escalation and unauthorized access via dialogue.

A very complex description that spans multiple lines and contains weird chars: !@#$%^&*()

Detect indirect prompt injection (goal hijack).

Detect persistent-memory poisoning and RAG/knowledge-base contamination via dialogue testing.

Detect tool misuse and unexpected code execution via dialogue testing.

Detect data exfiltration via URL path encoding and chained web_fetch navigation.

Run an evaluator-gated performance optimization workflow over Codex goal mode with durable OMX artifacts and safe goal handoffs.

Build a performance chart for nubjs.com — the SVG bar figures in blog posts, docs pages and social posts (a runtime augmentation against plain node, an…

Bounded research experiment loop that tries hypotheses, measures benchmark evidence, keeps what works, and records what fails.

评估发布前或低流量内容会吸引谁、开头能否留人，以及流量和商业价值。适用于整体内容表现判断；不负责传播机制解读或整篇逐句改稿。

自动识别用户是在解决具体商业问题，还是希望全面检查商业模式，并进入对应诊断流程。用户希望拆解业务、检查商业模式或消解具体商业困境时使用。

把模糊提问改写成 Agent 可推理、可批评、可验证的问题说明书，并判断自动化可解程度。用户要改进问题表述、研究问题或评估 Agent 可解性时使用；任务交付目标已明确时不重复澄清目标。