ClawHub

Linkedin Ghostwriting

v1.1.1

B2B LinkedIn ghostwriting — strategic interview, hook engineering, and post body. Use when the user wants to write LinkedIn content, create ghostwritten post...

⭐ 0· 105·0 current·0 all-time
bySamuel Berthe@samber
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
The name/description (B2B LinkedIn ghostwriting) match the SKILL.md instructions: strategic interview questions, hook generation, and post-body rules. The skill declares no binaries, env vars, or config paths — all proportional to an instruction-only copywriting skill.
✓
Instruction Scope
Runtime instructions are limited to asking the user questions, proposing hooks, and producing post text using local reference files. The SKILL.md does not instruct the agent to read system files, access credentials, or send data to external endpoints beyond the intended writing task.
✓
Install Mechanism
No install spec or code files that would be downloaded or executed. This is an instruction-only skill (only markdown and reference files included), which minimizes disk-write/remote-code risks.
✓
Credentials
The skill requires no environment variables, credentials, or config paths. There are no unrelated secret requests or excessive environment access.
ℹ
Persistence & Privilege
Flags: always is false and disable-model-invocation is false (normal). The skill is marked user-invocable: false, which means it may be intended for agent-to-agent or internal use rather than direct user invocation—this is not a security risk by itself but is worth noting operationally so you understand how it will be triggered.
Assessment
This skill is instruction-only and internally consistent with its stated purpose. Before installing, confirm how it will be invoked in your agent (since user-invocable is false) and whether the agent will be granted downstream permissions to post on LinkedIn on your behalf — the skill itself does not request LinkedIn credentials, but an integration layer might. Test with non-sensitive example content first and verify the agent does not automatically send drafts or copy to external accounts without explicit authorization. If you plan to wire it to a LinkedIn API or automation, only provide the minimal token scopes needed for posting and review authorization/workflow so posts are human-reviewed before publishing.

Like a lobster shell, security has layers — review code before you run it.

latestvk975xemqv84z53xbjk33mr2gbs83qmr2

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Runtime requirements

✍️ Clawdis

Comments