ClawHub

Writing Assistant

v0.1.0

You are a Writing Team Lead managing specialized writers via MCP tools. Please ANALYZE the writing task and then:1. if exist references, create a detailed co...

⭐ 7· 7.6k·92 current·98 all-time
by@urrrich
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 and description (manage writing tasks, create content strategies, assign to tools) match the SKILL.md instructions. The skill is instruction-only and does not declare unrelated credentials or binaries, which is proportionate for a purely procedural assistant.
✓
Instruction Scope
Instructions are limited to analyzing writing tasks, producing strategies/guidance, and assigning to an appropriate tool. They do not ask the agent to read arbitrary files, access environment variables, or exfiltrate data. The wording is somewhat general (e.g., 'assign to the appropriate tool'), but that is expected for a coordination-oriented skill.
✓
Install Mechanism
No install specification and no code files are present, so nothing will be downloaded or written to disk. This is the lowest-risk install profile.
✓
Credentials
The skill declares no environment variables, credentials, or config paths. That aligns with its role as an instruction-only agent behavior; nothing requests access to unrelated secrets or systems.
✓
Persistence & Privilege
The skill is not force-included (always: false) and uses the platform's normal model-invocation behavior. It does not request persistent modifications to other skills or system-wide configuration.
Assessment
This skill is instruction-only and appears coherent for coordinating writing tasks. Before installing, confirm what the platform means by 'MCP tools' and which platform tools the agent will be allowed to call (those tool integrations may require separate credentials or have broader access). Check how template variables like $DATE$ or $SESSION_GROUP_ID$ are substituted at runtime so they don't accidentally leak sensitive session data. Because the skill has no code and no installs, the main risk is the agent using other platform tools — only install if you trust the agent's tool permissions and the account that will run it.

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

latestvk973xk058kkq6rk35w0v09vgkh817m2d

License

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

Comments