ClawHub

Medium

v1.0.0

Rebuild dense ideas into authoritative long-form writing for Medium. Optimize clarity, intellectual structure, reader trust, and deep-read momentum for essay...

⭐ 0· 325·0 current·0 all-time
by@agimodel
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, and SKILL.md all describe long-form/article improvement tasks and the runtime instructions match that purpose. The skill requests no binaries, environment variables, installs, or file paths that would be unrelated to editing or critique.
✓
Instruction Scope
The SKILL.md confines the agent to parsing user-provided article drafts/outlines, diagnosing structure/readability, and proposing rewrites and plans. It explicitly includes guardrails about not asserting unsupported facts. The instructions do not ask the agent to read system files, environment variables, or transmit data to external endpoints.
✓
Install Mechanism
No install spec or code files are present; this is instruction-only, so nothing will be downloaded or written to disk by the skill itself.
✓
Credentials
The skill declares no required environment variables, credentials, or config paths. The SKILL.md also does not reference any external secrets or credentials.
✓
Persistence & Privilege
always is false and the skill does not request elevated or persistent system privileges. Autonomous invocation is allowed (platform default) but the skill's scope does not imply risky autonomous actions or modifications to other skills or system settings.
Assessment
This skill is instruction-only and appears coherent for editing and restructuring long-form Medium articles. Before using it: (1) avoid pasting sensitive or private data into the draft you provide, since the skill operates on user-supplied content; (2) treat factual claims and citations the skill produces as drafts that need independent fact-checking and legal review where required; (3) test the skill on sample drafts to confirm its tone and edits match your expectations; and (4) remember that autonomous invocation is platform-default—if you do not want the agent to call this skill without explicit permission, adjust agent settings or invocation policies accordingly.

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

latestvk970wn76zvpthx6fa1kzahzvtd82ng8c

License

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

Comments