Writer
v1.0.2Fix AI writing patterns that create repetitive and robotic content
⭐ 5· 3.7k·41 current·43 all-time
byIván@ivangdavila
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description align with SKILL.md content: the instructions are focused on diagnosing and fixing repetitive/robotic writing patterns. No unrelated capabilities, binaries, or credentials are requested.
Instruction Scope
Runtime instructions are limited to analyzing and rewriting text (paragraph openers, rhythm, vague claims, lists, parallelism, transitions, tone, word economy, nominalizations). They do not instruct reading unrelated files, accessing environment variables, or sending data to external endpoints.
Install Mechanism
No install spec and no code files — instruction-only. This minimizes filesystem or network install risk.
Credentials
Requires no environment variables, credentials, or config paths. The requested access is proportional to a text-editing helper.
Persistence & Privilege
Defaults (always: false, agent invocation enabled) are used. The skill does not ask for permanent presence or elevated privileges.
Assessment
This skill appears coherent and low-risk: it only provides heuristic rules for improving writing and requires no installs or secrets. Before installing, consider privacy of the text you will send to the agent (don't submit sensitive personal or proprietary content unless your environment/policy allows it). If you want to prevent autonomous use, review or disable agent autonomous invocation for this skill in your agent settings. Finally, remember these are stylistic heuristics — test on non-sensitive examples to confirm the results meet your quality expectations.Like a lobster shell, security has layers — review code before you run it.
latestvk9706de7mpht55ab223n26e99d80t8z5
License
MIT-0
Free to use, modify, and redistribute. No attribution required.