Writing Assistant
v1.0.1AI writing partner for solopreneurs and content creators. Drafts, edits, and improves written content — emails, blog posts, newsletters, social captions, and...
⭐ 0· 242·1 current·1 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The skill's name/description (drafting, editing, maintaining voice) aligns with its instructions. Required artifacts (writing-state.md, content-calendar, writing-sequences, research briefs) are coherent for a writing assistant. It does not request unrelated binaries, cloud creds, or system-level access.
Instruction Scope
Runtime instructions direct the agent to read and update workspace files (AGENTS.md, writing-state.md, content-calendar, writing-sequences/, research/). This is expected for a persistent voice/profile-based writing assistant, but it does mean the agent will store and modify user content and configuration files in the project workspace — review those files and their contents to avoid storing secrets or sensitive data.
Install Mechanism
Instruction-only skill with no install spec and no code files. No downloads, package installs, or binary requirements — lowest-risk installation footprint.
Credentials
No environment variables, credentials, or external tokens are requested. The skill's file I/O is limited to project/workspace paths described in the SKILL.md, which is proportionate to the described functionality.
Persistence & Privilege
always: false (not force-included). The skill suggests adding standing instructions to AGENTS.md and updating workspace files over time — reasonable for this use case. Autonomous invocation is allowed by default (platform normal) but is not combined with broad credential access or system-level persistence.
Assessment
This skill appears coherent and low-risk: it only reads and writes files in your agent workspace (voice/profile, drafts, sequences, calendar items) and does not request credentials or install code. Before installing: 1) Decide whether you want the agent to modify AGENTS.md and other workspace files; back them up if needed. 2) Avoid pasting secrets, private credentials, or highly sensitive client data into writing-state.md, drafts, or research files the skill will store. 3) If you integrate it with inbox/content-calendar skills, verify those integrations' auth and that auto-sending is disabled (the skill states it will present drafts for review). 4) If you want tighter control, keep this skill user-invoked only and monitor what it writes to the workspace.Like a lobster shell, security has layers — review code before you run it.
latestvk97265w88qz0bxf9xm2e1b7d2s82hj1w
License
MIT-0
Free to use, modify, and redistribute. No attribution required.