Writing Claw
v1.0.0Use this skill for any creative writing task involving narrative, character, story structure, or franchise development. Triggers: building or tracking charac...
⭐ 0· 55·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
medium confidencePurpose & Capability
Name and description describe a narrative / writing assistant; the SKILL.md defines registries (characters, settings, plots, motifs, themes) and tracking/state semantics that are coherent with a writing-focused tool. There are no declared binaries, env vars, or config paths that would be unrelated to this purpose.
Instruction Scope
The instructions direct the agent to treat a story as a stateful system (registries, auto-populated logs, gap detection). That scope is appropriate for a narrative OS, but implies state tracking. The skill does not declare any external storage, network endpoints, or credential access in the provided excerpt. Because the SKILL.md was truncated in the review payload, confirm the remainder doesn't instruct reading arbitrary files, environment variables, or sending data to external endpoints.
Install Mechanism
No install spec and no code files — instruction-only. This minimizes on-disk/third-party install risk.
Credentials
The skill does not request any environment variables, credentials, or config paths. That is proportional for a writing assistant that operates on in-memory state and agent-local data.
Persistence & Privilege
always is false and there are no declared config changes. However the skill's design explicitly describes tracking and auto-populating registries, which implies persistent state if the agent platform provides memory. If you do not want long-lived story data retained, verify how the platform stores skill state or disable agent memory for this skill.
Assessment
This skill appears internally consistent with a creative-writing purpose and requests no credentials or installs. Before installing: (1) review the full SKILL.md (the provided content was truncated) to ensure it doesn't later instruct the agent to read files, access environment variables, or call external endpoints; (2) decide whether you want the agent to retain story state between sessions — if not, disable persistent memory or clear story data periodically; (3) watch future versions for added install steps or required API keys (those would be unexpected for a writing-only skill). If you are comfortable with the agent keeping narrative state and the SKILL.md contains no hidden I/O, installing is reasonable.Like a lobster shell, security has layers — review code before you run it.
latestvk97f6weqfzwrb35f9bbp4rhvxs83sx81
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
