Doc Co

v1.0.0

Deep co-authoring workflow—context gathering, iterative drafting and structure, reader testing, and quality gates. Use when writing documentation, proposals,...

0· 55·0 current·0 all-time
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
Name/description (deep co‑authoring) match the SKILL.md workflow: context gathering, iterative drafting, and reader testing. The actions the skill asks for (reading shared docs, asking clarifying questions, drafting sections) are coherent with that purpose.
Instruction Scope
Instructions explicitly tell the agent to fetch shared documents and read team channels when the user provides links or enables connectors. That behavior is expected for this use case, but it means the agent will request access to potentially sensitive project content when the user allows integrations or pastes content into chat. The skill does prompt for user confirmation before searching connected tools.
Install Mechanism
No install spec and no code files — instruction‑only skill. Nothing is written to disk or downloaded by the skill itself.
Credentials
No environment variables, credentials, or config paths are requested. The SKILL.md references platform integrations (Slack, Google Drive, etc.) but does not attempt to collect tokens itself; relying on the hosting platform's connectors is consistent with the skill's purpose.
Persistence & Privilege
always is false and the skill does not request permanent system presence or modify other skills. Autonomous invocation is allowed by default (platform behavior) but not combined with other concerning privileges.
Assessment
This is an instruction-only co‑authoring workflow and is internally consistent with its purpose. Before using it, be aware that it asks you to provide or allow access to shared documents and team channels so the agent can fetch context—only enable connectors or paste content you are comfortable sharing. The skill does not request secrets or install code, but you should still: (1) review and approve any connector access in your platform settings, (2) avoid pasting passwords or other secrets into chat, and (3) review generated drafts before sharing externally. If you need a stricter privacy posture, decline automatic connector access and paste only the minimal excerpts required.

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

latestvk9707gqq2cr59ng0rnaxq8d7gh83pq86

License

MIT-0
Free to use, modify, and redistribute. No attribution required.

Comments