Meeting Prep
v1.1.0Prepares briefing docs so you walk into every meeting ready
⭐ 0· 698·0 current·0 all-time
by@1kalin
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name and description match the runtime instructions: research attendees and companies, produce scannable briefs and talking points. No unrelated binaries, env vars, or installs are requested.
Instruction Scope
The SKILL.md directs the agent to 'use web search' and to 'pull from any previous notes or CRM data' when available. That scope is relevant to meeting prep, but the instructions do not specify which user data sources or how to obtain/access them (credentials, connectors, or privacy handling), which is an ambiguity the user should be aware of.
Install Mechanism
Instruction-only skill with no install spec and no code files — nothing is written to disk or downloaded during install.
Credentials
The skill declares no required environment variables, credentials, or config paths. It does request reading user notes/CRM when present, which is proportionate to meeting prep but not explicitly tied to any declared credential—this is likely intended to rely on the agent/platform's existing connectors.
Persistence & Privilege
The skill is not always-enabled and does not request elevated or persistent system privileges. It contains no instructions to modify other skills or system-wide settings.
Assessment
This skill appears coherent for meeting preparation, but review a few points before installing: 1) Confirm which data sources your agent can access (notes, CRM, email) and whether you want the skill to read them — the SKILL.md asks the agent to pull previous notes/CRM data but doesn't specify how access is obtained. 2) Verify any time-sensitive 'recent news' the skill reports before acting; the skill instructs to research the web and could surface incomplete or unverified items. 3) If you have sensitive meetings, test the skill with a non-sensitive example first to check for hallucinations or inadvertent disclosure. 4) If you prefer restrictive access, ensure your agent's connectors/permissions are limited or disable autonomous invocation for this skill in your agent settings.Like a lobster shell, security has layers — review code before you run it.
latestvk97akk10jq6rncnpfga4n1qtx1812x6j
License
MIT-0
Free to use, modify, and redistribute. No attribution required.