Load before writing a message to a person: a reply, report, briefing, decision request, or work-item description or comment.
85%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Critical
Do not install without reviewing
Detected a prompt injection in the skill instructions. The skill contains hidden or deceptive instructions that fall outside its stated purpose and attempt to override the agent’s safety guidelines or intended behavior.
The skill is a legitimate writing guide, but its rule to never mention its own writing rules or say what the agent will not do could hide the skill's constraints and limitations from the user, which is a medium-risk concealment without malicious intent.
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The required workflow has the agent read the thread of each message it answers and read current open requests and the person's replies when writing a report, so chat threads that outsiders can post into are ingested without the agent selecting a specific item.
vanillagreencom/kendex
3a2f84c
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.