Deep interview process to transform vague ideas into detailed specs. Works for technical and non-technical users.
38%
Does it follow best practices?
Impact
96%
1.23xAverage score across 3 eval scenarios
Low
Low-risk findings worth noting
Fix and improve this skill with Tessl
tessl review fix ./.claude/skills/discovery-interview/SKILL.mdThe 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.
This skill's Phase 3 "Research Loops" explicitly requires spawning an oracle agent or using WebSearch/WebFetch to gather and summarize information from public sites (e.g., examples referencing AllRecipes, Tasty, WebSearch/WebFetch), so the agent will fetch and act on untrusted third-party web content as part of its workflow.
parcadei/Continuous-Claude-v3
d07ff4b
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.