Use when the user asks to widen, open or rethink a field of ideas that is empty, narrowed too early, or thin; a field merely looking narrow does not start it. The user can then see one map from their words and what they name — frames, branches, idea origins, the unexplored — and take it, nothing chosen.
63%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
Fix and improve this skill with Tessl
tessl review fix ./heuresis/skills/ideate/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.
The required workflow's `reference` step has a tool read the records the person names, such as an issue whose comments the skill cites as "from issue ROO-12's comments", and those returned texts enter the context as external turns, so outsider-authored issue comments reach the LLM once the person names the record.
jongwony/epistemic-protocols
471e9c5
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.