Query decomposition and multi-source search orchestration. Breaks natural language questions into targeted searches per source, translates queries into source-specific syntax, ranks results by relevance, and handles ambiguity and fallback strategies.
77%
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 ./enterprise-search/skills/search-strategy/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 runtime workflow for `search-strategy` decomposes a user question into searches across connected sources like `~~chat`, `~~knowledge base (Wiki)`, and `~~project tracker`, which necessarily entails the agent ingesting free-text content from those sources at least after selecting relevant results.
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.