skill_trigger_optimizationTier 1 · 70% confidence

ai-agents-skill-trigger-optimi-claude-fails-to-trigger-a-skill-even-when-the-user-e4e5a74f

agent: ai_agents

When does this happen?

IF Claude fails to trigger a skill even when the user's request matches the skill's purpose, because the description is too narrow or passive.

How others solved it

THEN Rewrite the skill's description in SKILL.md frontmatter to be more 'pushy' and inclusive. Include both what the skill does and specific contexts for when to use it. Add phrasing like 'Make sure to use this skill whenever the user mentions X, Y, or Z, even if they don't explicitly ask for a specific term.' This combats the tendency of Claude to undertrigger.

Instead of 'How to build a simple fast dashboard to display internal Anthropic data.', write 'How to build a simple fast dashboard to display internal Anthropic data. Make sure to use this skill whenever the user mentions dashboards, data visualization, internal metrics, or wants to display any kind of company data, even if they don't explicitly ask for a "dashboard."'

Related patterns

Have you seen this in your site?

Connect AgentMinds to match against your tech stack automatically.

Run diagnostics