From 17c72f176d6e821b6de48cc0c4baf776617dae3d Mon Sep 17 00:00:00 2001 From: Teknium <127238744+teknium1@users.noreply.github.com> Date: Sun, 12 Apr 2026 03:03:16 -0700 Subject: [PATCH] fix: make skill loading instructions more aggressive in system prompt (#8286) The previous wording ('If one clearly matches') set too high a threshold, and 'If none match, proceed normally' was an easy escape hatch for lazy models. Now: - Lowered threshold: 'matches or is even partially relevant' - Added MUST directive and 'err on the side of loading' guidance - Replaced permissive closer with 'only proceed without if genuinely none are relevant' This should reduce cases where the agent skips loading relevant skills unless explicitly forced. --- agent/prompt_builder.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/agent/prompt_builder.py b/agent/prompt_builder.py index e33569f051..6eec0392bb 100644 --- a/agent/prompt_builder.py +++ b/agent/prompt_builder.py @@ -762,7 +762,10 @@ def build_skills_system_prompt( "than to miss critical steps, pitfalls, or established workflows. " "Skills contain specialized knowledge — API endpoints, tool-specific commands, " "and proven workflows that outperform general-purpose approaches. Load the skill " - "even if you think you could handle the task with basic tools like web_search or terminal.\n" + "even if you think you could handle the task with basic tools like web_search or terminal. " + "Skills also encode the user's preferred approach, conventions, and quality standards " + "for tasks like code review, planning, and testing — load them even for tasks you " + "already know how to do, because the skill defines how it should be done here.\n" "If a skill has issues, fix it with skill_manage(action='patch').\n" "After difficult/iterative tasks, offer to save as a skill. " "If a skill you loaded was missing steps, had wrong commands, or needed "