Back to Signal Feed
CodeTracked since May 19, 2026

Fix plugin-mode activation routing for test-anti-patterns and test-smell-detection

Variant A changes only the plugin-mode prompt/description logic so the two overlapping test skills can be selected correctly, removing conflicting exclusion text and replacing it with explicit invocation rules and tighter "do not use" boundaries.

plugin modetest-anti-patternstest-smell-detectionskill activation prompts

What Happened

  • Variant A changes only the plugin-mode prompt/description logic so the two overlapping test skills can be selected correctly, removing conflicting exclusion text and replacing it with explicit invocation rules and tighter "do not use" boundaries.
  • Variant A changes only the plugin-mode prompt/description logic so the two overlapping test skills can be selected correctly, removing conflicting exclusion text and replacing it with explicit invocation rules and tighter "do not use" boundaries.
  • 1 evidence item attached for review.

What is Different

Before

Scattered source updates, isolated context, and manual follow-up across multiple feeds.

Now

Implemented an activation-only rewrite for the two test-analysis skills in plugin mode: both skills are retained, cross-skill exclusion instructions were removed, USE-FOR triggers were expanded with explicit eval-grade phrasing, DO NOT USE FOR was narrowed to actual disallow cases, and prompt wording from PR #653 was integrated to reduce wrong-or-empty skill selection.

Why Track This

Why It Matters

Developers and operators using these skills in plugin mode should see the intended skill invoked more reliably, which directly reduces no-op or wrong-check responses during automated test analysis and helps keep review suggestions aligned with the user intent. Practically, this targets the earlier failure pattern where anti-pattern and smell requests often triggered neither skill or the sibling one; the change is technically driven by removing mutually exclusive guidance and adding explicit `INVOKE THIS SKILL` trigger phrasing. Continue monitoring `/evaluate` results and real user prompts for residual sibling misrouting or any drop in recall on edge prompts.

Impact

Developers and operators using these skills in plugin mode should see the intended skill invoked more reliably, which directly reduces no-op or wrong-check responses during automated test analysis and helps keep review suggestions aligned with the user intent. Practically, this targets the earlier failure pattern where anti-pattern and smell requests often triggered neither skill or the sibling one; the change is technically driven by removing mutually exclusive guidance and adding explicit `INVOKE THIS SKILL` trigger phrasing. Continue monitoring `/evaluate` results and real user prompts for residual sibling misrouting or any drop in recall on edge prompts.

What To Watch Next

  • Watch whether plugin mode becomes a repeated pattern.
  • Track follow-up changes around Evals and Benchmarks.
  • Compare future signals against this evidence trail.
  • Re-check risk flags: monitor_zero_skill_invocation_rate_for_plugin_mode, watch_for_residual_cross_skill_misrouting.
Open Topic TimelineOpen Technical EventOpen Original Sourcemonitor_zero_skill_invocation_rate_for_plugin_mode / watch_for_residual_cross_skill_misrouting / validate_stability_of_invocation_rules_in_real_user_prompts

Supporting Evidence

GITHUB PULL REQUESTHigh Trust

dotnet/skills PR #670: test-anti-patterns / test-smell-detection: activation-only rewrite (Variant A)

Drop every cross-skill mutual-exclusion clause from both skill descriptions, lead with `INVOKE THIS SKILL when…`, and align eval-prompt triggers to the new wording so plugin-mode discrimination improves.