From 5de0daeac5e2d36dfc2dd8dae691e28e3423221b Mon Sep 17 00:00:00 2001 From: Claude Date: Thu, 22 Jan 2026 18:56:51 +0000 Subject: [PATCH] Fix erroneous text substitution in skill-template-best-practices rule Restore "agent" terminology that was mistakenly replaced with "claude prompt runtime" in commit 46be586. The term "agent" correctly refers to the AI agent executing the skill, not a configuration setting. --- .deepwork/rules/skill-template-best-practices.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/.deepwork/rules/skill-template-best-practices.md b/.deepwork/rules/skill-template-best-practices.md index 5c31bac9..ff33ecfd 100644 --- a/.deepwork/rules/skill-template-best-practices.md +++ b/.deepwork/rules/skill-template-best-practices.md @@ -24,7 +24,7 @@ The description appears in skill search results and helps users find the right s ## Prompt Structure 1. **Specificity first** - Detailed directions upfront prevent course corrections later -2. **Plan before action** - Ask claude prompt runtime to analyze/plan before implementing +2. **Plan before action** - Ask agent to analyze/plan before implementing 3. **Reference concrete files** - Use specific paths, not general descriptions 4. **Include context** - Mention edge cases, preferred patterns, and expected outcomes @@ -32,7 +32,7 @@ The description appears in skill search results and helps users find the right s 1. **Make measurable** - Criteria should be verifiable, not subjective 2. **Focus on outcomes** - What the output should achieve, not process steps -3. **Keep actionable** - Claude prompt runtime should be able to self-evaluate against criteria +3. **Keep actionable** - Agent should be able to self-evaluate against criteria ## Platform Considerations