diff --git a/skills/chatgpt-app-submission/SKILL.md b/skills/chatgpt-app-submission/SKILL.md
index 6a39887..b6bcc44 100644
--- a/skills/chatgpt-app-submission/SKILL.md
+++ b/skills/chatgpt-app-submission/SKILL.md
@@ -60,7 +60,7 @@ If tool names, descriptions, or CSP values appear missing or inconsistent with a
 
 ## Test Case Rules
 
-Generate at least five positive test cases and at least three negative test cases.
+Generate exactly five positive test cases and exactly three negative test cases.
 
 - Positive test cases must use exact MCP action names in `tools_triggered`.
 - Positive prompts should cover the main tool-backed workflows and edge conditions that review should exercise.
diff --git a/skills/ncbi-entrez-skill/SKILL.md b/skills/ncbi-entrez-skill/SKILL.md
index b9d6d87..7f99e45 100644
--- a/skills/ncbi-entrez-skill/SKILL.md
+++ b/skills/ncbi-entrez-skill/SKILL.md
@@ -14,6 +14,7 @@ description: Submit compact NCBI Entrez E-Utilities requests for PubMed, Gene, P
 
 ## Execution behavior
 - Return concise markdown summaries from the script output by default.
+- In final user-facing summaries, never display a bare PMID or DOI. Render every PMID as a Markdown link in the form `[PMID <PMID>](https://pubmed.ncbi.nlm.nih.gov/<PMID>/)` and every DOI as `[<DOI>](https://doi.org/<DOI>)`, including in tables, bullets, parentheticals, and source lists.
 - Return raw JSON or XML only if the user explicitly asks for machine-readable output.
 - Prefer targeted endpoint calls instead of broad unfiltered dumps.
 - If the user needs the full raw response, set `save_raw=true` and report the saved file path.