An agentic skills framework & software development methodology that works.
Red Flags: never tell a reviewer what not to flag or pre-rate severity
Jesse Vincent09742294183a
diff --git a/skills/subagent-driven-development/SKILL.md b/skills/subagent-driven-development/SKILL.mdindex 7741a53a9..60a8ad96c 100644--- a/skills/subagent-driven-development/SKILL.md+++ b/skills/subagent-driven-development/SKILL.md@@ -281,6 +281,9 @@ Done!- Accept "close enough" on spec compliance (spec reviewer found issues = not done)- Skip review loops (reviewer found issues = implementer fixes = review again)- Let implementer self-review replace actual review (both are needed)+- Tell a reviewer what not to flag, or pre-rate a finding's severity in the+ dispatch prompt ("treat it as Minor at most") — the plan's example code is+ a starting point, not evidence that its weaknesses were chosen- **Start code quality review before spec compliance is ✅** (wrong order)- Move to next task while either review has open issues