fix(enrichment): align SKILL.md threshold references with Level 3+ target#372
Merged
fix(enrichment): align SKILL.md threshold references with Level 3+ target#372
Conversation
…rget Four stale threshold references in skills/reference-enrichment/SKILL.md that were missed when #299 moved the audit to --min-level 3: - Line 30 top-level description: "Level 0-1 to Level 2-3" → "Level 0-2 to Level 3+" - Line 102 Phase 4 VALIDATE goal: "Level 2+ depth" → "Level 3+ depth" - Line 108 verification instruction: "level field is 2 or 3 ... If still Level 1" → "level field is 3 ... If still below Level 3" - Line 165 failure case heading: "Phase 4 Tier 1 still Level 1" → "Phase 4 Tier 1 still below Level 3" Companion to #371 which fixed the runtime prompt text. SKILL.md is documentation about the skill and not read by the cron, so the urgency was lower, but leaving these inconsistent would confuse anyone reading the skill and wondering why the audit threshold does not match the stated validation criteria.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Companion PR to #371. That PR fixed the runtime prompt text (
enrichment-prompt.md) that the hourly cron reads. This PR fixes the four stale threshold references still in the skill's documentation file.SKILL.md is the user-facing skill documentation and is not read by the cron at runtime, so the bug had no runtime impact. But leaving the SKILL.md description disagreeing with the actual audit threshold would confuse anyone trying to understand the skill from its docs.
Changes
Four text substitutions in
skills/reference-enrichment/SKILL.md:Lines 56, 66, 74, 91, 113, 151 already referenced Level 3 correctly and were left untouched.
Context
Observed during a manual enrichment cron run on 2026-04-11 at 09:31:21. The subagent skipped
react-native-engineerbecause its 7 reference files were already at Level 2, which the old prompt text treated as a valid stopping point. PR #371 fixed the runtime prompt. Then a broader grep found the same stale threshold in the skill documentation, which this PR addresses.The underlying cause for both PRs is the same: commit c5f89eb (#299) upgraded
scripts/audit-reference-depth.pyto--min-level 3but did not propagate the threshold change to the two files that describe what the audit does.Test plan
grep "Level [0-9]" skills/reference-enrichment/SKILL.mdthat all ten Level references are now internally consistent with Level 3 as the target.SKILL.mdstring content, so no test breakage expected.