OpenAgentSkill Registry Manifest
Skill: llm-gold-bound-failure-check
Slug: kennethkhoocy-llm-gold-bound-failure-check
Category: design-creative
Description: Diagnose whether an LLM classifier's validation-gate failure is GOLD-BOUND
before spending on prompt revision or model changes. Use when: (1) a scoring
pipeline over-predicts a label (precision low, recall high) and a prompt
clarification is proposed to tighten it, (2) a pilot/validation gate fails
and the fix candidates are prompt edits, (3) inter-rater agreement on the
weak label was already low (κ < ~0.6). Core check: if gold POSITIVES share
the exact feature the revision would exclude, no prompt can pass a
gold-scored gate — recall craters while precision barely moves. Also
documents the verified surgical-pilot design (single-section diff,
tune/holdout split, pre-registered gate, perturbation check on untouched
sections).

Agent fit:
- Decision: 63/100 Prototype first
- Primary fit: Document processing
- Role: Fallback candidate

Supply profile:
- Track: Design and creative production
- Scenario: Design and creative
- Applicable agents: Claude Code, CLI, Codex, Cursor
- Maintenance: Pushed today
- Risk: Needs review

Trust:
- Trust score: 79/100 Strong shortlist
- Audit: 80/100 Needs review

Attribution:
- Status: Registry indexed
- Source: recursive skill source sync
- Creator: Claude Code
- Claim URL: https://www.openagentskill.com/skills/kennethkhoocy-llm-gold-bound-failure-check#claim-this-skill

Install:
npx skills add kennethkhoocy/applied-micro-skills --skill llm-gold-bound-failure-check

URLs:
- Web: https://www.openagentskill.com/skills/kennethkhoocy-llm-gold-bound-failure-check
- API: https://www.openagentskill.com/api/agent/skills/kennethkhoocy-llm-gold-bound-failure-check
- Install API: https://www.openagentskill.com/api/skills/kennethkhoocy-llm-gold-bound-failure-check/install
- Repository: https://github.com/kennethkhoocy/applied-micro-skills/tree/main/plugins/applied-micro/skills/llm-gold-bound-failure-check