fine-tune-dependency-check
Find fine-tuned model references and check base model deprecation status. Trigger: /finetune-deps
SKILL.mdskills/ai-ml/fine-tune-dependency-check/SKILL.md
GitHub/finetune-deps
Fine-tuned models depend on their base model. When the base is deprecated, the fine-tune silently breaks.
What this is for
- Fine-tune references with deprecated base models
- Missing version pinning on HuggingFace models
- Fine-tune IDs that may have expired
- Read-only skill. No code changes.
PROTECTION RULE - never ~/.claude/
Read-only skill. Guard required if write mode added later.
What You Must Do When Invoked
During analysis, assign a confidence level to each finding: proven (confirmed by evidence), likely (strong signal, needs review), or suspected (weak signal).
If /finetune-deps -help or /finetune-deps -h (without further arguments)
is invoked: output the ## Usage section unchanged and stop.
Otherwise follow these steps in order, skipping none.
Step 1 - Help check
If invoked with -help or -h, output the ## Usage section unchanged and stop.
Step 2 - Clarify target
Clarify -ProjectDir. Get confirmation.
Step 3 - Scan
& "<SKILL_DIR>/scripts/finetune-scan.ps1" -ProjectDir "<path>"
Step 4 - Classification
For each fine-tune reference:
- Current: base model still supported
- Expiring-soon: within 3 months of EOL
- Deprecated: past EOL, will fail
- Unknown: model not in reference data, verify manually
Step 5 - Write report
File finetune-dependency-report.md in current working directory:
- Summary - references by classification.
- Reference table - deprecated first. Per reference: file, line, base model, fine-tune name, deprecation date, alternative, risk.
- Open questions.
Step 6 - Summarize
State report path, highlight deprecated and expiring fine-tunes.
Usage
/finetune-deps # interactive
/finetune-deps <dir> # scan project
/finetune-deps -help