ai4curation/ai-gene-review / .claude/skills/bioreason-predictions
bioreason-predictions
VerifiedWork with BioReason-Pro predictions and reasoning traces for protein function. Use when: comparing BioReason outputs against curated reviews, converting web exports to YAML, reviewing reasoning trace quality, or running the SFT/RL comparison. Triggers: "bioreason", "GO-GPT predictions", "reasoning trace review", "bioreason comparison", "SFT vs RL".
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 7.8 KB |
| references/converter.md | markdown | 1.2 KB |
references/converter.md
View on GitHub# BioReason-Pro Web Export Converter
Script: `~/.openclaw/workspace/scripts/bioreason_to_yaml.py`
## Usage
```bash
source .venv/bin/activate
python ~/.openclaw/workspace/scripts/bioreason_to_yaml.py --model rl [--dry-run] [--overwrite]
```
## What it does
1. Reads `*-bioreason-rl-predictions.md` from `~/worktrees/agr-bioreason/genes/`
2. Parses GO terms from the `### GO Terms` section (raw GO-GPT output)
3. Filters to leaf terms via OAK IS_A ancestor removal (~65% reduction)
4. Writes PredictionReview-conformant YAML with `source_method: GO-GPT`
5. References the raw md via `source_documents` field
## Options
| Flag | Description |
|------|-------------|
| `--model rl\|sft` | BioReason-Pro model version (default: rl) |
| `--dry-run` | Print stats without writing |
| `--overwrite` | Replace existing files |
| `--no-leaf-filter` | Skip OAK ancestor filtering |
| `--output-dir DIR` | Custom output directory |
## Output
`{GENE}-gogpt-leaf-predictions.yaml` in the gene directory.
## Note
These YAMLs contain GO-GPT predictions (the input to reasoning), not BioReason-Pro's post-reasoning GO terms. They are useful for bulk comparison but lower-value than the reasoning traces themselves.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| receiving-code-reviewobra/superpowersUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| requesting-code-reviewobra/superpowersUse when completing tasks, implementing major features, or before merging to verify work meets requirements | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| using-git-worktreesobra/superpowersUse when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| verification-before-completionobra/superpowersUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |