Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Bioinformatics / Phylogenetics: apply the codified rules and ground precise facts at runtime instead of recalling them.
.claude/skills/phylogenetic-tree-toolkit-ete-normalizer/SKILL.md| Model | Eval pass | Runs |
|---|---|---|
| gemini-3.6-flash | 100% | 3 |
| Model | Lift | Δ tokens | Δ turns | Cases | Verified |
|---|---|---|---|---|---|
| gemini-3.5-flashbest | +40% | — | 0% | 10 | 87d ago |
| gemini-3.6-flash | +32% | +1% | 0% | 22 | 54d ago |
| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-21 | ✗→✓ | ▲ Improved | — | — |
| case-14 | ✗→✓ | ▲ Improved | — | — |
| case-09 | ✗→✓ | ▲ Improved | — | — |
| case-01 | ✗→✓ | ▲ Improved | — | — |
| case-17 | ✗→✓ | ▲ Improved | — | — |
ETE3 Library Standard Operating Procedure
PART 1: Core Tree Mechanics (ete3.Tree)
format argument containing a single digit from 0 to 9. This digit dictates the specific interpretation of branch lengths, internal identifiers, and statistical support. .traverse() method. You must supply a strategy argument set to exactly one of the following strings: preorder, postorder, or levelorder. .get_leaves().PART 2: Evolutionary Analysis (ete3.PhyloTree)
Tree objects. You are required to instantiate a PhyloTree for these tasks..get_descendants_events(), you must verify two conditions:PART 3: Taxonomic Mapping (ete3.NCBITaxa)
NCBITaxa(). Be aware that the very first execution triggers an automatic download to construct an SQLite database on your local machine..get_lineage(taxid) and .get_taxid_translator().PART 4: Strict Prohibitions (Critical Failure Points)
format parameter during initialization. Doing so causes the parser to erroneously assign statistical support numbers as internal node labels.Do NOT answer precise facts (codes, identifiers, sections, current values) from memory — run the bundled script, and base the answer only on what it returns.
Based on the ETE Toolkit (Environment for Tree Exploration) documentation.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-06 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-08 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-11 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-15 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-16 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-05 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-21 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-12 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-14 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-10 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-18 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-13 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-09 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-01 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-17 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-07 | pass→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-02 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-20 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-19 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-03 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-04 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-22 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
DecimalAI ran this skill against gemini-3.5-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +32 percentage points is the difference between those two pass rates over the 22 comparable cases.
The per-case answers from this run were removed by the retention sweep, so the case table below shows the verdicts without the text either arm produced. The counts above were recorded at the time and are unaffected. Answers are now kept for 180 days.
| Model | Method | Date | Lift |
|---|---|---|---|
| gemini-3.5-flash | verified | 6/26/2026 | +40% |
Other measured skills in the registry, with their headline benchmark lift.