Conciseness

The tool tables and code examples are dense and token-efficient, but two whole sections restate textbook ecology Claude already knows — 'Competitive exclusion: Two species cannot stably coexist on single limiting resource (Gause's principle)', 'Mimicry: Batesian (harmless mimics dangerous) vs Mullerian', 'r-selected... vs K-selected', keystone species, island biogeography — and the 'LOOK UP DON'T GUESS' section repeats the search-the-literature instruction already given in Reasoning Strategy 1. That is more than minor over-explanation, placing it at the mostly-efficient-with-unnecessary-explanation anchor rather than 4.

Actionability

Guidance is fully executable: copy-paste-ready snippets with real, verified outputs ('tu.run_tool("GBIF_match_name", {"name": "Panthera leo"})["data"]["usageKey"] # 5219404'), concrete search templates ('[species name] invasive impact [region]'), and specific gotchas ('check the returned `rank` before assuming species-level', 'don't mix an ID from one database into another's lookup call'). The examples cover the common taxonomy, marine, and citizen-science cases.

Workflow Clarity

Each question type has a numbered sequence, and the GBIF section gives a clear ordered procedure ('Resolve a name to a GBIF usageKey once, then navigate the Backbone tree') with inline checkpoints like checking the returned rank before assuming species-level. It stays at 4 rather than 5 because checkpoints are informal and scattered rather than explicit validate-and-recover steps. No destructive or batch operations, so the workflow-clarity cap does not apply.

Progressive Disclosure

No bundle files exist and the single SKILL.md runs ~161 lines, with roughly half being tool-catalog material — the ~50-line 'Additional Taxonomy & Biodiversity Sources' table plus its worked examples is inline reference content that belongs in a separate file. Headers and tables keep it navigable, but content that should be separate is inline, matching the some-structure anchor rather than the good-placement anchor at 4 (and the under-50-line exception does not apply at this length).

Specificity

The description lists multiple concrete capabilities — 'species identification (GBIF, NCBI Taxonomy)', 'invasive species impact', 'conservation status (IUCN)', 'ecology-related literature search' — each tied to a specific authority database. Coverage spans taxonomy, invasion biology, conservation, and literature search with no noticeable gap, matching the comprehensive-coverage anchor rather than the minor-gaps anchor at 4.

Completeness

Both halves are explicit: the 'what' enumerates concrete capabilities with named data sources, and the 'when' is an explicit 'Use for biodiversity questions, species comparison, invasion biology, conservation prioritization, and ecology-related literature search' clause with concrete trigger phrases. This matches the anchor that clearly answers both what and when.

Trigger Term Quality

'biodiversity questions', 'species comparison', 'invasion biology', and 'conservation prioritization' are natural phrases a user would say, giving good keyword coverage. Not 5 because common variations like 'endangered species', 'wildlife', 'extinction risk', or 'marine species' are absent.

Distinctiveness Conflict Risk

The ecology/biodiversity/conservation niche is well-defined and anchored by distinctive database names (GBIF, NCBI Taxonomy, IUCN), so the skill is unlikely to trigger for an unrelated one. The only overlap risk is that 'ecology-related literature search' brushes against a general literature-search skill, but the scoping to ecology keeps it minimal.