conbio-writing-style — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited conbio-writing-style (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
A Conservation Biology paper must be readable by conservation scientists and practitioners beyond the author's own system, formatted to the journal Style Guide, and disciplined to the per-type word cap. This skill is about clarity, accessibility, and format — not about generating claims. (Verify the current per-type caps; they drift between Style Guide versions — see resources/official-source-map.md.)
problem, the question, the approach, and why it matters for conserving biodiversity. Don't make a generalist dig for the "so what."
paper, and a modeler should follow a field study. Spell out acronyms; use accepted species names.
without saying what they show and why it matters for conservation.
Abstract → Introduction → Methods → Results → Discussion; do not combine Results and Discussion, and do not add a separate Conclusion (conclusions belong in the Discussion).
Zotero/BibTeX). Literature Cited is included in the word count.
interrogative titles per the Style Guide.
neutralize obvious self-references; strip identifying file metadata (see conbio-submission).
Comments, or Diversity).
balance tables, and extended robustness to Supporting Information.
conbio-literature-positioning).
Title. The Style Guide bars hanging, full-sentence, and interrogative titles, so recast the question or clause as a declarative noun phrase that names taxon, mechanism, and conservation stake.
a fragmented region."* — states the finding, the guild, and the transferable scale in one line.
Abstract compression. When the ≤ 300-word abstract runs long, cut in this order: delete method-brand phrases first ("using a Bayesian implementation"), collapse background to one clause, and protect the finding-with-direction and the conservation payoff last. A sentence such as "We conducted a study in which we surveyed sites and subsequently fitted models to the resulting data" becomes "We surveyed 60 farms and modeled occupancy" — same content, roughly a third of the units.
Discussion, not Conclusion. Because there is no separate Conclusion section, the implications land in the Discussion. Do not close with an "In conclusion" paragraph; end on the scope-bounded conservation recommendation instead, and route the so-what through conbio-conservation-relevance-and-implications.
The count runs Abstract → Literature Cited, so trim where units are cheapest to lose:
legend and in-table text do not count, but a wall of in-text numbers does.
Cited, which is counted, for no argumentative gain.
【Conservation contribution stated by end of intro?】[Y/N]
【Reads past the system?】jargon defined / acronyms spelled? [Y/N]
【Abstract】word count (≤300)
【Word count】within the article-type cap (Abstract→Literature Cited)?
【Style Guide + anonymized + title style】[Y/N]
【Next】conbio-conservation-relevance-and-implications../../resources/external_tools.md — reference managers and typesetting../../resources/official-source-map.md — word/abstract caps, Style Guide, IMRAD, title rules~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.