anmath-workflow — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited anmath-workflow (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.
This is the router. It does not replace any specialized skill; it tells you *which anmath- skill to use at your current stage** of a theorem-and-proof manuscript.
Default assumption: unless you say otherwise, the target is Annals of Mathematics, where the bar is significance + originality + a complete, correct, rigorously verified proof with clear exposition. The importance threshold is very high and acceptance is highly competitive.
| Current symptom | Next skill |
|---|---|
| Unsure the result clears the Annals importance bar / is in scope | anmath-scope-fit |
| Main theorem stated vaguely; significance/positioning unclear | anmath-results-framing |
| Proof works but the argument's architecture is not laid out | anmath-methods |
| Exposition is hard to follow; sectioning/notation/diagrams weak | anmath-figures |
| Long computations / auxiliary lemmas clutter the main line | anmath-supplementary |
| Prose is sloppy; "clearly"/"it is easy to see" hide steps | anmath-writing-style |
| Paper feels bloated or padded; every section not yet justified | anmath-length-management |
| Preparing the cover note to the editors | anmath-cover-letter |
| Ready to submit; need the final preflight | anmath-submission |
| Want to anticipate how an expert referee will probe the proof | anmath-referee-strategy |
| Received a report; need to revise and reply | anmath-revision |
anmath-scope-fit — confirm the result is important and original enough for Annalsanmath-results-framing — state the main theorem(s) precisely and position themanmath-methods — lay out the proof strategy, key lemmas, and where the difficulty liesanmath-figures — exposition and structure: sectioning, notation, statements-before-proofsanmath-supplementary — move auxiliary results / long computations to appendicesanmath-writing-style — eliminate gaps and "clearly"; tighten every claimanmath-length-management — confirm every section is necessary; cut bloatanmath-cover-letter — concise letter framing significance for the editorsanmath-submission — final preflight (format, TeX, MSC, references, arXiv)anmath-referee-strategy — stress-test the proof against expert scrutiny before sendinganmath-revision — after the report arrivesanmath-writing-styleandanmath-length-managementare late-stage polish; do not run them before the proof is actually complete and the architecture is fixed.
anmath-scope-fitanmath-results-framinganmath-methodsanmath-figuresanmath-supplementaryanmath-writing-styleanmath-length-managementanmath-submissionanmath-revisionA generic LaTeX/writing helper optimizes for readability alone. This stack is tuned to the Annals standard: the importance bar is unusually high, and a single hidden gap is fatal. Significance and complete rigor dominate every routing decision here.
anmath-scope-fit — Annals desk-screens on importance firstanmath-figures polish exposition while a proof gap remains openanmath-revision draft a reply before you have actually fixed the textanmath-supplementary as a dumping ground — essentials stay in main text~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.