jet-workflow — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited jet-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.
The Journal of Economic Theory is Elsevier's flagship general economic-theory venue (ISSN 0022-0531). The deciding criterion is a rigorous, original theoretical contribution — mechanism design, information economics, decision theory, game theory, matching, market design, political economy, finance and macro/monetary theory. Empirical, experimental, quantitative, or computational work is welcome only when firmly grounded in theory. House style is theorem-proof, typeset in LaTeX (Elsevier elsarticle). Review is single anonymized (single-blind) with a floor of at least two referees after an editor desk screen.
jet-topic-selection (is this a JET-scope theoretical contribution?)
▼
jet-literature-positioning (stake the result against the theory frontier)
▼
jet-identification-strategy (assumptions, results, proof architecture, generality)
▼
jet-contribution-framing (state the theorem and why it matters)
▼
jet-data-analysis (numerical examples / computation — only if any)
▼
jet-tables-figures (schematic exhibits, notation discipline)
▼
jet-writing-style (elsarticle theorem-proof prose; polish)
▼
jet-replication-and-data-policy (Option C data statement; reproducible computation)
▼
jet-review-process (what single-anonymized refereeing expects)
▼
jet-submission (Editorial Manager preflight, .tex source, AI disclosure)
▼
jet-rebuttal (response letter on an R&R)jet-topic-selection.jet-literature-positioning.jet-identification-strategy.jet-contribution-framing.jet-data-analysis.jet-tables-figures.jet-submission and resources/official-source-map.md.The next skill should always reduce one JET desk/referee risk: off-scope empirics, overclaimed theorem, hidden assumption, unreadable proof, notation drift, or unsupported submission fact.
| Manuscript state | Dominant JET risk | Route |
|---|---|---|
| Idea + model, no theorem sentence yet | off-scope at the desk | jet-topic-selection |
| Theorem proved, novelty delta fuzzy | a "follows from known results" report | jet-literature-positioning |
| Theorem + proof drafted, assumptions scattered through proofs | hidden-assumption catch by a referee | jet-identification-strategy |
| Full draft, introduction shaped like a data story | theorem buried at the desk screen | jet-contribution-framing, then jet-writing-style |
| A numerical section dominating the paper | computation overshadowing the theory | jet-data-analysis |
| Exhibits renaming model objects | notation drift across figure and proof | jet-tables-figures |
| Camera-ready PDF, source files not checked | format bounce (PDF-as-source) | jet-submission |
| R&R letter alleging a proof gap | broken-lemma risk | jet-rebuttal plus jet-identification-strategy |
The paper proves a recursive characterization of optimal long-term contracts under two-sided limited commitment, plus one computed example. The pass order actually used:
sides.
Example added for one-sided commitment.
One skill was consciously skipped until submission: no external research data existed, but the computed example script was still made reproducible and the eventual Option C statement said so plainly. Record deliberate skips so a later pass does not mistake them for gaps.
delta sentence must shrink with the theorem.
framing, exhibits, and prose.
rebuttal sentence is drafted — the reduction must be checked first.
【Where you are】<stage>
【Use next】jet-<skill>
【Why】<one line tied to JET's theory-first bar>
【Volatile facts checked】editor roster / APC / abstract cap / data statement? [Y/N]~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.