Agent skills for DeepSeek Harness

Use when interpreting the Journal of Economic Theory (JET) review pipeline — editor desk-screening, single-anonymized refereeing, at least…

Use to understand how the Journal of Marriage and Family (JMF) evaluates a manuscript — double-blind anonymous peer review, editor and…

Use to understand how the Journal of Communication (JoC) evaluates a manuscript — double-anonymous review, editorial screening for fit…

Use to understand and navigate the Journal of Econometrics (JoE) editorial process — single-anonymized review, editor screening before a…

Use when anticipating how a Journal of Policy Analysis and Management (JPAM) manuscript will be evaluated — desk screening, double-blind…

Use to understand how the Journal of Public Administration Research and Theory (JPART) evaluates a manuscript — double-blind review, desk…

Use when anticipating how a Language (LSA) manuscript will be judged — the double-anonymous review, the general-audience and…

Show pull requests that need review, ranked by ease of review.

Produces a completion summary of a code-review session — what was resolved, skipped, and postponed — for a downstream consumer such as a…

Audit todo kotgent tasks against the current repository and recommend whether to keep, rewrite, merge, drop, or escalate them.

Use when bringing forward priors from PAST sessions / cross-agent history before doing new work — NOT about re-reading the current context…

Review one task diff or aggregate Change through owner-selected independent lenses, synthesize file-backed findings, and perform…

Track document approvals and milestone/phase gate decisions.

Review existing UI against the project's design context, accessibility expectations, responsive behavior, interaction quality, and…

Validate plans, execution, or PRs against wish criteria — returns SHIP / FIX-FIRST / BLOCKED with severity-tagged gaps.

# Review Writing — A Methodology for Writing Academic Reviews Section by Section

Use when reviewing a pull request or a change in this repository — orients the reviewer to this repository's standards (AGENTS.md…

Generic, repo-agnostic PR review methodology — use this whenever reviewing a pull request in any repo, whether that's an autonomous…

Reviews a Claude Skill or plugin before you trust it, whether it's a submission to an internal marketplace, a skill a colleague sent you…

Reviews animation and motion code against a high craft bar derived from Emil Kowalski's design engineering philosophy.

Use when asked to review a code change (diff, branch, or PR) for merge readiness and collaborate asynchronously with another agent (often…