Agent skills for DeepSeek Harness

Review and improve documentation with parallel evaluation and iterative improvement loop.

Use when an evaluation coordinator needs normalized findings from target artifacts and research evidence.

Use when reviewing a diff, pull request, or implementation for correctness, maintainability, and human readability.

Output in the specified format when a review of specific markdown is requested.

Checks the blast radius, impacted communities, and test gaps of changed files before a commit.

Turn PUBMAXX captain feedback and merged-fix lessons into durable review checks.

Use when receiving external input that needs structured intake before action — PR review feedback, code review comments, OR issue tracker…

Playbook: review the leads Pancake found since your last check — replay activity_since from a stored cursor, judge each new lead…

Owns the shared finding policy, Lens selection index, and individual Lens definitions used by review workflows.

Use when an evaluation run must merge research, findings, documentation, and repair outputs into one verified result.

Set up systematic review monitoring across e-commerce platforms.

Use when targeting Review of Economics and Statistics (REStat) or deciding whether an applied econometrics manuscript fits this venue.

Complete the questionnaire for reviewing the content of the report in a Gesia audit file, based on the annual accounts…

Simulated peer review of the sewage-house-prices manuscript.

Audit a Cursor plugin for marketplace readiness.

PR review using parallel specialized agents for code quality, security, testing, architecture, and performance analysis.

Use to understand how Environmental Science & Technology (ES&T) evaluates a manuscript — editor desk-screening that declines a significant…

Use when calibrating expectations for the Entrepreneurship Theory and Practice (ETP) review cycle — desk-reject odds, the developmental…

Use to understand how a Global Change Biology (GCB) manuscript is judged — high desk-rejection screening for scope and significance…

Use when calibrating expectations for the Human Relations (HR) review process — the editorial scoping screen, double-anonymous…

Use to understand how the Journal of the American Academy of Religion (JAAR) evaluates a manuscript — editor pre-screening for broad…