Agent skill · product strategy · yonatangross
ork-assess
Assess a code change, design, architecture, workflow, or competing options against explicit criteria and evidence. Use when a request asks to assess, rate, compare, identify trade-offs, evaluate readiness, or decide whether an approach is good enough. Do not use for a full pull-request review or to implement a chosen solution.
Why this skill is useful
Codifies a structured assessment process for evaluating code changes against specific criteria, reducing ambiguity in decision-making.
What it needs
About 1k tokens when loaded. Last updated 2026-08-06. 215 stars on the source repository.
What this skill does
Ork Assess State the decision, scope, and criteria before scoring. Choose criteria appropriate to the task—normally correctness, maintainability, security, operability, testability, cost, and reversibility—and omit criteria that have no bearing on the decision. Collect evidence from the code, repository guidance, tests, or authoritative documentation. For a third-party library, framework, or service, the authoritative source is the context7 MCP server: call resolve-library-id, then query-docs. Separate facts, assumptions, and unknowns. Do not invent numeric precision: use a score only when it makes the comparison clearer, and attach the evidence and confidence to it. For high-impact choices, ask an independent read-only orkreviewer or built-in reviewer to challenge the leading conclusion. End with a recommendation, conditions for approval, and concrete follow-up actions. Do not edit the target.
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills yonatangross/ork-assess