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,…
Verify that existing work is ready to merge, release, or hand off using an explicit evidence contract. Use when a request asks to verify, validate, prove, check readiness, run the relevant tests, or distinguish a claimed result from an observed one. Do not use to write missing
$ npx -y skills add yonatangross/orchestkit --skill ork-verify --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/ork-verifyContext preview
The summary Claude sees to decide when to auto-load this skill.
Verify that existing work is ready to merge, release, or hand off using an explicit evidence contract. Use when a request asks to verify, validate, prove, check readiness, run the relevant tests, or distinguish a claimed result from an observed one. Do not use to write missing
name: ork-verify description: Verify that existing work is ready to merge, release, or hand off using an explicit evidence contract. Use when a request asks to verify, validate, prove, check readiness, run the relevant tests, or distinguish a claimed result from an observed one. Do not use to write missing tests or fix failures.
Write the evidence contract first: target, required checks, environment, success condition, and budget. Read the repository instructions for canonical commands and run the narrowest relevant checks before broad suites.
Report each command and its summary exactly. When a check depends on a third-party command or API surface, confirm its current flags and semantics with the context7 MCP server (`resolve-library-id`, then `query-docs`); a flag you only remember is a gap, not evidence. A passing test or check proves only the path it executed; verify that every required signal actually ran. Treat missing logs, unavailable external services, and skipped gates as unknown, not as success.
For material changes, use a separate `ork_verifier` role when installed (or a fresh Codex reviewer) with the original task and final artifacts, not the implementer's reasoning. Return a binary verdict—PASS, FAIL, or BLOCKED—with evidence, gaps, and the next action. Do not change source files or tests.
The Complete AI Development Toolkit for Claude Code. 106 skills, 36 agents, 171 hooks. Install `ork` for stable (v9.x), or `ork-alpha` for the v10 line, which ships daily.
Repo: yonatangross/orchestkit
Assess a code change, design, architecture, workflow, or competing options against explicit criteria and evidence. Use when a request asks to assess, rate,…
Compare plausible implementation, architecture, product, or operational approaches before committing to one. Use when a request asks to brainstorm, think…
Map an unfamiliar codebase, feature, architecture, data flow, or operational path with file-backed evidence. Use when a request asks how a system works, where…
Make an approved, scoped change and prove the affected behavior. Use when a request asks to implement, build, add, or land a feature that already has an agreed…
Review a pull request or branch for correctness, regressions, security, operational risk, and missing evidence. Use when a request asks to review a PR, review…
Accessibility patterns for WCAG 2.2 compliance, keyboard focus management, React Aria component patterns, cognitive inclusion, native HTML-first philosophy,…