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 plausible implementation, architecture, product, or operational approaches before committing to one. Use when a request asks to brainstorm, think through options, choose an approach, evaluate trade-offs, or resolve significant uncertainty before implementation. Do not
$ npx -y skills add yonatangross/orchestkit --skill ork-brainstorm --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/ork-brainstormContext preview
The summary Claude sees to decide when to auto-load this skill.
Compare plausible implementation, architecture, product, or operational approaches before committing to one. Use when a request asks to brainstorm, think through options, choose an approach, evaluate trade-offs, or resolve significant uncertainty before implementation. Do not
name: ork-brainstorm description: Compare plausible implementation, architecture, product, or operational approaches before committing to one. Use when a request asks to brainstorm, think through options, choose an approach, evaluate trade-offs, or resolve significant uncertainty before implementation. Do not use for an already specified mechanical change.
Frame the outcome, constraints, non-goals, and decision deadline. Inspect the relevant repository and existing decisions before proposing options.
Generate two to four materially different approaches. For each, state the implementation shape, benefits, costs, risks, dependencies, reversibility, and the evidence that would disprove it. Do not pad the list with cosmetic variations.
When an option depends on what a library, framework, or service can actually do today, confirm it with the context7 MCP server (`resolve-library-id`, then `query-docs`) before scoring it. An option built on a capability you only remember is an assumption, and it belongs in the unresolved list.
Use one context for a normal decision. Delegate only when there are at least three independent unknowns; give each subagent one bounded question and synthesize its evidence. Prefer the installed `ork_explorer` role when available, otherwise use Codex's built-in `explorer` role.
End with a recommendation, the decision rationale, unresolved assumptions, and the smallest next action. Do not edit files until the user asks to implement the chosen approach.
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,…
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…
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,…
Accessibility patterns for WCAG 2.2 compliance, keyboard focus management, React Aria component patterns, cognitive inclusion, native HTML-first philosophy,…