ork-assess
Assess a code change, design, architecture, workflow, or competing options against explicit criteria and evidence. Use when a…
Works through the review comments written into a task artifact (plan or research under .ork/tasks/TASK/): lists the open ones, asks how to proceed, then replies, resolves or hands off to iterate-plan or iterate-research, and approves the artifact once nothing is open. Use when a
$ npx -y skills add yonatangross/orchestkit --skill review-artifact-comments --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/review-artifact-commentsContext preview
The summary Claude sees to decide when to auto-load this skill.
Works through the review comments written into a task artifact (plan or research under .ork/tasks/TASK/): lists the open ones, asks how to proceed, then replies, resolves or hands off to iterate-plan or iterate-research, and approves the artifact once nothing is open. Use when a
name: review-artifact-comments description: "Works through the review comments written into a task artifact (plan or research under .ork/tasks/TASK/): lists the open ones, asks how to proceed, then replies, resolves or hands off to iterate-plan or iterate-research, and approves the artifact once nothing is open. Use when a reviewer has commented on an artifact file or asks to address, resolve or approve its comments." argument-hint: "[artifact file]" user-invocable: true allowed-tools: "Bash Read Grep Glob AskUserQuestion" compatibility: "Claude Code 2.1.277+. Node 22+." metadata: version: "1.0.0" author: "OrchestKit" complexity: "low" tags: "review, artifacts, comments, approval, workflow"
Comments live inside the artifact, in the block at its end (format: the create-plan skill's `references/artifact-layout.md`). A reviewer adds one with the script or types it into the block by hand; both are read the same way. Nothing here deletes a comment.
1. **Pick the artifact.** Use the file given. Otherwise list the task directory and ask which one:
node "${CLAUDE_SKILL_DIR}/scripts/artifact.mjs" status --task-dir .ork/tasks/<task>2. **Read the artifact in full, then its open comments:**
node "${CLAUDE_SKILL_DIR}/scripts/artifact.mjs" list --file <artifact> --open3. **Ask how to proceed** unless the user already said (AskUserQuestion), for example:
4. **Work one comment at a time.** Check the claim in the code before answering. Reply with what you found or changed:
node "${CLAUDE_SKILL_DIR}/scripts/artifact.mjs" reply --file <artifact> --id c1 --author Claude --text "..."
node "${CLAUDE_SKILL_DIR}/scripts/artifact.mjs" resolve --file <artifact> --id c1 --author Claude --text "..."Resolve only when told to, or when the reply records a fix already made. 5. **Approve only for the reviewer, never for the author.** The approver is the reviewing seat, and `--ref` names the LAND message or comment id the approval rests on. The script refuses while a comment is open or when `--by` is the artifact's `author` (exit 1), and without `--by` or `--ref` (exit 2):
node "${CLAUDE_SKILL_DIR}/scripts/artifact.mjs" approve --file <artifact> --by <reviewer seat> --ref <LAND or comment id>An approved artifact with no open comment is the "phase done" signal other tools read.
node "${CLAUDE_SKILL_DIR}/scripts/artifact.mjs" comment --file <artifact> \
--author "<name>" --quote "<the line it is about>" --text "<the comment>"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.
Assess a code change, design, architecture, workflow, or competing options against explicit criteria and evidence. Use when a…
Compare plausible implementation, architecture, product, or operational approaches before committing to one. Use when a request…
Map an unfamiliar codebase, feature, architecture, data flow, or operational path with file-backed evidence. Use when a request…
Render an answer inline as compact ASCII or box-drawing art with semantic status icons. Use for status, inventories, budgets,…
Make an approved, scoped change and prove the affected behavior. Use when a request asks to implement, build, add, or land a…
Review a pull request or branch for correctness, regressions, security, operational risk, and missing evidence. Use when a…