Skip to content
Development
Skill

/iterate-research

Re-checks the code behind a research file from create-research when a reviewer challenges a claim or the question widens, then revises its findings with fresh file:line citations, comments intact. Use after review comments on research; stays descriptive.

BOOST
From plugin
orchestkit
299122 skills36 agents
Install
$ npx -y skills add yonatangross/orchestkit --skill iterate-research --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/iterate-research

Context preview

The summary Claude sees to decide when to auto-load this skill.

Re-checks the code behind a research file from create-research when a reviewer challenges a claim or the question widens, then revises its findings with fresh file:line citations, comments intact. Use after review comments on research; stays descriptive.

SKILL.md

iterate-research.SKILL.md
name: iterate-research
description: "Re-checks the code behind a research file from create-research when a reviewer challenges a claim or the question widens, then revises its findings with fresh file:line citations, comments intact. Use after review comments on research; stays descriptive."
argument-hint: "<research file> [follow-up]"
user-invocable: true
allowed-tools: "Bash Read Write Grep Glob Agent"
compatibility: "Claude Code 2.1.277+. Node 22+."
metadata:
  version: "1.0.0"
  author: "OrchestKit"
  complexity: "medium"
  tags: "research, artifacts, review, iteration, workflow"

iterate-research

Revise one research file. The body is rewritten from fresh reading of the code; the comment block is kept byte for byte. Layout: the create-plan skill's `references/artifact-layout.md`.

Steps

1. **Read the research in full** and list its open comments:

   node "${CLAUDE_SKILL_DIR}/scripts/artifact.mjs" list --file <research> --open

2. **Re-check every challenged claim in the code**, at the current commit. If the code moved since the artifact's `sha`, say which findings changed. 3. **New questions** get the same method as create-research: parallel `Explore` agents by area, citations checked by you. 4. **Write the revised body** to a scratch file (no comment block in it) and write it back:

   node "${CLAUDE_SKILL_DIR}/scripts/artifact.mjs" iterate --file <research> --body /tmp/research-body.md

5. **Reply to each comment you addressed** (`reply`, or `resolve` when the reviewer asked or the comment was a factual correction you made), then answer with the path, the revision and the comments still open.

Rules

  • Same rules as create-research: describe, cite, no recommendations.
  • Never edit the file with Write or Edit, and never delete a comment.

Related

  • `/ork:create-research` writes the first revision. `/ork:review-artifact-comments` handles comments without a

rewrite.

Read more
Ships withorchestkit

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.

Get the whole plugin

Other skills on orchestkit.