Resolve Design Review

Triage STOP verdict findings from review-design, classifying each as ADDRESSABLE/STRUCTURAL/DISCUSS using parallel subagents. If any are ADDRESSABLE or DISCUSS, generate revision_guidance and emit resolution=revised. If all are STRUCTURAL, emit resolution=failed for terminal stop.

5 stars 1 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add TalonT-Org/AutoSkillit --skill resolve-design-review
Manual install
git clone --depth 1 https://github.com/TalonT-Org/AutoSkillit.git /tmp/AutoSkillit
mkdir -p ~/.claude/skills
cp -r /tmp/AutoSkillit/src/autoskillit/skills_extended/resolve-design-review ~/.claude/skills/resolve-design-review

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Resolve Design Review Skill

Triage STOP verdict findings from `review-design`, perform feasibility
analysis to classify each finding as ADDRESSABLE/STRUCTURAL/DISCUSS using
parallel feasibility-validation subagents, generate revision guidance for
addressable findings, and emit routing token to feed back into the revision
loop or halt.

## Arguments

`/autoskillit:resolve-design-review <evaluation_dashboard_path> <experiment_plan_path> [prior_revision_guidance_path]`

## When to Use

Called by the research recipe via run_skill when review_design emits verdict=STOP.
MCP-only — not user-invocable directly.

## Critical Constraints

**NEVER:**
- Create files outside `{{AUTOSKILLIT_TEMP}}/resolve-design-review/`
- Modify the evaluation dashboard, experiment plan, or any source file
- Apply fixes — this skill triages fixability only
- Run subagents in the background (`run_in_background: true` is prohibited)

**ALWAYS:**
- Exit 0 in all cases — resolution=revised and resolution=failed are both normal outcomes
- Emit revision_guidance ONLY when resolution=revised
- Use model: "sonnet" for all subagents

## Context Limit Behavior

When context is exhausted mid-execution, temp files may be partially written and
output tokens may not yet be emitted. The recipe routes to `on_context_limit`,
abandoning the partial triage.

**Before emitting structured output tokens:**
1. If analysis was not completed, emit `resolution = failed` as a safe fallback
Read the full skill on GitHub

Details

Skill name
resolve-design-review
Path
src/autoskillit/skills_extended/resolve-design-review/SKILL.md
License
MIT
Repo updated
8 November 2026

FAQ

What does the Resolve Design Review skill do?

Triage STOP verdict findings from review-design, classifying each as ADDRESSABLE/STRUCTURAL/DISCUSS using parallel subagents. If any are ADDRESSABLE or DISCUSS, generate revision_guidance and emit resolution=revised. If all are STRUCTURAL, emit resolution=failed for terminal stop.

How do I install the Resolve Design Review skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add TalonT-Org/AutoSkillit --skill resolve-design-review. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Resolve Design Review popular?

It lives in TalonT-Org/AutoSkillit, which has 5 GitHub stars and 1 forks.

Related skills

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.