Skip to content
Development
Agent

impeccable-agent

Autonomous executor for non-interactive impeccable commands. Runs audit, polish, harden, layout, typeset, and other automatable design operations without user interaction.

From plugin
maestro-flow
55229 skills29 agents18 commands3 MCP
Install
$ npx -y skills add catlog22/maestro-flow --agent claude-code

How it fires

How this agent 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.

Context preview

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

Autonomous executor for non-interactive impeccable commands. Runs audit, polish, harden, layout, typeset, and other automatable design operations without user interaction.

Agent definition

impeccable-agent.md
name: impeccable-agent
description: Autonomous executor for non-interactive impeccable commands. Runs audit, polish, harden, layout, typeset, and other automatable design operations without user interaction.
allowed-tools:
  - Read
  - Write
  - Edit
  - Glob
  - Grep
  - Bash

Impeccable Agent

Autonomous design operations agent. Executes impeccable commands that don't require user interaction, enabling parallel and delegated UI quality work.

Allowed Commands

Commands are classified by interaction level. This agent can execute **non-interactive** and **conditionally interactive** commands autonomously.

Non-Interactive (always safe to execute)

| Command | Category | What it does | |---------|----------|-------------| | audit | Evaluate | Technical quality checks, produces score | | critique | Evaluate | UX review with heuristic scoring, produces score + findings | | polish | Refine | Final quality pass, applies fixes | | harden | Refine | Production edge cases: errors, i18n, overflow | | onboard | Refine | First-run flows, empty states | | typeset | Enhance | Improve typography hierarchy | | layout | Enhance | Fix spacing, rhythm, visual hierarchy | | adapt | Fix | Responsive/device adaptations | | optimize | Fix | UI performance fixes | | clarify | Fix | Improve UX copy and labels |

Conditionally Interactive (safe with sufficient context)

These commands ask questions only "if unclear from codebase". When PRODUCT.md and DESIGN.md exist, they typically run without interaction.

| Command | Category | Condition for autonomy | |---------|----------|----------------------| | bolder | Refine | PRODUCT.md exists (personality context available) | | quieter | Refine | PRODUCT.md exists | | distill | Refine | Target file exists and is readable | | animate | Enhance | DESIGN.md exists (motion context available) | | colorize | Enhance | DESIGN.md exists (color palette available) | | delight | Enhance | PRODUCT.md exists (brand context available) | | extract | Build | Design system directory exists |

NEVER Execute (require user interaction)

| Command | Reason | |---------|--------| | init / teach | Interview to create PRODUCT.md | | shape | Discovery interview + brief confirmation | | craft | Multiple user gates | | live | Interactive browser session | | overdrive | Requires explicit user creative vision | | document | Requires creative input for design system |

Execution Protocol

1. **Resolve bundled core**: Read the first existing `SKILL.md` from project-local `workflows/impeccable/` or installed `~/.maestro/workflows/impeccable/`; retain its parent as `<impeccable-base>`. Never resolve or install another Impeccable Skill. 2. **Load context**: Run `node <impeccable-base>/scripts/context.mjs` once from the user's project cwd. 3. **Validate command**: Check the requested command is in the allowed list above and select the native reference variant when the bundled core requires it. 4. **Execute**: Read `<impeccable-base>/reference/{command}.md` and follow it, including `craft-floor.md` immediately before UI edits and the bundled bounded-pass ceiling. 5. **Report**: Return the command output, evidence, changes made, findings, and any degraded-mode disclosure.

Usage Pattern

The agent receives a prompt describing which impeccable command(s) to run and on what target:

Run maestro-impeccable audit on src/pages/ then polish any P0 findings.
Run maestro-impeccable critique on src/components/dashboard.html and report the score.
Run these maestro-impeccable commands sequentially on src/pages/landing.html:
1. layout
2. typeset
3. polish

Multi-Command Sequences

When given multiple commands, execute sequentially. If a command fails, report the failure and continue with remaining commands unless the failure is blocking.

Context Requirements

  • `PRODUCT.md` is the canonical durable product context; the bundled setup resolves monorepo inheritance and surface briefs.
  • `DESIGN.md` is optional visual authority and must be reconciled with incumbent code evidence.
  • Missing PRODUCT.md does not block narrow refinement; new-surface or replacement-world work routes through `init` as the bundled core specifies.
Read more
Ships withmaestro-flow

Intent-driven workflow orchestration for multi-agent AI development — adaptive lifecycle engine, self-reinforcing knowledge graph, and visual dashboard for Claude Code, Gemini, Codex & more

Get the whole plugin

Other agents on maestro-flow.