Index of every page on this site: llms.txt
All skills
ntcoding avatar

/architect-refine-critique

@21c6101
by Nick Tunentcoding/claude-skillz366 stars
47
Run it yourself

Three-phase design review. Chain architect → refiner → critique subagents. Triggers on: 'design review', 'architecture review', '/arc', system design proposals, significant refactoring decisions, new service or module design.

Use this Skill: https://skilld.dev/gh/ntcoding/claude-skillz/architect-refine-critique

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈64 tokens for metadata: the name and description. ≈135 when used: this file. ≈5.6k more on demand in 6 files.

Description uses 3.2% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈253 characters, or 3.2%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Architect-Refine-Critique

Chain three subagents sequentially from the main conversation.

Usage

/arc [name] [target]

Execution

Use the architect subagent to create the initial design for [target] with name=[name], then use the refiner subagent to improve the design with name=[name], then use the critique subagent to challenge the design with name=[name].

After all three complete, tell the user: "Run /arc-review [name] to discuss findings."

Do not analyze. Do not summarize. Do not add value. Just chain and hand off.

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

1 warning1mo4 checks · Risk SAFE
  • Gen Agent Trust Hub1mo

    The skill implements an automated architecture review workflow involving Architect, Refiner, and Critique stages. It utilizes standard project analysis tools such as npx and reads codebase files. The primary security observation is a low-risk indirect prompt injection surface where the agent processes external PRDs and source code that could contain adversarial instructions.

  • Socket1mo

    No alerts

  • Snyk1mo

    Risk: LOW · No issues

  • Runlayer9mo

    7/7 files flagged

Signed by skilld at 21c6101. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub last month.

Dormantupdated 10 months ago
version
1.3.6

README badge

README badge for ntcoding/claude-skillz/architect-refine-critique