AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Quality Checklist

skill-houarnu166-skillful-agent-system-builder-quality-checklist · by houarnu166

|

No reviews yet
0 installs
26 views
0.0% view→install

Install

$ agentstack add skill-houarnu166-skillful-agent-system-builder-quality-checklist

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-houarnu166-skillful-agent-system-builder-quality-checklist)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
7mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Quality Checklist? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Quality Review Checklist

→ See [agent-validation.md](references/agent-validation.md) for Agent details → See [skill-validation.md](references/skill-validation.md) for Skill details → See [common-issues.md](references/common-issues.md) for troubleshooting

1. Structure Review

Overall System

  • [ ] Orchestrator Agent exists
  • [ ] All required Worker Agents defined
  • [ ] All required Skills defined
  • [ ] Workflow logical completeness
  • [ ] Error handling logic included

File Structure

  • [ ] .agents/ directory structure clear
  • [ ] .agents/skills/ directory structure clear
  • [ ] temp/ usage plan specified
  • [ ] outputs/ usage plan specified

2. Agent Review

For each Agent:

Frontmatter

  • [ ] name: lowercase, hyphens, 1-64 chars
  • [ ] name: no hyphen at start/end
  • [ ] name: no consecutive hyphens
  • [ ] description: 1-1024 chars
  • [ ] description: includes role description
  • [ ] description: trigger conditions clear
  • [ ] tools: only necessary tools included
  • [ ] tools: no excessive permissions
  • [ ] model: appropriate model (haiku/sonnet/opus)
  • [ ] permissionMode: appropriate permission mode
  • [ ] skills: referenced skills actually exist

System Prompt

  • [ ] Role clearly defined
  • [ ] Call conditions specified (if needed)
  • [ ] Process explained step by step
  • [ ] Output format defined
  • [ ] Examples included (recommended)
  • [ ] Cautions specified

3. Skill Review

For each Skill:

Frontmatter

  • [ ] name: lowercase, hyphens, 1-64 chars
  • [ ] name: matches directory name
  • [ ] name: no reserved words (anthropic, claude)
  • [ ] description: 1-1024 chars
  • [ ] description: includes functionality description
  • [ ] description: usage timing clear

Body Content

  • [ ] Overview clear
  • [ ] Core concepts explained
  • [ ] Usage detailed
  • [ ] Examples specific
  • [ ] Cautions specified
  • [ ] Under 500 lines (recommended)

Bundled Resources

  • [ ] references/ configured if needed
  • [ ] scripts/ configured if needed
  • [ ] assets/ configured if needed
  • [ ] File references accurate
  • [ ] 1 level depth maintained

4. Best Practices Review

Progressive Disclosure

  • [ ] Metadata: name + description concise
  • [ ] Instructions: SKILL.md under 5k tokens
  • [ ] Resources: load-on-demand structure

Least Privilege Principle

  • [ ] Each Agent has only necessary tools
  • [ ] Read-only Agents have no Write/Edit
  • [ ] Only Orchestrator has Task tool

Clear Triggers

  • [ ] All descriptions specify triggers
  • [ ] Include "Use when...", "Trigger: ..." etc.
  • [ ] Enable Claude auto-delegation

Orchestrator Mediation

  • [ ] No direct calls between Subagents
  • [ ] All data transfer via Orchestrator
  • [ ] Centralized state management

Error Handling

  • [ ] Handle missing files
  • [ ] Handle insufficient permissions
  • [ ] Handle user interruption
  • [ ] Retry logic (if needed)

5. Documentation Review

Start Prompt

  • [ ] System purpose clear
  • [ ] File structure provided
  • [ ] Usage detailed
  • [ ] Example scenarios included
  • [ ] Customization guide included

Workflow

  • [ ] Overall flow explained
  • [ ] Step-by-step details
  • [ ] Scenario examples
  • [ ] Diagrams (recommended)

6. Quality Standards

Critical (Required)

All Critical items must pass:

  • name/description required fields
  • Naming convention compliance
  • Clear role/process
  • Least privilege principle

Warning (Recommended)

Most Warning items should pass:

  • Examples included
  • Progressive disclosure
  • Sufficient documentation

Info (Reference)

Areas for improvement:

  • Add diagrams
  • More examples
  • Customization options

Review Result Format

## 🔍 Review Results

### ✅ Passed Items ({n})
- {item 1}
- {item 2}

### ⚠️ Warning Items ({m})
1. {issue}
   - Current: {status}
   - Recommended: {improvement}

### ❌ Required Fixes ({k})
1. {issue}
   - Current: {status}
   - Fix: {solution}

### 💡 Improvement Suggestions
- {suggestion 1}
- {suggestion 2}

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.