complexity-guard
The final gatekeeper. Audits RFCs to reject over-engineering, unnecessary dependencies, and resume-driven development.
76
Quality
62%
Does it follow best practices?
Impact
100%
1.17xAverage score across 3 eval scenarios
Optimize this skill with Tessl
npx tessl skill review --optimize ./.trae/skills/complexity-guard/SKILL.mdDiscovery
32%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description has a clear personality ('final gatekeeper') and identifies specific anti-patterns to catch, but lacks explicit trigger guidance and concrete action verbs. The colorful language ('resume-driven development') adds character but doesn't compensate for missing 'Use when...' instructions that would help Claude know when to select this skill.
Suggestions
Add a 'Use when...' clause with trigger terms like 'review RFC', 'architecture proposal', 'design document', 'tech spec review'
Replace abstract 'audits' with specific actions like 'reviews complexity, flags unnecessary abstractions, identifies scope creep, questions new dependencies'
Include file type or context triggers such as 'when reviewing .md files in /rfcs folder' or 'when user asks for design feedback'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (RFC auditing) and some actions (reject over-engineering, unnecessary dependencies, resume-driven development), but lacks concrete specific actions like 'reviews architecture decisions' or 'flags complexity metrics'. | 2 / 3 |
Completeness | Describes what it does (audits RFCs) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | Includes some relevant terms like 'RFC', 'over-engineering', 'dependencies', but misses common variations users might say like 'design review', 'architecture review', 'tech spec', or 'proposal review'. | 2 / 3 |
Distinctiveness Conflict Risk | The RFC focus and specific anti-patterns (over-engineering, resume-driven development) provide some distinction, but 'audits' and 'gatekeeper' are vague enough to potentially overlap with other review or validation skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
92%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted skill with excellent conciseness and actionability. The workflow is clear with explicit validation steps and decision criteria. The main weakness is that some content (the Techniques section) could be better organized through progressive disclosure, though this is a minor issue given the skill's overall clarity.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, using tables, bullet points, and terse examples. No unnecessary explanations of concepts Claude already knows; every section serves a clear purpose. | 3 / 3 |
Actionability | Provides concrete, executable guidance with specific file paths, exact commands (view_file, write_to_file), clear scoring thresholds (>7 = REJECT), and specific examples of what to reject with verdicts. | 3 / 3 |
Workflow Clarity | Clear 4-step sequence in Quick Start with explicit validation (sequential thinking with 3-7 steps), completion checklist with checkboxes, and clear decision criteria. The workflow includes feedback loops (suggest alternatives if REJECT). | 3 / 3 |
Progressive Disclosure | Good structure with Quick Start, Checklist, Techniques, and Toolkit sections. However, references to external file (references/anti_patterns.md) could be better signaled, and the Techniques section is somewhat lengthy inline content that could potentially be split out. | 2 / 3 |
Total | 11 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.