simplify
Manually trigger the cdd-code-simplifier agent to review and simplify code
62
52%
Does it follow best practices?
Impact
67%
1.52xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/simplify/SKILL.mdQuality
Discovery
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 is minimally functional but lacks depth. It identifies the core action (review and simplify code) but fails to provide explicit trigger guidance, natural user-facing keywords, or specific concrete capabilities. The phrase 'manually trigger' focuses on invocation mechanics rather than helping Claude understand when to select this skill.
Suggestions
Add an explicit 'Use when...' clause with trigger terms like 'simplify code', 'reduce complexity', 'refactor', 'clean up code', 'make code simpler'.
List specific concrete actions the agent performs, such as 'removes dead code, reduces nesting depth, extracts helper functions, simplifies conditional logic'.
Remove or rephrase 'manually trigger' since it describes invocation mechanics rather than the skill's purpose; focus on what the skill accomplishes and when it should be selected.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (code simplification) and a couple of actions (review and simplify code), but doesn't list specific concrete actions like refactoring patterns, removing dead code, reducing complexity metrics, etc. | 2 / 3 |
Completeness | Describes what it does (review and simplify code) but has no explicit 'Use when...' clause or equivalent trigger guidance. The word 'manually trigger' describes invocation mechanics rather than when to use it. Per rubric guidelines, missing 'Use when' caps completeness at 2, and the 'what' is also weak, so this scores a 1. | 1 / 3 |
Trigger Term Quality | Includes some relevant terms like 'simplify code' and 'code-simplifier', but misses common natural variations users might say such as 'refactor', 'clean up code', 'reduce complexity', 'make code simpler', or 'code review'. | 2 / 3 |
Distinctiveness Conflict Risk | The specific agent name 'cdd-code-simplifier' adds some distinctiveness, but 'review and simplify code' could overlap with general code review or refactoring skills. The mention of 'manually trigger' helps distinguish it as an agent invocation but is not strongly distinctive. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a concise, well-structured skill that clearly communicates the intent and basic workflow for triggering the code simplifier agent. Its main weaknesses are the lack of a concrete Task tool invocation example and missing error handling/validation steps for when the agent produces unexpected results. The examples section effectively shows user-facing usage patterns.
Suggestions
Add a concrete example of the actual Task tool invocation with the expected parameters/structure, so Claude knows exactly how to call it rather than inferring from the description.
Add error handling guidance: what to do if the agent returns no changes, fails, or makes changes that break tests—include a validation step like running tests after simplification.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lean and efficient. Every section serves a purpose—task definition, scope determination logic, post-completion steps, and usage examples. No unnecessary explanations of what code simplification is or how agents work. | 3 / 3 |
Actionability | Provides clear guidance on using the Task tool with `subagent_type: "cdd-code-simplifier"` and gives concrete git commands for scope determination, but lacks an executable example of the actual Task tool invocation (e.g., the exact JSON/call structure). The examples section shows user commands, not Claude's execution steps. | 2 / 3 |
Workflow Clarity | The workflow has a clear sequence (determine scope → run agent → review → ask about commit → summarize), but lacks validation checkpoints. There's no guidance on what to do if the agent fails, produces no changes, or makes problematic simplifications—no feedback loop for error recovery. | 2 / 3 |
Progressive Disclosure | For a simple, single-purpose skill under 50 lines with no need for external references, the content is well-organized with clear sections (task, scope determination, post-completion steps, examples). No bundle files are needed. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- aaddrick/claude-desktop-debian
- Commit
76a5a21
- 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.