CtrlK
BlogDocsLog inGet started
Tessl Logo

reducing-entropy

Manual-only skill for minimizing total codebase size. Only activate when explicitly requested by user. Measures success by final code amount, not effort. Bias toward deletion.

85

1.16x
Quality

80%

Does it follow best practices?

Impact

92%

1.16x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/reducing-entropy/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Discovery

75%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This description has strong completeness with explicit activation criteria and clear distinctiveness through its manual-only constraint. However, it lacks specific concrete actions beyond 'deletion' and could benefit from more natural trigger terms that users would actually say when requesting this type of work.

Suggestions

Add specific concrete actions like 'removes dead code, consolidates duplicate functions, eliminates unused dependencies, simplifies over-engineered abstractions'

Include natural trigger terms users might say: 'reduce code', 'clean up codebase', 'remove dead code', 'shrink the code', 'code minimization'

DimensionReasoningScore

Specificity

Names the domain (codebase size minimization) and mentions some actions ('deletion', 'measures success by final code amount'), but lacks concrete specific actions like 'remove unused imports', 'consolidate duplicate functions', or 'eliminate dead code paths'.

2 / 3

Completeness

Clearly answers both what ('minimizing total codebase size', 'bias toward deletion') and when ('Only activate when explicitly requested by user', 'Manual-only skill'), providing explicit trigger guidance about requiring explicit user request.

3 / 3

Trigger Term Quality

Contains some relevant terms like 'codebase size', 'deletion', and 'minimize', but misses common natural variations users might say such as 'reduce code', 'clean up', 'remove dead code', 'code cleanup', or 'shrink codebase'.

2 / 3

Distinctiveness Conflict Risk

The 'manual-only' and 'explicitly requested' constraints create a clear niche that won't accidentally trigger. The specific focus on minimizing code size through deletion distinguishes it from general refactoring or code quality skills.

3 / 3

Total

10

/

12

Passed

Implementation

85%

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-structured conceptual skill that efficiently communicates a decision-making framework for code minimization. Its strengths are excellent conciseness and clear workflow with explicit gates. The main weakness is limited actionability - while the mental model is clear, there are no concrete tools, scripts, or measurable techniques provided for actually counting or comparing code.

Suggestions

Add a concrete example showing before/after line counts for a real refactoring scenario

Include a simple command or script for measuring codebase size (e.g., `find . -name '*.py' | xargs wc -l`)

DimensionReasoningScore

Conciseness

Every section earns its place. No explanation of concepts Claude knows, no padding. The content is lean and direct, using bullet points and short phrases effectively.

3 / 3

Actionability

Provides clear mental frameworks and questions to ask, but lacks concrete code examples or specific commands. The guidance is conceptual rather than executable - no line-counting scripts, no deletion commands, no before/after code samples.

2 / 3

Workflow Clarity

Clear sequence: load mindset first, then apply three questions in order. The 'Before You Begin' section has explicit steps with a gate ('Do not proceed until'). For a conceptual/decision-making skill, the workflow is appropriately structured.

3 / 3

Progressive Disclosure

Well-organized with clear sections. References to external files (references/, adding-reference-mindsets.md) are one level deep and clearly signaled. Content is appropriately split between overview and detailed reference materials.

3 / 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.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
softaworks/agent-toolkit
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.