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.

1.16x

Quality

65%

Does it follow best practices?

Impact

92%

1.16x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./dist/plugins/reducing-entropy/skills/reducing-entropy/SKILL.md

Quality

Content

75%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is concise, well-structured, and provides concrete decision rules with a validation checkpoint for destructive deletions. Its main weakness is a broken reference to adding-reference-mindsets.md and some mantra repetition.

Suggestions

Create references/adding-reference-mindsets.md (or remove the dangling reference) so all cited bundle paths resolve.

Trim the restated mantras ('Measure the end state, not the effort' appears twice; the closing line repeats the opening) to push conciseness to 5.

Consider a short explicit 'verify before finishing' step that re-runs the before/after line count to close the deletion feedback loop.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence without explaining known concepts (entropy, YAGNI), but the core mantra ('measure the end state', 'bias toward deletion') is restated a few times, keeping it just below anchor 5.	4 / 5
Actionability	It gives concrete, executable decision rules ('Count lines before and after. If after > before, reject it.', 'Could this be 2 functions instead of 14?') and specific red-flag callouts, which is actionable guidance; no literal code, but that is justified for a mindset skill.	4 / 5
Workflow Clarity	A clear sequence exists (Before You Begin with numbered steps, an explicit 'Do not proceed until...' gate, then the Three Questions) plus a line-count validation checkpoint for the destructive/deletion changes, fitting anchor 4.	4 / 5
Progressive Disclosure	The body is a concise overview that clearly signals one-level-deep references in references/ with discovery instructions, but it cites adding-reference-mindsets.md which is not present in the bundle, a minor organization gap that prevents a 5.	4 / 5
	Total	16 / 20 Passed

Description

55%Weight 40%Scale 1-5

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 clearly states what the skill does and gives explicit (if restrictive) activation guidance, but it lacks natural user trigger phrases and lists only a couple of concrete behaviors. It is distinct but would benefit from trigger-term coverage.

Suggestions

Add a 'Use when...' clause with natural trigger phrases such as 'delete code', 'reduce codebase size', 'shrink the codebase', or 'cleanup before refactor'.

List a few more concrete actions (e.g., 'count lines before and after', 'identify deletion opportunities') to lift specificity.

Keep the manual-only restriction but pair it with the concrete situations that warrant it to reduce ambiguity.

Dimension	Reasoning	Score
Specificity	Names the domain ('minimizing total codebase size') and a couple concrete behaviors ('Measures success by final code amount', 'Bias toward deletion'), but does not enumerate several specific actions, so it sits at anchor 3 rather than 4.	3 / 5
Completeness	It states a clear 'what' (minimize total codebase size) and an explicit 'when' ('Only activate when explicitly requested by user'), but the when is restrictive rather than concrete trigger phrases, so it does not reach anchor 5.	4 / 5
Trigger Term Quality	It offers one generic keyword ('minimizing total codebase size') but omits the natural phrases users actually say ('delete code', 'reduce code', 'shrink the codebase', 'cleanup'), matching anchor 2.	2 / 5
Distinctiveness Conflict Risk	The deletion/minimize-codebase niche plus the manual-only restriction make it mostly distinct with minor overlap risk against general refactor/cleanup skills, fitting anchor 4 rather than a fully crisp 5.	4 / 5
	Total	13 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: softaworks/agent-toolkit
Path: dist/plugins/reducing-entropy/skills/reducing-entropy/SKILL.md
Commit: 3027f20

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

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.