CtrlK
BlogDocsLog inGet started
Tessl Logo

kaizen

Guide for continuous improvement, error proofing, and standardization. Use this skill when the user wants to improve code quality, refactor, or discuss process improvements.

44

Quality

48%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/kaizen/SKILL.md

The canonical home for this skill is kaizen in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

46%Scale 1-5

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

This skill provides a comprehensive philosophy guide for continuous improvement with good concrete TypeScript examples, but it is far too verbose for its purpose—most of the concepts (YAGNI, guard clauses, Result types, iterative refinement) are well-known programming principles that Claude doesn't need taught at this length. The content would benefit greatly from being condensed to ~100 lines of key principles and patterns, with detailed examples moved to separate reference files.

Suggestions

Reduce content by 60-70%: remove explanations of concepts Claude already knows (YAGNI, guard clauses, early returns, Result types) and keep only project-specific conventions or non-obvious patterns.

Split detailed code examples into separate reference files (e.g., ERROR_PROOFING_EXAMPLES.md, JIT_EXAMPLES.md) and link from the main skill with clear one-line descriptions.

Add explicit validation checkpoints to the refactoring workflow, e.g., 'Run tests after each change' with specific commands rather than just mentioning 'keep tests passing'.

Consolidate the Good/Bad examples to one per pillar maximum in the main file, moving additional examples to bundle reference files.

DimensionReasoningScore

Conciseness

The skill is significantly verbose at ~400+ lines. It extensively explains concepts Claude already knows well (YAGNI, early returns, guard clauses, Result types, iterative refinement). Many code examples illustrate basic programming principles that don't need teaching. The Good/Bad pattern is repeated excessively when a single example per concept would suffice.

2 / 5

Actionability

The skill provides concrete, executable TypeScript examples throughout, with clear Good/Bad comparisons showing exactly what to do and what to avoid. However, it's more of a philosophy/principles guide than a step-by-step operational skill—the 'In Practice' sections give actionable checklists but the overall content is more about mindset than specific executable procedures.

4 / 5

Workflow Clarity

The iterative refinement workflow (make it work → make it clear → make it efficient) is clearly sequenced, and the 'In Practice' sections provide ordered steps. However, there are no explicit validation checkpoints or feedback loops for the refactoring/improvement processes described. The 'When refactoring' section mentions 'keep tests passing throughout' but doesn't specify how to verify.

3 / 5

Progressive Disclosure

All content is inlined in a single monolithic file with no references to supporting files. The commands section references /why, /cause-and-effect, etc. but doesn't link to where those are defined. Given the length (~400+ lines), significant portions (e.g., detailed code examples for each pillar) should be split into separate reference files. No bundle files are provided to support this large body of content.

2 / 5

Total

11

/

20

Passed

Description

49%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 provides a basic structure with both 'what' and 'when' clauses, which is positive. However, it suffers from vagueness in its capabilities — 'guide for continuous improvement' doesn't convey concrete actions — and its broad scope creates significant overlap risk with other coding and process-related skills. The trigger terms are too generic to reliably distinguish this skill from others.

Suggestions

Add specific concrete actions the skill performs, e.g., 'Applies error-proofing patterns like input validation, defensive coding, and exception handling' instead of the vague 'guide for continuous improvement'.

Narrow the scope and add distinctive trigger terms to reduce conflict risk, e.g., 'Use when the user mentions error proofing, poka-yoke, standardizing workflows, or applying continuous improvement methodologies like kaizen to code.'

Include more natural user phrases and synonyms such as 'best practices', 'defensive coding', 'code standards', 'technical debt reduction' to improve trigger term coverage.

DimensionReasoningScore

Specificity

Names the domain ('continuous improvement, error proofing, standardization') but the actions are vague and generic — 'guide' is not a concrete action, and 'improve code quality, refactor, or discuss process improvements' are broad categories rather than specific capabilities.

2 / 5

Completeness

Has both a 'what' ('guide for continuous improvement, error proofing, and standardization') and a 'when' ('Use this skill when the user wants to improve code quality, refactor, or discuss process improvements'). However, the 'what' is vague and the 'when' could be more specific with concrete trigger scenarios.

4 / 5

Trigger Term Quality

Includes some relevant keywords like 'refactor', 'code quality', and 'process improvements', but misses many natural user phrases such as 'best practices', 'clean code', 'technical debt', 'code review', 'linting', or 'standardize'. The terms present are somewhat generic.

3 / 5

Distinctiveness Conflict Risk

Very broad scope — 'improve code quality' and 'refactor' could overlap with nearly any coding skill, code review skill, or linting skill. 'Process improvements' is extremely generic and could conflict with project management or DevOps skills. There is high overlap risk.

2 / 5

Total

11

/

20

Passed

Validation

81%

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

Validation9 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (733 lines); consider splitting into references/ and linking

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

9

/

11

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.