analyse
Auto-selects best Kaizen method (Gemba Walk, Value Stream, or Muda) for target
45
33%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/kaizen/skills/analyse/SKILL.mdQuality
Discovery
40%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 identifies a clear niche in Kaizen methodology selection, which gives it strong distinctiveness. However, it lacks a 'Use when...' clause, uses technical jargon without common user-facing synonyms, and doesn't explain what concrete outputs or actions the skill produces beyond method selection. The word 'target' is ambiguous and needs clarification.
Suggestions
Add a 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks about process improvement, lean manufacturing, waste reduction, or continuous improvement methodologies.'
Clarify what the skill does after selecting a method—does it generate an analysis, provide a template, create a report? e.g., 'Analyzes a process and auto-selects the best Kaizen method, then generates an improvement plan.'
Replace or supplement technical terms with natural language users would say, such as 'process improvement', 'efficiency', 'waste elimination', or 'lean'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names the domain (Kaizen) and lists three specific methods (Gemba Walk, Value Stream, Muda), but doesn't describe what concrete actions the skill performs beyond 'auto-selects.' What happens after selection—does it generate a report, provide recommendations, run an analysis? | 2 / 3 |
Completeness | It partially addresses 'what' (auto-selects a Kaizen method) but has no 'Use when...' clause or equivalent trigger guidance. The word 'target' is vague—target of what? This lacks explicit guidance on when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | Includes domain-specific terms like 'Kaizen', 'Gemba Walk', 'Value Stream', and 'Muda' which are relevant but fairly technical. Missing natural user language like 'process improvement', 'waste reduction', 'lean manufacturing', or 'continuous improvement' that users might actually say. | 2 / 3 |
Distinctiveness Conflict Risk | The Kaizen methodology focus with specific named methods (Gemba Walk, Value Stream, Muda) creates a clear niche that is unlikely to conflict with other skills. This is a very specialized domain. | 3 / 3 |
Total | 8 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is comprehensive in scope but severely over-engineered for a SKILL.md file. It contains extensive example outputs that demonstrate desired formats well but at enormous token cost—most of the content is illustrative examples that could be in separate files. The skill lacks executable code/commands and validation checkpoints, relying instead on conceptual frameworks and output templates that Claude likely already understands.
Suggestions
Split each method (Gemba Walk, VSM, Muda) into separate referenced files (e.g., GEMBA.md, VSM.md, MUDA.md) and keep SKILL.md as a concise overview with method selection logic and links.
Reduce examples to one compact example per method in the main file, moving detailed examples to the method-specific files.
Remove explanatory content Claude already knows (e.g., definitions of the 7 wastes, what a value stream map is) and focus on the specific output format and analysis approach expected.
Add validation checkpoints to the workflow, such as 'Verify assumptions against actual code before documenting findings' and 'Confirm identified waste items with concrete evidence (file paths, metrics).'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~350+ lines. The extensive examples (authentication Gemba Walk, CI/CD Gemba Walk, Feature Development VSM, Incident Response VSM, full Muda analysis) are illustrative but massively bloat the skill. Much of this is teaching Claude concepts it already knows (what the 7 wastes are, what a value stream map is). The method selection logic and waste type definitions could be dramatically condensed. | 1 / 3 |
Actionability | The skill provides detailed examples of output formats and analysis structures, which is useful guidance. However, there is no executable code or concrete commands—everything is conceptual templates and example outputs. The 'Steps' section (understand, determine, explain, guide, present) is vague. The examples show what output should look like but don't provide executable tooling or specific commands Claude should run to gather the data. | 2 / 3 |
Workflow Clarity | Each method has a numbered process, and the overall steps are listed. However, there are no validation checkpoints or feedback loops. For a skill that involves analyzing codebases and making recommendations, there's no verification step to confirm findings are accurate, no checkpoint to validate assumptions before proceeding, and no error recovery guidance. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of text with all three methods fully detailed inline. The three methods (Gemba Walk, VSM, Muda) with their extensive examples should each be in separate referenced files. The SKILL.md should be a concise overview with method selection logic and links to detailed method files. No bundle files exist to support this structure. | 1 / 3 |
Total | 6 / 12 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.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (511 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
- NeoLabHQ/context-engineering-kit
- Commit
dedca19
- 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.