why
Iterative Five Whys root cause analysis drilling from symptoms to fundamentals
55
45%
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/why/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 identifies a specific methodology (Five Whys) which gives it some distinctiveness, but it reads more like a title than a functional description. It lacks explicit trigger guidance ('Use when...'), concrete action steps, and natural keyword variations that users would employ when needing this skill.
Suggestions
Add an explicit 'Use when...' clause with trigger scenarios, e.g., 'Use when the user wants to investigate why a problem occurred, asks for root cause analysis, or needs to drill down into the underlying cause of an issue.'
List specific concrete actions the skill performs, e.g., 'Guides iterative questioning through five layers of causation, documents each why-level finding, and produces a root cause summary with recommended corrective actions.'
Include natural keyword variations users might say, such as 'why did this happen', 'troubleshooting', 'RCA', 'problem investigation', 'incident analysis', or 'find the root cause'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain ('Five Whys root cause analysis') and describes the general action ('drilling from symptoms to fundamentals'), but doesn't list multiple concrete actions like generating reports, creating action plans, or documenting findings. | 2 / 3 |
Completeness | Describes what it does (Five Whys root cause analysis) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, missing 'Use when' caps completeness at 2, and the 'what' is also only partially described, warranting a 1. | 1 / 3 |
Trigger Term Quality | Includes relevant terms like 'Five Whys', 'root cause analysis', and 'symptoms', but misses common natural variations users might say such as 'why did this happen', 'problem analysis', 'troubleshooting', 'incident investigation', or 'RCA'. | 2 / 3 |
Distinctiveness Conflict Risk | The 'Five Whys' methodology is fairly specific and distinguishable, but 'root cause analysis' could overlap with other analytical or problem-solving skills. The lack of explicit trigger conditions increases potential for mismatched selection. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A solid instructional skill with excellent examples that demonstrate the Five Whys technique across increasing complexity levels. The main weaknesses are redundancy in the Notes section, somewhat generic step descriptions, and a validation workflow that could be more explicit. The examples do most of the heavy lifting in making this skill useful.
Suggestions
Remove duplicate points in the Notes section (e.g., 'Document each why' and 'multiple root causes' each appear twice) and consolidate with the Description to reduce redundancy.
Make the validation step more concrete—e.g., 'Read the chain backwards: does [Root Cause] → [Why 4] → ... → [Problem] form a logical causal chain? If any link feels like a leap, revisit that step.'
Tighten the Steps section by merging steps 2-4 into a single iterative instruction and making step 6 (branching) a clearer decision point rather than an afterthought.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill has some redundancy—the Notes section repeats points (e.g., 'Document each why' appears twice, 'multiple root causes' mentioned twice). The Description section restates what the title and first line already convey. However, the examples are well-structured and earn their space. | 2 / 3 |
Actionability | The three examples are concrete and illustrative, showing the full chain from problem to solution. However, this is an instruction-only skill with no executable code or commands—the guidance is specific enough to follow but relies on Claude already knowing how to structure this analysis. The steps are somewhat generic ('Ask why and document the answer'). | 2 / 3 |
Workflow Clarity | Steps are listed sequentially and include a validation step (step 5: work backwards from root cause to symptom), which is good. However, the validation is vague—there's no explicit checkpoint for when to stop, how to verify the root cause is truly fundamental, or what to do if backward validation fails. The branching instruction in step 6 is mentioned but not well-integrated into the workflow. | 2 / 3 |
Progressive Disclosure | For a standalone skill with no bundle files, the content is well-organized into clear sections (Usage, Variables, Steps, Examples, Notes). The three examples progressively increase in complexity (simple linear, linear, multi-branch). No external references are needed for this scope. | 3 / 3 |
Total | 9 / 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
- 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.