analyse-problem
Comprehensive A3 one-page problem analysis with root cause and action plan
43
30%
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-problem/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 the A3 methodology domain but lacks sufficient detail on concrete actions and completely omits trigger guidance for when Claude should select this skill. It reads more like a title than a functional description, and would benefit from listing specific deliverables and explicit 'Use when' conditions.
Suggestions
Add an explicit 'Use when...' clause with trigger terms like 'A3 report', 'root cause analysis', 'lean problem solving', 'Toyota A3', 'problem-solving template'.
List specific concrete actions such as 'Define problem statement, conduct root cause analysis with 5-whys or fishbone diagrams, propose countermeasures, create implementation timeline'.
Include natural keyword variations users might say, such as 'lean', 'continuous improvement', 'PDCA', 'problem-solving one-pager', or 'A3 template'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (A3 problem analysis) and mentions some components (root cause, action plan), but doesn't list specific concrete actions like 'create fishbone diagrams', 'define countermeasures', or 'track metrics'. | 2 / 3 |
Completeness | Describes what it does at a high level 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 weak, so this scores a 1. | 1 / 3 |
Trigger Term Quality | Includes 'A3', 'root cause', 'action plan', and 'problem analysis' which are relevant terms, but misses common variations users might say like 'lean', 'Toyota', 'problem solving', 'one-pager', 'A3 report', or '8-step problem solving'. | 2 / 3 |
Distinctiveness Conflict Risk | 'A3' and 'one-page' provide some distinctiveness from generic problem-solving skills, but 'root cause and action plan' could overlap with other problem-solving or analysis skills without clearer scoping. | 2 / 3 |
Total | 7 / 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 provides a well-structured A3 template with thorough examples, but suffers significantly from verbosity—two full-length examples that repeat the same structure consume most of the token budget without adding proportional value. The content explains a framework Claude already knows rather than providing unique, actionable guidance on how to apply it effectively. The lack of validation checkpoints and the monolithic structure further weaken the skill.
Suggestions
Reduce to one concise example (or move examples to a separate EXAMPLES.md) and trim the template to just the section headers with brief one-line guidance per section.
Remove the Description section which duplicates the Steps section, and trim the Notes section to only non-obvious guidance.
Add explicit validation checkpoints, e.g., 'After Root Cause Analysis, verify each root cause by asking: if this cause were removed, would the problem disappear?'
Extract the full template and examples into separate referenced files (TEMPLATE.md, EXAMPLES.md) to keep the main skill lean and navigable.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose. The description section repeats what the steps section says. The template is shown empty, then two full-length examples repeat the same structure with extensive detail. Claude already knows the A3 format and doesn't need 200+ lines of filled-in examples. The notes section also restates obvious points. | 1 / 3 |
Actionability | The template and examples provide concrete output format, and the steps give a clear sequence. However, this is an instruction-only skill with no executable code or tool commands—it's essentially a template with placeholder guidance like '[Context, impact, urgency, who's affected]' rather than specific techniques for how Claude should gather or analyze information. | 2 / 3 |
Workflow Clarity | The 7 steps are clearly sequenced and the template provides structure. However, there are no validation checkpoints—no guidance on when to verify root causes are actually root causes, no feedback loop for checking countermeasures address identified causes, and no explicit quality gates between steps. | 2 / 3 |
Progressive Disclosure | Everything is in a single monolithic file with no references to external resources. Two massive examples that are nearly identical in structure are inlined, making the file extremely long. The examples could easily be in a separate EXAMPLES.md, and the template could be in a TEMPLATE.md, with the main skill being a concise overview. | 1 / 3 |
Total | 6 / 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.