analyse-problem

Comprehensive A3 one-page problem analysis with root cause and action plan

Quality

30%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./plugins/kaizen/skills/analyse-problem/SKILL.md

Quality

Content

27%

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

The skill provides a well-structured A3 template with clear sections, but is severely bloated by two full-length examples that repeat the same structure without adding proportional value. The content explains concepts Claude already knows (what A3 is, what a fishbone diagram is) and lacks validation checkpoints in the workflow. The entire skill could be condensed to ~30% of its current size while retaining all actionable information.

Suggestions

Remove one of the two examples entirely, or replace both with a single condensed example showing just 2-3 sections filled in, with a note that the same pattern applies to all sections.

Add validation checkpoints to the workflow, e.g., 'Confirm root causes with the user before generating countermeasures' and 'Verify countermeasures map to identified root causes.'

Remove the Description section (Claude knows what A3 is) and trim the Notes section to only non-obvious guidance.

Split the full example(s) into a separate EXAMPLES.md file referenced from the main skill to reduce token consumption.

Dimension	Reasoning	Score
Conciseness	The skill is extremely verbose. The template is shown once, then two full-length examples repeat the exact same structure with placeholder-level content that doesn't add much beyond what the template already communicates. The description section explains what A3 is, which Claude already knows. The notes section restates obvious points. This could be cut by 60%+ without losing value.	1 / 3
Actionability	The template and examples provide a clear output format, and the steps are enumerated. However, the guidance is more about filling in a template than providing concrete, executable instructions. The examples show filled-in templates but don't give Claude specific techniques for performing root cause analysis or generating countermeasures—they describe what should go in each box rather than how to produce it.	2 / 3
Workflow Clarity	The 7 steps are clearly sequenced and logically ordered. However, there are no validation checkpoints—no guidance on when to verify with the user, how to confirm root causes are actually root causes vs. symptoms, or when to iterate. For a problem analysis process, feedback loops (e.g., 'verify root cause before proceeding to countermeasures') would be important.	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 bloat the file significantly. The template, examples, and notes could easily be split into separate files, with the main SKILL.md providing just the template and a brief example.	1 / 3
	Total	6 / 12 Passed

Description

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 (A3) and mentions key components but lacks the depth needed for reliable skill selection. It is missing an explicit 'Use when...' clause, which is critical for Claude to know when to choose this skill. The trigger terms are partially relevant but miss common lean/continuous improvement vocabulary that users might naturally use.

Suggestions

Add a 'Use when...' clause with explicit triggers, e.g., 'Use when the user asks for A3 reports, lean problem-solving, structured root cause analysis, or one-page problem summaries.'

Include more natural trigger terms users might say, such as 'lean', 'Toyota', 'PDCA', '5 whys', 'fishbone diagram', 'countermeasures', or 'continuous improvement'.

List more specific concrete actions, e.g., 'Creates A3 reports with problem statement, current state analysis, root cause investigation using 5 whys/fishbone, target state, countermeasures, and implementation plan.'

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 (A3 problem analysis with root cause and action plan) 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 moderately clear, warranting 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 template', 'one-pager', 'PDCA', or '5 whys'.	2 / 3
Distinctiveness Conflict Risk	'A3' is a fairly specific methodology term that provides some distinctiveness, but 'problem analysis', 'root cause', and 'action plan' are generic enough to potentially overlap with other problem-solving or analysis skills.	2 / 3
	Total	7 / 12 Passed

Validation

90%

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 — 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: 3711edf

Reviewed: 20 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.