Name: analyse-problem
Rating: 46.400000000000006 (1 reviews)
Author: NeoLabHQ

Blog Docs Log in Get started

analyse-problem

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

Quality

48%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./antigravity/skills/analyse-problem/SKILL.md

The canonical home for this skill is analyse-problem in NeoLabHQ/context-engineering-kit

Quality

Content

42%Weight 40%Scale 1-5

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

The skill lays out a clear A3 structure with a blank template and worked examples, but it is verbose for what Claude already knows and lacks the validation feedback loop the rubric requires for structured-output workflows, capping workflow clarity at 3. Worked examples are inlined rather than separated, leaving progressive disclosure mid-range.

Suggestions

Move the two full worked A3 examples into a separate references/EXAMPLES.md and link to them from SKILL.md so the overview stays lean and respects the token budget.

Add an explicit validation/feedback step before delivery (e.g., 'Verify each countermeasure maps to an identified root cause and each implementation-plan item maps to a countermeasure; if not, revise') to satisfy the batch-output feedback-loop requirement.

Trim the redundant duplication between the ## Steps list and the A3 Template headers, and cut background that explains what A3 is, since Claude already knows the format.

Dimension	Reasoning	Score
Conciseness	The body repeats the A3 section list twice (the ## Steps prose and the near-identical A3 template headers) and then re-states all seven sections verbatim inside two full worked examples, padding the context with large ASCII boxes Claude does not need.	2 / 5
Actionability	It provides a concrete blank template and two filled examples showing the expected output shape, but the guidance is structural ('fill in the boxes') rather than executable steps or commands, leaving it as partial instruction rather than copy-paste ready code.	3 / 5
Workflow Clarity	The seven-step sequence is clearly listed, but the rubric caps this at 3 because the skill drives a batch/structured-output operation with no validation checkpoint confirming the completed A3 is internally consistent (countermeasures address root causes, plan matches countermeasures) before delivery.	3 / 5
Progressive Disclosure	There is section structure (Steps, Template, Examples, Notes) and no bundle files exist, but the two full multi-page worked examples are inlined directly in SKILL.md rather than split out, so content that could live one level deep is inline.	3 / 5
	Total	11 / 20 Passed

Description

53%Weight 40%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 states what the skill does in recognizable terms but lacks any explicit 'when to use' trigger clause, which the rubric caps at completeness 3. Specificity and trigger-term coverage are adequate but not comprehensive, with reasonable distinctiveness.

Suggestions

Add an explicit 'Use when...' clause naming trigger phrases users would say (e.g., 'Use when investigating recurring incidents, post-mortems, or complex multi-step problems needing structured root-cause analysis').

Include natural synonyms users actually say, such as 'incident analysis', 'troubleshooting', 'post-mortem', and '8D report', to broaden trigger-term coverage.

Name more concrete actions performed (e.g., 'document current condition, run 5 Whys/Fishbone root cause analysis, propose countermeasures, and sequence an implementation plan') to lift specificity.

Dimension	Reasoning	Score
Specificity	The phrase 'Comprehensive A3 one-page problem analysis with root cause and action plan' names the domain (A3 problem analysis) and two concrete actions (root cause analysis, action plan), but coverage is limited rather than comprehensive.	3 / 5
Completeness	It gives a clear 'what' (A3 one-page analysis, root cause, action plan) but there is no 'Use when...' clause or equivalent explicit 'when' guidance, capping completeness at 3 per the rubric.	3 / 5
Trigger Term Quality	It surfaces 'problem analysis', 'root cause', and 'action plan', which are reasonable natural terms, but omits common variations a user might say such as 'incident', 'post-mortem', 'troubleshooting', or '8D'.	3 / 5
Distinctiveness Conflict Risk	The A3 framing plus 'root cause' and 'action plan' carve a recognizable niche distinct from generic analysis skills, with only minor overlap risk against other problem-solving templates.	4 / 5
	Total	13 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: NeoLabHQ/context-engineering-kit
Path: antigravity/skills/analyse-problem/SKILL.md
Commit: 23e2428

Reviewed: 1 day 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.