solve-problem

This skill should be used when the user says "solve problem", "solve this problem", or invokes /solve-problem. Applies a methodical, evidence-first approach to diagnosing a problem - understand intent, observe the problem first-hand, form multiple hypotheses, gather discriminating evidence to eliminate them, propose an evidenced solution, and verify the fix actually resolves the original symptom. Do NOT use for general how-to questions, explanations, or building new features.

Quality

94%

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

Quality

Content

100%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.

A tightly written, instruction-only skill that sequences a six-move diagnostic workflow with validation checkpoints and feedback loops, supplies a concrete report template, and defers deeper worked examples to a verified one-level-deep references bundle.

Dimension	Reasoning	Score
Conciseness	Lean throughout with no padding about concepts Claude already knows; every section (the moves, anti-rush rules, show-your-working template) earns its place and assumes Claude's competence.	5 / 5
Actionability	Provides concrete, executable guidance per move — 'list at least two candidate causes', 'run the cheapest check that discriminates between causes', a falsification lens with worked contrasting example, and a copy-ready 'show your working' report template covering the common cases.	5 / 5
Workflow Clarity	A clearly numbered six-move sequence with explicit validation checkpoints (confirm before hunting causes, eliminate hypotheses with evidence) and feedback loops (recurrence returns to move 2 with more instrumentation), plus move 6 as an explicit verification step.	5 / 5
Progressive Disclosure	SKILL.md is a concise overview pointing to well-signaled, one-level-deep references in references/ (verified: README.md plus two example files exist), with the worked-examples section explicitly listing and describing each referenced file for easy navigation.	5 / 5
	Total	20 / 20 Passed

Description

88%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.

A well-crafted description that concretely enumerates the skill's actions, names natural trigger phrases plus a slash command, and bounds its scope with an explicit exclusion. The only minor gap is a slightly thin set of trigger synonyms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'understand intent, observe the problem first-hand, form multiple hypotheses, gather discriminating evidence to eliminate them, propose an evidenced solution, and verify the fix' — giving comprehensive coverage rather than a single generic action.	5 / 5
Completeness	Explicitly answers both 'what' (the methodical evidence-first diagnosis approach with its named moves) and 'when' ('when the user says... or invokes /solve-problem'), reinforced by an explicit exclusion clause ('Do NOT use for general how-how questions...').	5 / 5
Trigger Term Quality	Includes natural phrases a user would actually say ('solve problem', 'solve this problem') plus a slash invocation (/solve-problem), but offers few synonyms or variations beyond that narrow set, leaving a few natural terms missing.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (structured problem diagnosis) with distinct triggers and an explicit negative-boundary clause that minimizes overlap with how-to, explanation, or feature-building skills.	5 / 5
	Total	19 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	15 / 16 Passed

Repository: dwmkerr/claude-toolkit
Path: plugins/toolkit/skills/solve-problem/SKILL.md
Commit: 4316684

Reviewed: 8 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.