structured-step-by-step-reasoning

Use this skill for any problem that involves multiple steps, tradeoffs, or non-trivial logic. Think out loud before answering to improve accuracy and transparency. Apply whenever the answer is not immediately obvious.

Quality

75%

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 ./memory_data/skills/structured-step-by-step-reasoning/SKILL.md

Quality

Content

100%Weight 40%Scale 1-3

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

The content is a concise, well-structured instruction skill with a clear sequenced workflow and an explicit consistency-check checkpoint, appropriate for its simple single-purpose scope.

Dimension	Reasoning	Score
Conciseness	Lean body with no padding and no explanation of concepts Claude already knows; every line (steps, use-cases, anti-pattern) earns its place.	3 / 3
Actionability	Provides a concrete, ordered five-step procedure ('Restate the question', 'Identify sub-problems', 'Work through each', 'Check intermediate results', 'Summarize') that is directly executable as an instruction-only skill.	3 / 3
Workflow Clarity	Clear numbered sequence with an explicit consistency-check checkpoint at step 4 ('Check your intermediate results for consistency') acting as a validation step before the summary.	3 / 3
Progressive Disclosure	Under 50 lines with no external references needed; content is well-organized into clear sections (Steps, Especially useful for, Anti-pattern), satisfying the simple-skill guideline.	3 / 3
	Total	12 / 12 Passed

Description

50%Weight 40%Scale 1-3

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 answers both what and when with an explicit trigger, but it is written in second-person voice and uses an extremely broad trigger that would conflict with many skills, with only abstract actions.

Suggestions

Rewrite the description in third person ('Reasons through multi-step problems...') to satisfy the voice guideline and recover specificity.

Narrow the trigger to a concrete niche (e.g., 'multi-constraint planning, debugging, architecture tradeoffs') instead of 'any problem... non-trivial logic' to reduce conflict risk.

Add concrete capability verbs ('Restates the question, decomposes sub-problems, checks intermediate results') so specificity reaches multiple specific actions.

Dimension	Reasoning	Score
Specificity	Names a domain (multi-step problems, tradeoffs, logic) and a meta-action ('Think out loud before answering'), but the actions are abstract rather than concrete capabilities; base 2, reduced by 1 for second-person voice ('Use this skill', 'Think out loud', 'Apply whenever').	1 / 3
Completeness	States what the skill does ('Think out loud before answering to improve accuracy and transparency') and gives an explicit when trigger ('Apply whenever the answer is not immediately obvious'), answering both what and when.	3 / 3
Trigger Term Quality	Contains some relevant terms ('multiple steps', 'tradeoffs', 'non-trivial logic') but lacks common natural phrasings a user would actually say, missing common variations.	2 / 3
Distinctiveness Conflict Risk	Trigger is maximally broad ('any problem that involves multiple steps, tradeoffs, or non-trivial logic', 'whenever the answer is not immediately obvious'), overlapping with virtually all reasoning skills and conflicting with many.	1 / 3
	Total	7 / 12 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aiming-lab/MetaClaw
Path: memory_data/skills/structured-step-by-step-reasoning/SKILL.md
Commit: 922caf3

Reviewed: 9 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.