sequential-thinking

Use when complex problems require systematic step-by-step reasoning with ability to revise thoughts, branch into alternative approaches, or dynamically adjust scope. Ideal for multi-stage analysis, design planning, problem decomposition, or tasks with initially unclear scope.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

87%

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 lean, actionable overview with a concrete tool reference, full parameter documentation, and well-signaled one-level-deep references to real bundle files; its only real gap is that the multi-step workflow presents checkpoints implicitly rather than as explicit validation steps.

Suggestions

Make the workflow's checkpoints explicit: add a step such as 'before incrementing thoughtNumber, confirm the prior thought is sound or mark it for revision' so the validation/feedback loop is visible in the sequence rather than only in Tips.

Collapse the redundant intro line and Core Capabilities bullets (which restate the description) to save tokens, or differentiate them so each earns its place.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence: it lists parameters with types, a compact workflow, and a concrete example without explaining what reasoning or MCP tools are; the intro line and Core Capabilities mildly restate the description but do not pad with concept exposition.	3 / 3
Actionability	Provides the exact MCP tool name, every parameter with its type, a sequenced workflow, and a fully-formed copy-paste-ready TypeScript example with concrete values, matching the 'fully executable, copy-paste ready' anchor.	3 / 3
Workflow Clarity	The Workflow Pattern gives a clear numbered sequence and a termination condition, but validation/checkpoint steps are only implicit (e.g., 'adjust dynamically', 'use revision when assumptions prove incorrect') rather than explicit checkpoints in the flow.	2 / 3
Progressive Disclosure	The body is a clear overview that delegates advanced revision/branching patterns and real-world examples to two real, one-level-deep reference files (references/advanced.md, references/examples.md) with well-signaled links, matching the top anchor.	3 / 3
	Total	11 / 12 Passed

Description

77%

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 is well-structured with an explicit trigger clause and a clear enumeration of capabilities, but its trigger terms lean on tool jargon rather than natural user phrasings, and the problem-solving triggers are generic enough to risk overlap with other skills.

Suggestions

Add natural user-facing trigger phrases (e.g., "think through this step by step", "break this problem down", "reason about this in stages") alongside the tool-jargon capabilities so the description matches how users actually ask for help.

Sharpen distinctiveness by tying triggers to the unique revision/branching behavior rather than generic 'complex problems' phrasing that many skills could claim.

Tighten the lead so the distinctive capability (iterative reasoning that can revise and branch) is the headline, reducing surface similarity to general planning skills.

Dimension	Reasoning	Score
Specificity	Lists multiple distinct concrete capabilities of the tool — "revise thoughts", "branch into alternative approaches", "dynamically adjust scope" — alongside concrete use cases (multi-stage analysis, design planning, problem decomposition), matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers both what it does ("systematic step-by-step reasoning with ability to revise thoughts, branch into alternative approaches, or dynamically adjust scope") and when to use it via an explicit "Use when..." clause, matching the top anchor.	3 / 3
Trigger Term Quality	Some natural terms appear ("complex problems", "multi-stage analysis", "problem decomposition", "design planning") but tool-specific jargon like "branch into alternative approaches", "revise thoughts", and "dynamically adjust scope" is language users would not naturally say, missing common phrasings.	2 / 3
Distinctiveness Conflict Risk	The revision/branching capabilities give it a niche, but the triggers ("complex problems", "multi-stage analysis", "problem decomposition") are fairly generic problem-solving language that could overlap with other reasoning or planning skills.	2 / 3
	Total	10 / 12 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: mrgoonie/claudekit-skills
Path: .claude/skills/sequential-thinking/SKILL.md
Commit: 80113d8

Reviewed: about 9 hours 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.