sequential-thinking

Structured reflective problem-solving methodology. Process: decompose, analyze, hypothesize, verify, revise. Capabilities: complex problem decomposition, adaptive planning, course correction, hypothesis verification, multi-step analysis. Actions: decompose, analyze, plan, revise, verify solutions step-by-step. Keywords: sequential thinking, problem decomposition, multi-step analysis, hypothesis verification, adaptive planning, course correction, reflective thinking, step-by-step, thought sequence, dynamic adjustment, unclear scope, complex problem, structured analysis. Use when: decomposing complex problems, planning with revision capability, analyzing unclear scope, verifying hypotheses, needing course correction, solving multi-step problems.

3.17x

Quality

—

Does it follow best practices?

Impact

54%

3.17x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

92%

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

The body is a tight, well-sequenced methodology with concrete thought-format templates and clear completion criteria, scoring high on conciseness, actionability, and workflow clarity. Progressive disclosure is the weak point because the referenced bundle files are not present.

Suggestions

Create the referenced files under references/ and scripts/ (core-patterns.md, examples-api.md, examples-debug.md, examples-architecture.md, advanced-techniques.md, advanced-strategies.md, process-thought.js, format-thought.js) so the signaled navigation resolves to real content.

If those files are intentionally omitted, remove the References and Scripts sections or note they are optional stubs, so the body does not advertise material that is absent.

Dimension	Reasoning	Score
Conciseness	Lean and efficient — short bullet lists and compact thought-format templates with no padding or explanation of concepts Claude already knows; every section earns its place.	3 / 3
Actionability	Provides concrete, copy-paste-ready thought markers ("Thought 1/5", "[REVISION of Thought 2]", "[BRANCH A from Thought 2]", "[FINAL]") with explicit field structure, giving clear executable guidance for the methodology.	3 / 3
Workflow Clarity	A clearly sequenced 7-step Core Process with feedback loops (revise → re-verify, branch → converge) and an explicit "Complete Only When Ready" completion checkpoint listing verification criteria.	3 / 3
Progressive Disclosure	The body is a clean overview with a well-signaled one-level-deep References section listing six reference files and two scripts, but none of those bundle files (references/, scripts/) actually exist in the skill, so the navigation points to missing material.	2 / 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 comprehensive and well-structured with explicit what/when guidance and concrete actions, but the keyword list leans on process jargon and some triggers are generic enough to risk overlap with other problem-solving skills.

Suggestions

Trim the keyword list to natural user phrasings (e.g., "think through a hard problem step by step", "work through a problem with revisions") and drop self-referential process jargon like "adaptive planning" and "course correction".

Add more distinctive triggers that separate this skill from general coding/planning skills, such as "when you keep revising an approach as you learn more" or "when a problem's scope keeps shifting".

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "decompose, analyze, hypothesize, verify, revise" and "verify solutions step-by-step" — naming the domain and a comprehensive action set, in third person.	3 / 3
Completeness	Explicitly answers both what ("Process: decompose, analyze, hypothesize, verify, revise") and when via a clear "Use when:" clause with concrete triggers.	3 / 3
Trigger Term Quality	Includes a keywords block with some natural terms ("sequential thinking", "step-by-step", "complex problem"), but much of it is process jargon ("adaptive planning", "course correction", "hypothesis verification") rather than phrases a user would naturally say, and the list reads as keyword-stuffed.	2 / 3
Distinctiveness Conflict Risk	"Sequential thinking" is a recognizable niche, but generic triggers like "complex problem", "structured analysis", and "multi-step" could overlap with general coding or planning skills.	2 / 3
	Total	10 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 8 missing	Warning

	Total	14 / 16 Passed

Repository: majiayu000/claude-skill-registry
Commit: cb3ef45

Reviewed: about 18 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.