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.
72
72%
Does it follow best practices?
Impact
54%
3.17xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./data/0-sequential-thinking/SKILL.mdQuality
Discovery
59%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 structurally complete with explicit 'Use when' triggers, but suffers from being overly abstract and generic. It describes a meta-methodology (thinking/reasoning process) rather than a concrete capability tied to a specific domain, which makes it nearly impossible to distinguish from other skills. The heavy repetition of near-synonymous terms across capabilities, actions, and keywords adds verbosity without clarity.
Suggestions
Narrow the scope to a specific domain or problem type — e.g., 'Use when solving ambiguous engineering design problems' rather than generic 'complex problems' — to reduce conflict risk with other skills.
Replace abstract methodological terms like 'adaptive planning' and 'course correction' with concrete examples of what the skill actually produces or handles, such as specific output formats or problem categories.
Reduce redundancy — 'decompose,' 'problem decomposition,' 'complex problem decomposition,' and 'decomposing complex problems' all appear as near-duplicates across different sections.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names a domain (reflective problem-solving) and lists actions like 'decompose, analyze, hypothesize, verify, revise,' but these are abstract methodological steps rather than concrete, tangible actions. It never specifies what kinds of problems or what concrete outputs it produces. | 2 / 3 |
Completeness | The description explicitly answers both 'what does this do' (structured reflective problem-solving with decompose/analyze/verify process) and 'when should Claude use it' with an explicit 'Use when:' clause listing specific trigger scenarios like decomposing complex problems, analyzing unclear scope, and needing course correction. | 3 / 3 |
Trigger Term Quality | It includes several keywords like 'sequential thinking,' 'problem decomposition,' 'step-by-step,' and 'complex problem,' some of which users might naturally say. However, many terms are methodological jargon ('hypothesis verification,' 'adaptive planning,' 'course correction') that users are unlikely to use verbatim, and the keyword list feels padded with near-synonyms. | 2 / 3 |
Distinctiveness Conflict Risk | This description is extremely generic — virtually any complex task involves decomposition, analysis, planning, and verification. It would conflict with nearly any skill that involves problem-solving, coding, debugging, or analytical work, making it very difficult to distinguish from other skills. | 1 / 3 |
Total | 8 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured methodological skill that efficiently communicates a reflective problem-solving framework. Its strengths are excellent progressive disclosure, clear workflow sequencing with feedback loops, and token efficiency. The main weakness is that the guidance, while structured, is more of a thinking methodology template than concrete executable instructions, which slightly limits actionability.
Suggestions
Consider adding one brief, complete worked example inline (e.g., a 3-4 thought debugging sequence) to make the methodology more concrete and actionable rather than purely template-based.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It avoids explaining what sequential thinking or problem decomposition is conceptually, instead jumping straight into actionable process steps. Every section earns its place with no padding or unnecessary context. | 3 / 3 |
Actionability | The skill provides concrete formatting templates (thought markers, revision format, branching format) which are useful, but the guidance is more structural/methodological than executable. The 'code' blocks are templates rather than copy-paste-ready executable code, and the actual problem-solving steps remain somewhat abstract (e.g., 'Address one aspect per thought'). | 2 / 3 |
Workflow Clarity | The multi-step process is clearly sequenced from initial estimate through dynamic adjustment, revision, branching, hypothesis verification, and completion criteria. Each step has explicit markers and the workflow includes feedback loops (revise when needed, iterate until hypothesis verified, complete only when ready with clear criteria). | 3 / 3 |
Progressive Disclosure | The skill provides a clear overview with well-organized sections, then points to one-level-deep references for deeper content (core patterns, examples, advanced techniques). Scripts are marked as optional. Navigation is clear and appropriately structured. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- majiayu000/claude-skill-registry-data
- Commit
6770aaa
- Reviewed
Table of Contents
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.