moai-workflow-thinking

Sequential Thinking MCP for structured step-by-step analysis via --deepthink flag. Separate from UltraThink which is Claude's native extended reasoning mode. Use for multi-step analysis or architecture decisions.

Quality

72%

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 ./.moai/archive/skills/v3.0/moai-workflow-thinking/SKILL.md

Quality

Content

70%

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

The content is well-structured with a clear, validated workflow and no reference-chain problems, but its examples are template-style rather than executable MCP calls and the rationalizations section adds padding. Making examples real and trimming the prose would lift the weaker dimensions.

Suggestions

Show actual MCP tool invocations (the full tool name with arguments) instead of YAML-style parameter templates, so the usage examples are directly copy-pasteable.

Move or trim the 'Common Rationalizations' table; it restates concepts Claude already applies and competes with the context window without adding executable guidance.

Dimension	Reasoning	Score
Conciseness	The parameter reference, usage pattern, and guidelines are lean and earn their tokens, but the 'Common Rationalizations' table is philosophical padding that restates what Claude already infers, so the body could be tightened overall.	2 / 3
Actionability	Concrete guidance exists, but the usage-pattern blocks are YAML-style parameter templates rather than actual MCP tool invocations, so they read as pseudocode rather than copy-paste-ready executable calls.	2 / 3
Workflow Clarity	The Usage Pattern lays out a clear Step 1 → Step 2 → Revision → Conclusion sequence with an explicit revision feedback loop, and the Verification section provides a checklist for complex sessions.	3 / 3
Progressive Disclosure	No bundle files exist and none are needed; the body is organized into clearly headed single-level sections (modes, triggers, parameters, usage, guidelines, verification) with no nested reference chains and easy navigation.	3 / 3
	Total	10 / 12 Passed

Description

75%

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-differentiated and answers both 'what' and 'when' explicitly, but its capability list is abstract and its trigger-term coverage is narrower than the keywords the skill itself lists. Tightening these two areas would raise it from good to excellent.

Suggestions

Replace abstract phrasing like 'structured step-by-step analysis' with concrete actions the skill performs, e.g. 'Decompose problems into numbered thoughts, branch alternatives, and revise prior steps'.

Broaden trigger terms beyond '--deepthink flag' and 'architecture decisions' to natural phrasings users actually say, such as 'complex problem', 'trade-offs', 'technology selection', and 'breaking changes'.

Dimension	Reasoning	Score
Specificity	Names the domain ('Sequential Thinking MCP') and a couple of actions ('structured step-by-step analysis', 'architecture decisions') but does not list multiple concrete, distinct actions the way a score-3 example like 'extract, fill, merge' does.	2 / 3
Completeness	Clearly states what the skill does ('Sequential Thinking MCP for structured step-by-step analysis') and provides an explicit trigger clause ('Use for multi-step analysis or architecture decisions'), satisfying both what and when.	3 / 3
Trigger Term Quality	Includes some relevant natural terms ('multi-step analysis', 'architecture decisions') but the primary trigger ('--deepthink flag') is a flag rather than an utterance, and common variations from the body's keyword list (e.g. 'trade-offs', 'breaking changes', 'complex problem') are omitted.	2 / 3
Distinctiveness Conflict Risk	It explicitly carves out a niche and disambiguates from a near-sibling ('Separate from UltraThink which is Claude's native extended reasoning mode'), with a flag-gated trigger unlikely to fire for the wrong skill.	3 / 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: modu-ai/moai-adk
Path: .moai/archive/skills/v3.0/moai-workflow-thinking/SKILL.md
Commit: 05117b6

Reviewed: 1 day 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.