CtrlK
BlogDocsLog inGet started
Tessl Logo

moai-foundation-thinking

Unified thinking toolkit: Creative frameworks (Critical Evaluation, Diverge-Converge, Deep Questioning), First Principles reasoning (absorbed from moai-foundation-philosopher), and Adaptive Thinking via the `ultrathink` keyword. Use for ideation, strategic analysis, architecture decisions, and deep reasoning on complex problems.

60

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/moai-foundation-thinking/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

77%

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

The body is well-organized, actionable, and clearly sequenced with checklists, but it is verbose for concepts Claude largely already knows and—more seriously—references module files that are absent from the bundle while duplicating that detail inline. Fixing the broken module links and trimming inline redundancy would meaningfully raise quality.

Suggestions

Create the referenced modules/*.md files (critical-evaluation, diverge-converge, deep-questioning, first-principles, assumption-matrix, trade-off-analysis, cognitive-bias) or remove the dead links, so progressive-disclosure navigation actually resolves.

Trim the inline full-step reproductions of widely-known frameworks (critical thinking, brainstorming, five-whys, first-principles) to overviews, moving exhaustive step lists into the module files; remove the unsourced IMPACT statistics.

Move the time-sensitive version language (Opus 4.7+/4.8/5 references) into the existing Backward Compatibility / deprecated-style section so the main body stays evergreen.

DimensionReasoningScore

Conciseness

The body is well-structured but verbose: it spells out full step-by-step procedures for critical-thinking, brainstorming, and first-principles concepts Claude already knows, plus unsourced "IMPACT" stats ("catches 60-80%", "3x more", "40-60%") and inline time-sensitive version markers ("Opus 4.7+... including Opus 5 and 4.8") outside any deprecated section; not a 1 because it is organized rather than a padded wall, not a 3 due to the redundancy and fluff.

2 / 3

Actionability

Provides concrete, specific guidance: numbered steps (7-step evaluation, 5-phase diverge-converge, 6-layer questioning), explicit per-layer questions, defined Output Format templates, a Decision Complexity Guide, Red Flags, and a Verification checklist with checkboxes — actionable for an instruction-only skill without needing code.

3 / 3

Workflow Clarity

Multi-step processes are clearly sequenced (per-framework phases, a Combined Workflow ordering Question→Generate→Evaluate, and a Decision Complexity Guide) with an explicit Verification checklist and progressive depth indicators acting as checkpoints; not capped because the operations are analytical rather than destructive/batch.

3 / 3

Progressive Disclosure

References are one-level and signaled, but the body links to seven module files (e.g. [Critical Evaluation](modules/critical-evaluation.md), [First Principles](modules/first-principles.md), [Trade-off Analysis](modules/trade-off-analysis.md)) that do not exist in the bundle, while the full framework detail is also reproduced inline; not a 3 because navigation is broken and content that should live in the modules is duplicated inline, not a 1 because structure exists and references are not deeply nested.

2 / 3

Total

10

/

12

Passed

Description

67%

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 clearly states both capability and use cases with a reasonable trigger list, but leans on framework names over concrete actions and signals overlap with a sibling skill. It is solid but not maximally specific or distinctive.

Suggestions

Replace abstract use-case verbs with concrete actions the skill performs (e.g., 'Evaluate proposals through a 7-step critique', 'Generate 20-50 candidate solutions then score them') to lift specificity.

Add common natural trigger terms users actually say ('brainstorming', 'trade-off analysis', 'five whys', 'root cause') alongside the framework names.

Clarify the boundary with moai-foundation-philosopher so the description signals when this skill is the right choice vs. the absorbed predecessor.

DimensionReasoningScore

Specificity

Names concrete frameworks ("Critical Evaluation, Diverge-Converge, Deep Questioning", "First Principles reasoning", "Adaptive Thinking via the ultrathink keyword") but the actions are use-case abstractions ("ideation, strategic analysis, architecture decisions, and deep reasoning") rather than concrete operations; not a 3 because no specific concrete actions are enumerated.

2 / 3

Completeness

Explicitly answers both what ("Unified thinking toolkit: Creative frameworks..., First Principles reasoning..., and Adaptive Thinking via the ultrathink keyword") and when ("Use for ideation, strategic analysis, architecture decisions, and deep reasoning on complex problems").

3 / 3

Trigger Term Quality

Includes some natural terms users would say ("ideation", "strategic analysis", "architecture decisions", "deep reasoning") but is weighted toward framework jargon ("Critical Evaluation", "Diverge-Converge", "ultrathink") and misses common variations like "brainstorming" or "trade-offs"; not a 3 due to uneven natural coverage.

2 / 3

Distinctiveness Conflict Risk

The framework niche is somewhat distinct, but the skill self-identifies overlap ("absorbed from moai-foundation-philosopher") and "thinking" is a broad category that could trigger for related thinking/philosophy skills; not a 3 due to this stated overlap.

2 / 3

Total

9

/

12

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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

relative_links

Relative link issues: 10 missing

Warning

Total

13

/

16

Passed

Repository
modu-ai/moai-adk
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.