thinking-deeply
Engages structured analysis to explore multiple perspectives and context dependencies before responding. Use when users ask confirmation-seeking questions, make leading statements, request binary choices, or when feeling inclined to quickly agree or disagree without thorough consideration.
62
53%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./think_deeply/SKILL.mdQuality
Discovery
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 has a well-structured format with an explicit 'Use when' clause that covers both what the skill does and when to invoke it. Its main weaknesses are that the capability description is somewhat abstract rather than listing concrete actions, and the trigger terms describe meta-cognitive patterns that users are unlikely to explicitly state in their requests. The skill's niche is moderately distinct but could overlap with general analytical or reasoning skills.
Suggestions
Add more concrete actions the skill performs, e.g., 'identifies assumptions, generates counterarguments, evaluates evidence from multiple angles, surfaces hidden context dependencies'.
Include more natural user-facing trigger terms that people would actually say, such as 'Is X always better than Y?', 'Don't you think...', 'Should I just...', 'yes or no', or 'right or wrong'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names a domain ('structured analysis', 'multiple perspectives', 'context dependencies') and describes a general approach, but the concrete actions are vague—'engages structured analysis' and 'explore multiple perspectives' are more abstract process descriptions than specific concrete actions like 'generates pro/con lists' or 'identifies assumptions'. | 2 / 3 |
Completeness | The description clearly answers both 'what' (engages structured analysis to explore multiple perspectives and context dependencies) and 'when' (explicit 'Use when' clause listing confirmation-seeking questions, leading statements, binary choices, and the internal trigger of feeling inclined to quickly agree/disagree). | 3 / 3 |
Trigger Term Quality | Includes some useful trigger terms like 'confirmation-seeking questions', 'leading statements', 'binary choices', which are somewhat natural. However, these are more analytical/meta-cognitive terms than phrases users would naturally say—users are unlikely to say 'I have a confirmation-seeking question' or 'I'm making a leading statement'. | 2 / 3 |
Distinctiveness Conflict Risk | The skill occupies a somewhat distinct niche around critical thinking and avoiding hasty agreement, but 'structured analysis' and 'multiple perspectives' are broad enough to potentially overlap with general reasoning, debate, or decision-making skills. The triggers around 'binary choices' and 'confirmation-seeking' help but are not highly distinctive. | 2 / 3 |
Total | 9 / 12 Passed |
Implementation
39%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill has a well-structured workflow but is severely bloated. The three examples are repetitive (all follow the identical pattern for tech choices), and the skill over-explains concepts Claude inherently understands like what confirmation bias is or how to consider multiple perspectives. The content could be reduced by 60-70% without losing any actionable guidance.
Suggestions
Reduce to one example maximum and move it to a separate EXAMPLES.md file, since all three examples demonstrate the identical pattern with different tech topics.
Remove sections that explain concepts Claude already knows: the 'When This Skill Activates' list items don't need definitions (e.g., 'Questions that contain embedded assumptions'), and the 'Remember' section restates the purpose.
Condense the anti-patterns list into the core protocol steps rather than a separate section - e.g., integrate 'don't immediately agree' into step 1 rather than listing it twice.
Add a brief 'Quick Reference' section at the top with the 5 steps as a one-line-each summary, then link to detailed sections below for progressive disclosure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~200+ lines. Extensively explains concepts Claude already understands (what confirmation-seeking questions are, what leading statements are, how to think about trade-offs). The three full examples are repetitive and follow the same pattern - one would suffice. The anti-patterns, success criteria, and 'Remember' sections restate what's already covered. Much of this could be condensed to 30-40 lines. | 1 / 3 |
Actionability | The skill provides a concrete 5-step protocol and detailed response templates with examples, which is somewhat actionable. However, this is an instruction-only skill (no code/commands), and the guidance is more of a thinking framework than precise, executable steps. The response format template in step 4 is concrete but formulaic, and the examples show the same pattern applied mechanically rather than demonstrating nuanced application. | 2 / 3 |
Workflow Clarity | The 5-step workflow (Pause → Reframe → Map → Respond → Avoid anti-patterns) is clearly sequenced and logical. Each step has explicit sub-steps. The structured response format provides a clear template. For a non-destructive thinking/reasoning skill, validation checkpoints aren't critical, and the workflow is unambiguous. | 3 / 3 |
Progressive Disclosure | Monolithic wall of text with no references to external files. The three lengthy examples (each 30+ lines) are inline and could easily be in a separate EXAMPLES.md. The content is not split or organized for progressive discovery - everything is dumped into one long document with no navigation aids or cross-references. | 1 / 3 |
Total | 7 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- brunoasm/my_claude_skills
- Commit
f569911
- 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.