ultrathink
Display colorful ANSI art of the word "ultrathink". Use when the user says "ultrathink" or invokes /ultrathink.
96
95%
Does it follow best practices?
Impact
100%
1.58xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a well-structured description for a very narrow skill. It clearly states what it does and when to use it, with distinctive trigger terms that minimize conflict risk. The only minor weakness is that the capability itself is singular and simple, so there isn't much to elaborate on in terms of specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names a specific action ('Display colorful ANSI art of the word "ultrathink"') but describes only a single, narrow action rather than listing multiple concrete capabilities. | 2 / 3 |
Completeness | Clearly answers both 'what' (display colorful ANSI art of the word 'ultrathink') and 'when' (when the user says 'ultrathink' or invokes /ultrathink), with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes the natural trigger terms 'ultrathink' and '/ultrathink', which are exactly what a user would say to invoke this skill. Given the narrow scope, these are the right and sufficient keywords. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — the trigger 'ultrathink' and '/ultrathink' are unique terms unlikely to conflict with any other skill. The niche is very clear and narrow. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an exemplary simple skill — maximally concise, fully actionable, and perfectly scoped. It provides an executable command with a clear behavioral constraint ('Do not add any other output or commentary'), and wastes zero tokens on explanation Claude doesn't need.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely lean — no unnecessary explanation, no padding. Every token serves a purpose. Claude doesn't need to be told what ANSI art is or how printf works. | 3 / 3 |
Actionability | Provides a fully executable, copy-paste ready bash command. The instruction is completely unambiguous: run this command, output nothing else. | 3 / 3 |
Workflow Clarity | This is a single-action skill with no multi-step process. The single action is completely unambiguous: run the command, no other output. Per scoring notes for simple skills, this merits a 3. | 3 / 3 |
Progressive Disclosure | For a skill under 50 lines with no need for external references, the content is well-organized with a clear heading and a single well-structured section. No external files are needed. | 3 / 3 |
Total | 12 / 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
- intellectronica/agent-skills
- Commit
9b0e00a
- 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.