behavioral-modes
AI operational modes (brainstorm, implement, debug, review, teach, ship, orchestrate).
38
Quality
23%
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 ./.agent/skills/behavioral-modes/SKILL.mdQuality
Discovery
25%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 description provides a list of operational mode names but fails to explain what they do or when to use them. The lack of a 'Use when...' clause and the generic nature of terms like 'debug' and 'review' make it difficult for Claude to know when to select this skill over others. The description needs substantial improvement to be effective for skill selection.
Suggestions
Add a 'Use when...' clause specifying triggers like 'when the user wants to switch working modes', 'asks to brainstorm ideas', or 'requests a code review'
Briefly explain what each mode does (e.g., 'brainstorm mode for generating ideas without implementation, implement mode for writing production code')
Add distinguishing context such as 'for structured AI collaboration workflows' to differentiate from general coding or review skills
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists seven specific operational modes by name (brainstorm, implement, debug, review, teach, ship, orchestrate), which names the domain and some actions, but doesn't explain what each mode actually does or what concrete actions they enable. | 2 / 3 |
Completeness | Only partially answers 'what' (lists mode names without explaining them) and completely missing 'when' - no 'Use when...' clause or explicit trigger guidance for when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'brainstorm', 'implement', 'debug', 'review' that users might naturally say, but missing common variations and the term 'operational modes' is somewhat technical jargon users wouldn't typically use. | 2 / 3 |
Distinctiveness Conflict Risk | Very generic terms like 'implement', 'debug', 'review' would conflict with many other coding, development, or workflow skills. No clear niche established to distinguish from other skills. | 1 / 3 |
Total | 6 / 12 Passed |
Implementation
22%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill content is essentially a disorganized index of links with no actionable guidance. It fails to explain how to invoke modes, when to use each one, or how they interact. The structure conflates top-level modes with their sub-components, creating confusion rather than clarity.
Suggestions
Add a quick-start section showing how to invoke a mode (e.g., 'Enter BRAINSTORM mode' or whatever the activation syntax is) with a concrete example
Reorganize the list to clearly separate the 7 main modes from their sub-components using proper hierarchy (nested lists or separate sections)
Add a brief decision guide or table showing when to use each mode (e.g., 'Use DEBUG when: encountering errors, unexpected behavior')
Include at least one complete example showing mode invocation and expected AI behavior change
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is relatively brief but includes redundant header formatting (numbered list items that are also links with numbers in titles). The 'Knowledge Modules (Fractal Skills)' section header adds no value and the organization is confusing. | 2 / 3 |
Actionability | No concrete guidance on how to use these modes, when to switch between them, or what commands/syntax to invoke them. It's purely a list of links with no executable instructions or examples. | 1 / 3 |
Workflow Clarity | No workflow is defined for selecting or transitioning between modes. The list appears disorganized (modes 1-6 mixed with sub-components like 'Critical', 'Improvements', 'Good' that seem to belong under REVIEW mode). No sequence or decision logic provided. | 1 / 3 |
Progressive Disclosure | References to sub-skills exist and are one level deep, but the organization is poor. Sub-components of modes (like 'Critical', 'Good', 'What is it?') are listed at the same level as top-level modes, making navigation confusing. The hierarchy is unclear. | 2 / 3 |
Total | 6 / 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
- Dokhacgiakhoa/antigravity-ide
- Commit
3395991
- 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.