behavioral-modes

AI operational modes (brainstorm, implement, debug, review, teach, ship, orchestrate).

Quality

27%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.agent/skills/behavioral-modes/SKILL.md

Quality

Discovery

32%

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 provides a list of operational modes but lacks explanation of what each mode does and critically omits any guidance on when Claude should use this skill. The brevity sacrifices clarity - users and Claude cannot determine from this description what capabilities each mode provides or what triggers should activate this skill.

Suggestions

Add a 'Use when...' clause specifying trigger scenarios, e.g., 'Use when the user wants to switch working styles, asks to brainstorm ideas, requests focused implementation, or needs structured debugging assistance.'

Expand each mode with a brief action description, e.g., 'brainstorm (generate ideas freely), implement (write production code), debug (systematically find and fix issues)...'

Include natural language triggers users might say, such as 'let's think through this', 'help me build', 'what's wrong with this code', 'review my work'.

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 phrases users would use to invoke these modes (e.g., 'help me think through', 'fix this bug', 'code review').	2 / 3
Distinctiveness Conflict Risk	The term 'AI operational modes' provides some distinctiveness, but individual modes like 'debug' and 'review' could easily conflict with other coding or review-focused skills without clearer scoping.	2 / 3
	Total	7 / 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 functions as a poorly organized index rather than actionable guidance. It lacks any explanation of what the modes do, when to use them, or how they change AI behavior. The sub-skill references are disorganized, mixing top-level modes with their sub-components at the same hierarchy level.

Suggestions

Add a brief description (1-2 sentences) for each mode explaining its purpose and when to use it, directly in this file

Organize the sub-skills hierarchically - group sub-components under their parent modes (e.g., Critical/Improvements/Good under REVIEW)

Add a quick reference table or decision guide showing which mode to use for common scenarios

Include at least one concrete example of mode activation syntax or trigger phrases

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	The skill provides zero concrete guidance on how to use these modes, when to switch between them, or what behaviors each mode entails. It's purely a list of links with no executable instructions or examples.	1 / 3
Workflow Clarity	There is no workflow defined - no sequence for when to use which mode, no guidance on mode transitions, and no validation of whether a mode is appropriate for a given task. The numbered list doesn't represent a workflow, just a disorganized index.	1 / 3
Progressive Disclosure	The skill does reference sub-skills appropriately (one level deep), but the organization is poor - modes are mixed with sub-components (Critical, Improvements, Good appear to be parts of REVIEW mode but are listed at the same level). Navigation is confusing due to inconsistent numbering and unclear hierarchy.	2 / 3
	Total	6 / 12 Passed

Validation

90%

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 — 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: 332e58b

Reviewed: 17 days 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.