behavioral-modes
AI operational modes (brainstorm, implement, debug, review, teach, ship, orchestrate). Use to adapt behavior based on task type.
47
34%
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 ./skills/behavioral-modes/SKILL.mdQuality
Discovery
42%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 names seven operational modes which provides some structure, but fails to explain what each mode concretely does or when it should be triggered in specific user scenarios. The broad nature of the modes (debug, review, implement) creates high conflict risk with other skills, and the trigger guidance is too vague to be actionable for skill selection.
Suggestions
Add explicit 'Use when...' triggers with concrete user scenarios, e.g., 'Use when the user explicitly requests a specific working mode like brainstorming ideas, debugging code, or reviewing a pull request.'
Reduce conflict risk by clarifying that this skill governs meta-level behavior switching rather than performing the tasks themselves, e.g., 'Configures Claude's response style and approach when the user specifies a working mode.'
Add brief concrete descriptions of what each mode does differently, e.g., 'brainstorm: generates many ideas without filtering; debug: systematically isolates root causes.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists the seven operational modes by name (brainstorm, implement, debug, review, teach, ship, orchestrate), which gives some specificity, but does not describe what concrete actions each mode entails. 'Adapt behavior based on task type' is vague. | 2 / 3 |
Completeness | The 'what' is partially addressed (AI operational modes that adapt behavior), and there is a 'Use to...' clause, but 'adapt behavior based on task type' is too vague to serve as an explicit trigger. It doesn't clearly specify when Claude should select this skill in concrete, user-facing scenarios. | 2 / 3 |
Trigger Term Quality | The mode names (brainstorm, implement, debug, review, teach, ship, orchestrate) are somewhat natural keywords a user might say, but the description lacks common variations or phrases users would naturally use (e.g., 'code review', 'debugging', 'brainstorming session', 'deployment'). The framing as 'operational modes' is more internal jargon than user-facing language. | 2 / 3 |
Distinctiveness Conflict Risk | The modes listed (debug, review, implement, etc.) are extremely broad and would overlap with virtually any coding, writing, or task-specific skill. 'Adapt behavior based on task type' is generic enough to conflict with many other skills. | 1 / 3 |
Total | 7 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is overly verbose, spending many tokens describing behaviors Claude would naturally exhibit (asking clarifying questions, being thorough in reviews, explaining concepts simply). The output style templates add some value but could be dramatically condensed. The multi-agent collaboration section feels half-baked with an empty 'Combining Modes' section and vague references to files and patterns that aren't fleshed out.
Suggestions
Condense the entire skill to a compact reference table: mode name, 2-3 key behavioral overrides (things Claude wouldn't do by default), and a one-line output format hint. Remove all obvious behavioral instructions like 'ask for error messages' or 'be thorough but constructive'.
Either remove the 'Multi-Agent Collaboration Patterns' and 'Combining Modes' sections or flesh them out with concrete, actionable content including actual file schemas and transition workflows.
Split detailed output templates into a separate reference file (e.g., MODE_TEMPLATES.md) and keep SKILL.md as a lean overview with links.
Add a concrete link or path for the referenced 'clean-code' skill, and resolve the empty 'Combining Modes' section which currently has a heading with no content.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose for what it conveys. Most of this is template output formatting that Claude already knows how to produce. The mode descriptions explain obvious behaviors (e.g., 'Ask for error messages' in debug mode, 'Explain from fundamentals' in teach mode). The entire skill could be condensed to a compact table of modes with key behavioral overrides. | 1 / 3 |
Actionability | The output style templates provide some concrete guidance on expected format, and the mode detection table gives specific trigger words. However, there's no executable code, the 'Multi-Agent Collaboration Patterns' section is vague (references discovery-report.json and task.md without concrete details), and the 'Combining Modes' section is completely empty. | 2 / 3 |
Workflow Clarity | The mode detection table and manual switching commands provide a clear mechanism for mode selection. The PEC (Plan-Execute-Critic) pattern outlines a sequence. However, there are no validation checkpoints, the 'Combining Modes' section is empty with no guidance, and there's no clear workflow for transitioning between modes or handling ambiguous situations. | 2 / 3 |
Progressive Disclosure | Everything is in one monolithic file with no references to supporting documents. The skill references a 'clean-code' skill but doesn't link to it. At 150+ lines, content like detailed output templates, the mode detection table, and multi-agent patterns could be split into separate reference files. The 'Combining Modes' section header exists but is empty. | 1 / 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
- sickn33/antigravity-awesome-skills
- Commit
9d0b37c
- 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.