behavioral-modes

AI operational modes (brainstorm, implement, debug, review, teach, ship, orchestrate). Use to adapt behavior based on task type.

Quality

57%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/behavioral-modes/SKILL.md

Quality

Content

57%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is a well-organized catalog of behavioral modes with concrete behaviors, output templates, and a trigger table, making it reasonably actionable. Its weaknesses are verbosity from per-mode template blocks and a lack of validation/feedback structure or any progressive disclosure.

Suggestions

Trim the per-mode emoji output-style templates to short exemplars and remove the empty 'Combining Modes' section to reduce token bloat.

Add a brief validation/feedback step (e.g. confirm the detected mode with the user before committing to a behavior) to strengthen workflow clarity.

Move the detailed per-mode output templates or the multi-agent collaboration patterns into a reference file and link to it from SKILL.md to enable progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is mostly structured but noticeably padded: full emoji output-style templates for every mode, an empty 'Combining Modes' section, and generic boilerplate in 'When to Use'/'Limitations' could be trimmed.	3 / 5
Actionability	Each mode gets concrete behaviors and an output template, plus a trigger->mode table and explicit slash-command examples, giving mostly executable guidance with only minor gaps.	4 / 5
Workflow Clarity	Mode detection plus manual switching forms a rough two-step flow, but there are no validation or feedback checkpoints and no real multi-step sequencing.	3 / 5
Progressive Disclosure	The single file is well-sectioned per mode, but ~250 lines are all inline with no reference files or progressive disclosure mechanism, and the empty 'Combining Modes' header signals an organization gap.	3 / 5
	Total	13 / 20 Passed

Description

57%Weight 40%Scale 1-5

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 clearly conveys what the skill covers by listing its modes, but the 'when to use' guidance is generic and lacks concrete trigger phrases. Trigger-term quality is its strongest dimension, while completeness and distinctiveness are limited by the vague use-case clause.

Suggestions

Replace 'Use to adapt behavior based on task type' with concrete triggers, e.g. 'Use when the user wants to brainstorm ideas, implement a feature, debug an error, review code, teach a concept, or prepare a release.'

Tie each mode to the natural phrases users say (e.g. 'brainstorm', 'debug', 'review') to sharpen trigger-term coverage with synonyms.

Narrow the scope or clarify how it differs from dedicated review/debug skills to reduce overlap/conflict risk.

Dimension	Reasoning	Score
Specificity	Names the domain ('AI operational modes') and enumerates seven concrete mode names, but the only stated action ('adapt behavior based on task type') is generic rather than a concrete capability, so coverage is present but not comprehensive.	3 / 5
Completeness	The 'what' is clear (the listed operational modes), but the 'when' clause ('Use to adapt behavior based on task type') is weak and generic with no concrete trigger phrases, leaving 'when' only weakly specified.	3 / 5
Trigger Term Quality	The mode names ('brainstorm', 'implement', 'debug', 'review', 'teach', 'ship') are natural terms users would actually say, giving good keyword coverage, though a few common synonyms are missing.	4 / 5
Distinctiveness Conflict Risk	The named modes give it some specificity, but as a broad behavior-adaptation meta-skill it overlaps with dedicated review/debug/coding skills, so conflict risk remains moderate.	3 / 5
	Total	13 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: sickn33/antigravity-awesome-skills
Path: skills/behavioral-modes/SKILL.md
Commit: b6ceca3

Reviewed: 3 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.