behavioral-modes

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

Quality

73%

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 ./.agents/skills/behavioral-modes/SKILL.md

Quality

Content

75%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-structured, actionable catalog of behavioral modes with clear sequencing guidance and explicit mode-switch triggers, losing points only for minor padding and the lack of any reference split for the larger inline detail.

Suggestions

Trim the IMPLEMENT "NOT" anti-example and consolidate emoji-heavy output templates to tighten token efficiency.

Add a brief concrete mechanism for switching or persisting mode state across a task (e.g. how MENTAL MODEL SYNC is loaded/saved) to close the actionability gap.

Consider splitting the per-mode output-style templates into a single one-level-deep reference (e.g. MODE-TEMPLATES.md) to improve progressive disclosure for the longer inline detail.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient mode definitions and templates with no over-explanation of concepts Claude already knows; only minor illustrative padding (the IMPLEMENT "NOT" example and emoji output templates) could be trimmed.	4 / 5
Actionability	Each mode provides concrete behavior bullets and an output-style template with specific directives (e.g. "Offer multiple alternatives (at least 3)", "Form hypothesis → test → verify"), with only minor gaps around the mechanics of actually switching or persisting mode state.	4 / 5
Workflow Clarity	The "Combining Modes" table sequences explicit mode chains per flow and includes a checkpoint signal ("drop from IMPLEMENT to DEBUG the moment a test fails"), but these are illustrative flows rather than a single enforced validated workflow.	4 / 5
Progressive Disclosure	A single self-contained file with clear headers and a navigation/detection table is well-organized, though the ~245-line monolith inlines substantial per-mode detail that is not split into one-level-deep references.	4 / 5
	Total	16 / 20 Passed

Description

71%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 cleanly names the skill's seven modes and pairs a what with a when, but the when-clause stays generic and the meta-behavioral framing leaves moderate overlap risk with other task-oriented skills.

Suggestions

Fold concrete trigger phrases into the description (e.g. "Use when the user asks to brainstorm, debug, review, teach, or ship code") to lift completeness toward 5.

Add synonyms users naturally say alongside each mode (e.g. "fix bug" for debug, "code review" for review) to broaden trigger-term coverage.

Sharpen the niche by framing the skill around adaptive operating modes specifically, reducing overlap with generic task skills.

Dimension	Reasoning	Score
Specificity	Enumerates seven concrete modes (brainstorm, implement, debug, review, teach, ship, orchestrate) and a concrete action ("adapt behavior based on task type"), listing several specific actions with only minor coverage gaps.	4 / 5
Completeness	States both the "what" (operational modes) and a "when" ("Use to adapt behavior based on task type"), though the when-clause is generic rather than concrete trigger phrases.	4 / 5
Trigger Term Quality	Includes natural user-facing terms like "brainstorm", "debug", "review", and "ship", but offers no synonyms or common variations (e.g. "fix bug", "code review") beyond the mode names.	4 / 5
Distinctiveness Conflict Risk	The meta-framing of "adapt behavior based on task type" is broad and could overlap with general task-handling skills, though the enumerated mode list provides a recognizable niche.	3 / 5
	Total	15 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: vudovn/ag-kit
Path: .agents/skills/behavioral-modes/SKILL.md
Commit: 549ba3d

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.