behavioral-modes

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

1.10x

Quality

56%

Does it follow best practices?

Impact

96%

1.10x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/behavioral-modes/SKILL.md

The canonical home for this skill is behavioral-modes in sickn33/agentic-awesome-skills

Quality

Content

47%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 body is a well-structured catalog of behavior modes with concrete templates and a detection table, but it is padded with verbose/decorative templates and tangential sections, and it lacks a clear sequenced workflow with validation checkpoints.

Suggestions

Trim the decorative emoji output-templates and the 'NOT:' example to reduce token overhead while preserving the behavioral guidance.

Either remove the empty 'Combining Modes' section or fill it with concrete guidance on how to combine or transition between modes.

Add an explicit workflow with checkpoints for mode selection (detect trigger → confirm mode → apply behavior → verify output matches the mode's style), and clarify how the manual /brainstorm-style commands are actually invoked.

Dimension	Reasoning	Score
Conciseness	The body is mostly focused and does not re-explain concepts Claude already knows, but the decorative emoji output-templates, the illustrative 'NOT:' example, and the tangential 'Multi-Agent Collaboration Patterns (2025)' section add padding that could be tightened.	3 / 5
Actionability	Concrete guidance is present (e.g. 'at least 3 alternatives', severity categories, a deployment checklist, a trigger→mode table) but interleaved with abstract directives like 'Think divergently', and the manual /brainstorm-style commands are mentioned without explaining how they are wired.	3 / 5
Workflow Clarity	There is no clearly sequenced multi-step workflow with validation checkpoints; the PEC pattern offers only a rough three-step sequence with no checkpoints, and mode detection is a mapping rather than a workflow.	2 / 5
Progressive Disclosure	No bundle files exist and the single file is well organized into clearly headed per-mode sections; the only organization gap is an empty 'Combining Modes' placeholder section, keeping it just below a 5.	4 / 5
	Total	12 / 20 Passed

Description

66%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 states what the skill covers (seven named operational modes) and includes a 'Use to…' when clause, but the when guidance is generic and the mode names are broad verbs that overlap with many skills.

Suggestions

Add concrete trigger phrases to the when clause, e.g. 'Use when the user says brainstorm, implement, debug, review, teach, ship, or wants to switch AI behavior to match a task type.'

Sharpen the action framing beyond 'adapt behavior based on task type' to describe what the modes actually do (e.g. 'switches AI communication style, output format, and priorities to match the task').

Narrow distinctiveness by distinguishing these modes from generic verbs, e.g. framing as a meta-routing skill rather than overlapping with implement/debug/review skills.

Dimension	Reasoning	Score
Specificity	Names the domain and enumerates seven concrete modes (brainstorm, implement, debug, review, teach, ship, orchestrate), but the only action framing is the generic 'adapt behavior based on task type' with no concrete actions described.	3 / 5
Completeness	It has a clear 'what' (the enumerated modes) and a 'when' clause ('Use to adapt behavior based on task type'), but the when is generic and lacks concrete trigger phrases, matching the 'could be more explicit or specific' anchor.	4 / 5
Trigger Term Quality	The enumerated mode names are natural terms users actually say and give good keyword coverage, though common synonyms and explicit trigger phrases are missing, so it falls short of a 5.	4 / 5
Distinctiveness Conflict Risk	The 'behavioral modes' framing is a somewhat distinct niche, but the trigger terms (implement, debug, review, brainstorm) are generic verbs with real overlap risk against many other skills.	3 / 5
	Total	14 / 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: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/behavioral-modes/SKILL.md
Commit: 57c135b

Reviewed: 17 hours 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.