behavioral-modes

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

1.10x

Quality

60%

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/skills/behavioral-modes/SKILL.md

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

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 well-organized into clearly delineated modes with concrete behavioral guidance and a useful detection table, but it is a single long inline file with padded output templates, an empty section, and no validation checkpoints in its mode-switching workflow.

Suggestions

Remove the empty 'Combining Modes' section and trim the verbose per-mode output-style code blocks to lean directives.

Move the time-sensitive 'Multi-Agent Collaboration Patterns (2025)' detail into a separate reference file and drop the year from the header, or place it under a clearly labeled dated section.

Add a brief validation/confirmation step to the mode-selection workflow (e.g. confirm the detected mode with the user before applying) so the sequence has an explicit checkpoint.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and assumes Claude's intelligence (no basic concept explanations), but it carries illustrative output-style templates, an empty 'Combining Modes' section, and a time-sensitive 'Multi-Agent Collaboration Patterns (2025)' header that could become stale.	3 / 5
Actionability	Concrete behavioral directives ('Offer multiple alternatives (at least 3)', 'Categorize by severity (Critical/High/Medium/Low)'), a trigger-to-mode detection table, and explicit slash commands give mostly executable guidance, with a few abstract items like 'Think divergently'.	4 / 5
Workflow Clarity	A loose detect-mode-then-apply sequence exists via the detection table, but there are no validation checkpoints or feedback loops, and the multi-mode reference is not a clearly sequenced multi-step process.	3 / 5
Progressive Disclosure	The body is well-sectioned into per-mode headers, but all 248 lines are inline in a single file with no bundle references; output-style templates and the multi-agent patterns could be split into separate files for cleaner navigation.	3 / 5
	Total	13 / 20 Passed

Description

62%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 names the domain and enumerates concrete modes, but its trigger guidance is a purpose statement rather than an explicit 'Use when...' clause, and several mode names overlap with existing specialized skills.

Suggestions

Replace 'Use to adapt behavior based on task type' with an explicit trigger clause, e.g. 'Use when the user asks to brainstorm, debug, review, teach, or ship a task and wants behavior tuned to that task type.'

Add natural synonyms a user might say (e.g. 'troubleshoot', 'audit', 'deploy', 'explain') to broaden trigger-term coverage.

Clarify what distinguishes this from dedicated debug/review skills so it does not trigger for those single-purpose tasks.

Dimension	Reasoning	Score
Specificity	Enumerates seven concrete modes ('brainstorm, implement, debug, review, teach, ship, orchestrate'), listing several specific capabilities, though 'adapt behavior based on task type' remains somewhat abstract rather than a fully comprehensive action set.	4 / 5
Completeness	The 'what' is clear (AI operational modes enumerated), but the 'when' is only weakly implied: 'Use to adapt behavior based on task type' states purpose rather than an explicit trigger, and the rubric caps completeness at 3 when 'Use when...' trigger guidance is absent.	3 / 5
Trigger Term Quality	Includes natural terms users actually say ('brainstorm', 'debug', 'review', 'teach', 'ship'), giving good keyword coverage, but lacks synonyms and the phrase 'adapt behavior based on task type' is not a natural user utterance.	4 / 5
Distinctiveness Conflict Risk	The 'behavioral/operational modes' niche is somewhat specific, but enumerated modes like 'debug' and 'review' overlap with dedicated debugging and code-review skills, leaving moderate conflict risk.	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/skills/behavioral-modes/SKILL.md
Commit: 57c135b

Reviewed: 23 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.