behavioral-modes

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

Quality

59%

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 ./cli-tool/components/skills/ai-research/behavioral-modes/SKILL.md

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

Quality

Content

61%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-organized catalog of seven modes with concrete behavioral guidance and output templates, plus a useful trigger-to-mode detection table. Weaknesses are an empty 'Combining Modes' section, padded template blocks, and the absence of an explicit mode-selection workflow.

Suggestions

Fill in or remove the empty 'Combining Modes' section — a header with no content is the most visible structural gap.

Replace the implicit mode-selection logic with an explicit short workflow (e.g. 1. Match user intent against the trigger table; 2. Apply the mode's behavior list; 3. Follow its output style) so detection is a sequence rather than an implication.

Trim the output-style templates to one-line format summaries and move the dated 'Multi-Agent Collaboration Patterns (2025)' section to a deprecated/optional reference or drop the year to avoid time-sensitive staleness.

Dimension	Reasoning	Score
Conciseness	The per-mode bullet lists are efficient, but the full output-style templates (e.g. the TEACH template's five headed sections), emoji-decorated headers, and the 'Multi-Agent Collaboration Patterns (2025)' section with a time-sensitive date outside any deprecated section add padding that could be trimmed. Mostly efficient but noticeably tighten-able.	3 / 5
Actionability	Each mode gets concrete behaviors, explicit output-style templates, and the Mode Detection table maps trigger words ('not working', 'error', 'bug' → DEBUG) to modes, plus manual slash commands. Minor gaps remain: templates contain unfilled placeholders and '/brainstorm'-style commands have no implementation, keeping it below fully executable.	4 / 5
Workflow Clarity	Mode selection is implied by the trigger table but never sequenced as a workflow (no detect → apply → verify steps), and the 'Combining Modes' section is an empty header with no content — a clear gap. Sequence is present but implicit with no checkpoints, matching the 3 anchor.	3 / 5
Progressive Disclosure	The single-file skill has no bundle files (no references/, scripts/, or assets/ exist) and all content is appropriately inline at overview level, organized into consistent per-mode sections with a clear table of trigger mappings. The empty 'Combining Modes' header and the tacked-on multi-agent section are minor organization gaps.	4 / 5
	Total	14 / 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 states what the skill provides (seven named behavioral modes) but its trigger guidance is generic and lacks explicit 'use when' phrasing. Mode names like 'review' and 'debug' carry notable overlap risk with more specialized skills.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks to brainstorm, debug, review code, learn a concept, or prepare a release' — currently 'Use to adapt behavior based on task type' gives no concrete invocation signal.

State the core action more concretely than 'adapt behavior', e.g. 'Selects an operating mode and applies mode-specific behaviors, communication style, and output formats'.

Differentiate from overlapping skills by scoping the triggers (e.g. 'use for task-type adaptation, not full code review or debugging workflows').

Dimension	Reasoning	Score
Specificity	The description names the domain ('AI operational modes') and enumerates seven concrete modes ('brainstorm, implement, debug, review, teach, ship, orchestrate'), but the only stated action is the generic 'adapt behavior based on task type'. This matches the anchor for naming a domain with limited concrete actions rather than the 4-anchor's list of several specific actions.	3 / 5
Completeness	The 'what' is clear (seven named operational modes), but the 'when' is only weakly implied by 'Use to adapt behavior based on task type' — there is no explicit 'Use when...' clause with concrete trigger phrases. Per the judging guideline, missing explicit trigger guidance caps completeness at 3.	3 / 5
Trigger Term Quality	Terms like 'brainstorm', 'debug', 'review', 'teach', and 'ship' are natural phrases a user would say when needing this skill, giving good keyword coverage. It falls short of 5 because common variations and synonyms are absent, and the trigger clause 'Use to adapt behavior based on task type' is generic.	4 / 5
Distinctiveness Conflict Risk	The mode enumeration is somewhat specific, but generic mode names like 'review', 'debug', and 'implement' overlap heavily with dedicated code-review and debugging skills, creating real mis-trigger risk. Not clearly a 4 ('minor overlap risk') since these are among the most common skill trigger words.	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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	15 / 16 Passed

Repository: davila7/claude-code-templates
Path: cli-tool/components/skills/ai-research/behavioral-modes/SKILL.md
Commit: f41d583

Reviewed: 16 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.