behavioral-modes

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

Quality

56%

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

67%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 structured and lean: each mode gets concrete trigger conditions, behavior rules, and output templates, and the detection table makes mode selection unambiguous. Its weaknesses are an empty 'Combining Modes' section and a speculative multi-agent section that names patterns without actionable guidance.

Suggestions

Fill in or delete the empty 'Combining Modes' section — a heading with no content is the most visible gap in the skill.

Either make the multi-agent patterns actionable (e.g., what EXPLORE's 'discovery-report.json' should contain, when to enter the PEC cycle) or move them out of the skill.

Replace the generic 'When to Use' boilerplate ('applicable to execute the workflow or actions described in the overview') with the actual trigger situations from the mode-detection table.

Dimension	Reasoning	Score
Conciseness	The body is efficient — terse behavior bullets and compact output templates, with no explanation of concepts Claude already knows. Minor padding keeps it from a 5: the IMPLEMENT 'NOT:' anti-example, the '(2025)' framing on the multi-agent section, and one-line sketches like 'Mental Model Sync' could be trimmed.	4 / 5
Actionability	The six core modes each have concrete when-to-use criteria, behavior bullets, and copy-paste output templates, but the multi-agent section ('Socratic questioning, deep-dive code reading, dependency mapping') only describes rather than instructs and the 'Combining Modes' section is empty — concrete guidance that is incomplete in key places. Not a 4 because an entire section of the skill lacks executable guidance.	3 / 5
Workflow Clarity	Mode selection is clearly sequenced: a trigger-keyword detection table routes to per-mode behavior and output templates, plus explicit manual switching commands. Not a 5 because the PEC mode-transition cycle is loosely specified and the empty 'Combining Modes' section leaves sequencing across modes unaddressed.	4 / 5
Progressive Disclosure	A single-file skill with no bundle files, organized with clear per-mode section headers and a detection table, so nothing is buried and no nested references exist. Not a 5 because the trailing sections (empty 'Combining Modes', boilerplate 'When to Use') show minor organization gaps.	4 / 5
	Total	15 / 20 Passed

Description

46%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 lists the mode names, which gives it some concreteness, but it lacks explicit 'use when' trigger guidance and describes its purpose in generic terms that would match almost any task. Its trigger words ('review', 'debug', 'implement') create real conflict risk with dedicated single-task skills.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks to brainstorm ideas, review or audit code, debug an error, learn a concept, or prepare a release' — this would lift completeness and trigger-term quality.

Replace the generic 'adapt behavior based on task type' with what the skill concretely does, e.g. 'Switches AI response style, output format, and questioning behavior between seven named modes'.

Distinguish the skill from single-task skills (debugging, code review) by scoping it to tasks where the working mode itself matters, e.g. 'when the task type or collaboration style should change how the AI works'.

Dimension	Reasoning	Score
Specificity	The description names the domain and enumerates seven concrete mode names ('brainstorm, implement, debug, review, teach, ship, orchestrate') but the only stated action is the generic 'adapt behavior based on task type' — comparable to 'Processes PDF files and extracts content'. It is not a 4 because no specific per-mode actions are described.	3 / 5
Completeness	The 'what' is stated (defines operational modes that adapt behavior) but the 'when' is only weakly implied: 'Use to adapt behavior based on task type' is a purpose clause, not explicit trigger guidance, which caps completeness at 3. Not a 4 because there is no 'Use when...' clause with concrete trigger situations.	3 / 5
Trigger Term Quality	'brainstorm', 'debug', 'review', and 'teach' are terms users naturally say, but the description is a bare parenthetical list with no trigger phrasing and misses common variations like 'troubleshoot', 'explain', or 'deploy'. Not a 4 because keyword coverage stops at the mode names themselves.	3 / 5
Distinctiveness Conflict Risk	'Adapt behavior based on task type' applies to virtually any task, and mode names like 'review', 'debug', and 'implement' overlap heavily with dedicated skills for those tasks — very broad with high overlap risk. Not a 3 because nothing in the description narrows its scope.	2 / 5
	Total	11 / 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/agentic-awesome-skills
Path: skills/behavioral-modes/SKILL.md
Commit: 7b534bc

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.