dialectic

Work out an unsettled idea together through concrete attempts to articulate and express it. Use when the user asks for a dialectic, wants to explore what a skill or workflow should do, is finding a direction for writing, wants to judge a proposed change, wants to think through an uncertain model or decision, or needs help articulating a thought they cannot quite express. Do not use for routine execution of a settled request, a standalone explanation of settled material, or a code review.

Quality

79%

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/dialectic/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.

A well-structured, instruction-only skill body: concrete, domain-specific guidance with a clear three-phase flow and a properly externalized example-conversations reference. The main costs are repetition across sections and an abstract opening section that dilutes the otherwise actionable directives.

Suggestions

Merge the duplicated 'recommend a direction' guidance and trim abstract meta-statements (e.g., 'Economical commentary does not require a short expression') to lift conciseness.

Replace the abstract opening section's phrases ('Give the thought a useful shape') with the concrete criteria already used later in the body.

Verify or inline-justify the ../writing-voice/SKILL.md sibling-skill link so navigation does not depend on an unshipped file.

Dimension	Reasoning	Score
Conciseness	The body is entirely skill-specific with no padding of concepts Claude already knows, but guidance repeats across sections ('Recommend a direction when you have grounds' appears twice) and includes abstract restatements like 'Economical commentary does not require a short expression' that could be tightened.	3 / 5
Actionability	Concrete, checkable directives dominate: 'Before showing an exact proposed diff, read the current code and affected callers', 'for a blog, render the proposed writing in the actual site and show screenshots', 'label hypothetical code as a sketch'. The opening section ('Give the thought a useful shape', 'Give each part useful work') stays more abstract.	4 / 5
Workflow Clarity	The phases are clearly sequenced — articulate/express, make the model and its consequences judgeable, then learn from the response — with explicit checkpoints such as 'Ask when missing information would make the attempt misleading'. It lacks an explicit numbered sequence or a validate/retry feedback loop, keeping it below the top anchor.	4 / 5
Progressive Disclosure	The 14KB example material is appropriately split into references/conversations.md, which exists, is well-signaled ('Read the example conversations when developing writing, an API, a skill, or a website'), and is one level deep. The cross-skill link ../writing-voice/SKILL.md is not verifiable within this bundle layout, a minor navigation gap.	4 / 5
	Total	15 / 20 Passed

Description

83%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.

A strong description: it explicitly states what the skill does, gives multiple natural trigger phrases for when to use it, and adds do-not-use exclusions that disambiguate it from code review and routine execution. Minor room to grow in trigger synonym coverage and sharpening the more abstract phrases.

Suggestions

Add common user synonyms such as 'brainstorm', 'talk through an idea', or 'work out an approach' to the trigger list.

Tighten the abstract opener ('Work out an unsettled idea together') toward a more concrete capability statement.

Dimension	Reasoning	Score
Specificity	Names several concrete actions — 'explore what a skill or workflow should do', 'finding a direction for writing', 'judge a proposed change', 'think through an uncertain model or decision' — though the framing 'Work out an unsettled idea together' is abstract, leaving minor gaps versus the comprehensive anchor.	4 / 5
Completeness	Explicitly answers both 'what' ('Work out an unsettled idea together through concrete attempts to articulate and express it') and 'when' ('Use when the user asks for a dialectic, wants to explore...'), plus explicit 'Do not use for' exclusions with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural trigger phrases like 'asks for a dialectic', 'finding a direction for writing', and 'think through an uncertain model or decision' would plausibly be said by users, but common synonyms such as 'brainstorm' or 'talk it through' are missing.	4 / 5
Distinctiveness Conflict Risk	A clear niche with explicit negative triggers ('Do not use for... a code review') reduces conflict risk, but broader phrases like 'think through an uncertain model or decision' and 'finding a direction for writing' overlap with general planning and writing skills.	4 / 5
	Total	17 / 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
relative_links	Relative link issues: 1 suspicious	Warning

	Total	15 / 16 Passed

Repository: EpicenterHQ/epicenter
Path: .agents/skills/dialectic/SKILL.md
Commit: f9441c8

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.