dialectic

Co-create an explicitly accepted, uncompromising destination before planning or implementation. Use when the user wants to discover what they actually want, asks for an uncompromising vision, wants iterative synthesis and pushback, is exploring an architecture or product model before a plan exists, or says to use dialectic. Do not use for interrogating an existing plan, comparing one bounded implementation choice, or ordinary implementation with a settled destination.

Quality

92%

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

Quality

Content

85%

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 highly actionable for a meta-skill, with clear sequencing, an explicit acceptance-gate validation checkpoint, and lean templates. The only weak dimension is conciseness, where some framing prose could be trimmed.

Suggestions

Tighten the prose in 'Establish The Frame' and 'Read Reactions As Directional Data' to rely more on the existing templates and cut explanatory framing.

Consider collapsing the 'Transition' code block into a short prose list since it restates handoff destinations already implied by the Compose With section.

Merge the Completion Check checklist into the Acceptance Gate section to reduce redundancy between the two end-of-loop checkpoints.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and template-driven without explaining basics Claude already knows, but ~190 lines of prose around the templates could be tightened in places (e.g., framing sentences in 'Establish The Frame' and 'Read Reactions As Directional Data'), so it sits at 'mostly efficient but could be tightened' rather than 'every token earns its place'.	2 / 3
Actionability	Provides concrete, copy-paste-ready frameworks — the positive-synthesis template, the preserve/reject/intensify/resolve reaction template, the acceptance-gate artifact template, and the completion checklist — which is specific actionable guidance for an instruction-only skill; absence of code is appropriate here.	3 / 3
Workflow Clarity	A clear sequenced loop (synthesis -> reaction -> revised synthesis -> explicit acceptance), a numbered 3-step revise-and-apply-pressure process, and an explicit Acceptance Gate validation checkpoint with a feedback loop (caveats start another round) plus a completion checklist match the 'clear sequence with explicit validation steps' anchor.	3 / 3
Progressive Disclosure	No bundle files exist, so scoring is on the body's organization; it is a single well-structured file with clear headers and clearly signaled one-level cross-skill links (one-sentence-test, greenfield-clean-breaks, grill-me, ui-design) and no nested/deep references, fitting the 'well-organized sections' allowance for self-contained skills.	3 / 3
	Total	11 / 12 Passed

Description

100%

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 is strong: it states concrete actions, gives natural trigger phrasings, explicitly answers both what and when, and includes a negative-trigger clause that sharply distinguishes it from adjacent skills. No changes needed.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions specific to the skill ('Co-create an explicitly accepted, uncompromising destination', 'discover what they actually want', 'iterative synthesis and pushback', 'exploring an architecture or product model'), matching the 'lists multiple specific concrete actions' anchor rather than the single-domain 2 anchor.	3 / 3
Completeness	Explicitly answers both what ('Co-create an explicitly accepted, uncompromising destination before planning or implementation') and when (a full 'Use when...' clause plus a 'Do not use for...' exclusion), matching the 3 anchor for both what AND when with explicit triggers.	3 / 3
Trigger Term Quality	Covers natural user phrasings ('wants to discover what they actually want', 'asks for an uncompromising vision', 'exploring an architecture or product model', 'says to use dialectic'), giving good coverage of terms a user would actually say rather than only jargon.	3 / 3
Distinctiveness Conflict Risk	A clear niche (convergence before a plan exists) plus an explicit 'Do not use for interrogating an existing plan, comparing one bounded implementation choice, or ordinary implementation' clause makes it unlikely to trigger for the wrong skill.	3 / 3
	Total	12 / 12 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: 4 suspicious	Warning

	Total	15 / 16 Passed

Repository: EpicenterHQ/epicenter
Path: .agents/skills/dialectic/SKILL.md
Commit: cb12bcc

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.