CtrlK
BlogDocsLog inGet started
Tessl Logo

034-architecture-design-exploration

Use when a sanitized issue summary, requirement summary, or design brief needs technical design exploration before creating ADRs, specifications, or implementation plans. This skill inspects repository context, clarifies material ambiguity, compares feasible approaches and trade-offs, recommends a direction, obtains approval, and identifies ADR candidates. This should trigger for requests such as Explore a design; Compare implementation approaches; Recommend an architecture direction; Clarify technical options before planning. Part of Plinth Toolkit

69

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

70%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, interactive design-exploration skill with a clear sequenced workflow, explicit gates, and clean one-level progressive disclosure. Its main weakness is redundancy between the coverage list and the workflow, plus a lack of concrete examples to make the guidance fully actionable.

Suggestions

Remove or condense the 'What is covered in this Skill?' bullet list, since it duplicates the Workflow steps and adds token cost without new information.

Add a short concrete example — e.g., a compact sample trade-off table or a sample approved-direction outcome — so the comparison and hand-off steps are exemplified rather than only described.

Clarify the Step 2 'focused questions' guidance with a brief example of a material-vs-non-blocking question to anchor when to pause for clarification.

DimensionReasoningScore

Conciseness

Mostly efficient and free of concept-over-explanation, but the 'What is covered in this Skill?' bullet list substantially restates the Workflow steps (context inspection, ambiguity clarification, approach comparison, recommendation/approval, ADR candidates), adding redundancy that could be trimmed.

2 / 3

Actionability

Concrete guidance exists — explicit MUST/MUST NOT/TRUST GATE constraints, a numbered workflow, and named comparison dimensions (complexity, maintainability, performance, security, testability, migration, operational cost) — but it describes what to produce rather than exemplifying it, with no sample trade-off table or example outcome to anchor execution.

2 / 3

Workflow Clarity

Five steps are clearly sequenced with explicit checkpoints: the Step 1 TRUST GATE and the Step 5 'approve or revise' loop provide validation/feedback, appropriate for a non-destructive interactive design skill.

3 / 3

Progressive Disclosure

SKILL.md is a concise overview pointing to one clearly signaled, one-level-deep reference (references/034-architecture-design-exploration.md, verified to exist), with content appropriately split and easy to navigate.

3 / 3

Total

10

/

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.

A strong, third-person description with explicit trigger guidance, concrete capability listing, and a well-scoped niche. The trailing 'Part of Plinth Toolkit' is minor metadata fluff but does not weaken the trigger or specificity.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'inspects repository context, clarifies material ambiguity, compares feasible approaches and trade-offs, recommends a direction, obtains approval, and identifies ADR candidates' — matching the multiple-specific-actions anchor.

3 / 3

Completeness

Explicitly answers both what (inspects, clarifies, compares, recommends, approves, identifies ADRs) and when via a clear 'Use when...' clause plus 'This should trigger for requests such as...', matching the both-what-and-when anchor.

3 / 3

Trigger Term Quality

Natural trigger phrases a user would say are present: 'Explore a design; Compare implementation approaches; Recommend an architecture direction; Clarify technical options before planning', giving good coverage of likely phrasings.

3 / 3

Distinctiveness Conflict Risk

The pre-ADR/spec design-exploration niche with sanitized-summary inputs is a clear, distinct framing unlikely to trigger the wrong skill; it is not generic enough to conflict broadly.

3 / 3

Total

12

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
jabrena/plinth
Reviewed

Table of Contents

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.