CtrlK
BlogDocsLog inGet started
Tessl Logo

architect-first

Guide for implementing the Architect-First development philosophy - perfect architecture, pragmatic execution, quality guaranteed by tests. Use this skill when starting new features, refactoring systems, or when architectural decisions are needed. Enforces non-negotiables like complete design/documentation before code, zero coupling, and validation by multiple perspectives before structural decisions.

69

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

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 process skill with clear sequenced workflows, explicit validation checkpoints, and good progressive disclosure via a real bundle of scripts, references, and templates. Its main weaknesses are content redundancy and a missing referenced template file that slightly undermine conciseness and actionability.

Suggestions

Add the missing `assets/adr-template.md` file (referenced in Resources and in the 'Making architectural changes' quick reference) or remove the references to it, so every cited path resolves.

Deduplicate the accept/reject rules: consolidate the ACCEPTABLE/REJECTED block, Stop Rules, and Will Accept/Will Reject sections into a single source of truth to reduce token cost and maintenance drift.

Tighten abstract heuristics (e.g. 'Speed via Automation: Not via shortcuts') into concrete directives, or move them to a reference file so the main body stays actionable.

DimensionReasoningScore

Conciseness

Mostly efficient and assumes Claude's intelligence, but the accept/reject rules are restated nearly verbatim across Implementation Style, Stop Rules, and Acceptance Criteria, and the mantra appears in both Portuguese and English; the body could be tightened by deduplicating these.

2 / 3

Actionability

Concrete guidance exists (named scripts, templates, checklists, numbered steps), but `assets/adr-template.md` is referenced in two places yet is not present in the bundle, and a few heuristics like "Speed via Automation: Not via shortcuts" are abstract rather than executable.

2 / 3

Workflow Clarity

The Architecture Flow (six numbered steps) and Execution Flow (five steps) are clearly sequenced with explicit validation checkpoints (multi-agent validation, gold-standard baseline, coupling validation) and STOP conditions, plus a Quick Reference recap.

3 / 3

Progressive Disclosure

SKILL.md acts as an overview with well-signaled, one-level-deep references (inline calls like "Load references/architecture-checklist.md", a Resources section listing scripts/references/assets); navigation is easy, though the referenced `assets/adr-template.md` file is missing.

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 description that clearly states capabilities, includes an explicit 'Use this skill when...' trigger with natural terms, and occupies a distinct architectural-decision niche. It uses third-person/infinitive voice consistent with the good examples and avoids first/second person.

DimensionReasoningScore

Specificity

Lists multiple concrete enforcement actions: "complete design/documentation before code, zero coupling, and validation by multiple perspectives before structural decisions," beyond merely naming the domain.

3 / 3

Completeness

Explicitly answers both what ("Guide for implementing the Architect-First development philosophy... Enforces non-negotiables...") and when via the explicit "Use this skill when..." trigger clause.

3 / 3

Trigger Term Quality

Natural phrases users actually say — "starting new features, refactoring systems, or when architectural decisions are needed" — provide good coverage of likely trigger language.

3 / 3

Distinctiveness Conflict Risk

The Architect-First / architectural-decision framing with multi-agent validation is a clear niche; the "when architectural decisions are needed" trigger narrows it away from generic coding skills.

3 / 3

Total

12

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Repository
SynkraAI/aiox-core
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.