CtrlK
BlogDocsLog inGet started
Tessl Logo

architecture

Creates Architecture Decision Records (ADRs) in MADR format and arc42 documentation. Generates plan-context.md as the context bridge to Claude Code. Use this skill when the user mentions "architecture", "ADR", "arc42", "Architecture Decision", "tech stack", "solution design", "system design", "architecture review", "plan-context", or similar. Also when requirements exist and the next step is technical structuring. This skill creates PROPOSALS. Claude Code makes the final decisions based on the real state of the codebase.

72

Quality

88%

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

81%Scale 1-5

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

This is a well-structured, project-specific architecture skill with clear phased workflows, explicit quality gates, and good progressive disclosure to external templates and references. Its main strengths are the detailed handoff ritual, mid-course error handling, and concrete naming/formatting conventions. Minor weaknesses include reliance on external templates without inline examples and slight verbosity in the handoff section.

DimensionReasoningScore

Conciseness

The skill is fairly efficient and avoids explaining concepts Claude already knows. It's dense with project-specific rules and conventions. Minor verbosity in the Handoff Ritual section (template blocks could be slightly tighter), but overall each section earns its place.

4 / 5

Actionability

Provides concrete file paths, naming conventions, line caps, specific commands (e.g., `python3 tools/github-integration/flow.py tag-phase`), and exact commit message formats. However, some references point to external templates and files without inline examples of what the ADR or plan-context content should look like, creating minor gaps in executable guidance.

4 / 5

Workflow Clarity

The workflow is clearly sequenced across four phases with explicit quality gates, a mid-course discovery protocol with a stop-and-reroute feedback loop, and a detailed handoff ritual with commit, tagging, and transition steps. The 'Mid-course requirements discovery' section provides an explicit error-recovery path for broken specs.

5 / 5

Progressive Disclosure

The skill references multiple external files (templates, team-workflow.md, graph-invariants.md, canonical-specs) at appropriate points, keeping the main file as an overview. References are one level deep and clearly signaled. Minor gap: no bundle files were provided to verify these references exist, and some references use relative paths without link formatting, which slightly reduces navigability.

4 / 5

Total

17

/

20

Passed

Description

95%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.

This is a strong skill description that clearly communicates its purpose, lists specific outputs and formats, and provides comprehensive trigger terms. The explicit 'Use this skill when...' clause with numerous natural keywords makes it highly discoverable. The added context about creating proposals vs. final decisions helps distinguish it from related skills.

DimensionReasoningScore

Specificity

Lists several specific actions: creating ADRs in MADR format, arc42 documentation, generating plan-context.md as a context bridge. Minor gaps in coverage — doesn't elaborate on what arc42 documentation entails or what plan-context.md contains.

4 / 5

Completeness

Clearly answers both 'what' (creates ADRs in MADR format, arc42 docs, generates plan-context.md) and 'when' (explicit 'Use this skill when...' clause with concrete trigger phrases, plus the additional context about when requirements exist and technical structuring is needed).

5 / 5

Trigger Term Quality

Comprehensive coverage of natural trigger terms including 'architecture', 'ADR', 'arc42', 'Architecture Decision', 'tech stack', 'solution design', 'system design', 'architecture review', 'plan-context'. These are terms users would naturally say, and synonyms/variations are well covered.

5 / 5

Distinctiveness Conflict Risk

Highly distinctive niche — ADRs, MADR format, arc42, and plan-context.md are very specific concepts unlikely to overlap with other skills. The clarification that this skill creates proposals (not final decisions) further distinguishes it from implementation-focused skills.

5 / 5

Total

19

/

20

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.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
salemaziel/digital-innovation-agents
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.