CtrlK
BlogDocsLog inGet started
Tessl Logo

create-architecture

Guided, section-by-section authoring of the master architecture document for the game. Reads all GDDs, the systems index, existing ADRs, and the engine reference library to produce a complete architecture blueprint before any code is written. Engine-version-aware: flags knowledge gaps and validates decisions against the pinned engine version.

60

Quality

72%

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

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/create-architecture/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

77%

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

A highly actionable, well-sequenced workflow with strong validation checkpoints, but it is long and monolithic, with reusable templates and protocol guidance inlined rather than split into reference files.

Suggestions

Move the Collaborative Protocol and the Phase 8 handoff/output templates into a reference file (e.g. references/handoff-template.md) and link to them, trimming SKILL.md to an overview.

Tighten repeated per-phase approval wording into a single stated convention rather than restating 'Get user approval before writing' at each phase.

Pull the ADR-audit and traceability table templates into a reference doc to reduce inline bulk while keeping the workflow steps in SKILL.md.

DimensionReasoningScore

Conciseness

The body is mostly procedural and earns its length, but at ~460 lines it could be tightened — repeated approval phrasing, the standalone Collaborative Protocol, and inline templates that duplicate gate definitions elsewhere keep it from the lean anchor.

2 / 3

Actionability

Provides concrete file paths, exact slash-commands, named gates (TD-ARCHITECTURE, LP-FEASIBILITY), AskUserQuestion option lists, and copy-paste-ready output templates — fully executable guidance.

3 / 3

Workflow Clarity

A clearly sequenced Phase 0–8 flow with explicit approval checkpoints at each phase, a knowledge-gap validation gate (0d), ADR audit feedback loops, and a traceability coverage check — matching the 'clear sequence with explicit validation steps' anchor.

3 / 3

Progressive Disclosure

Well-organized into phases and correctly points to director-gates.md for gate patterns, but the skill is a single monolithic ~460-line file with no bundle files; templates and gate criteria that could be split out remain inline.

2 / 3

Total

10

/

12

Passed

Description

67%

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 specific, well-scoped description that concretely lists what the skill does and is clearly distinguishable, but it omits an explicit 'Use when...' trigger clause and leans somewhat on domain jargon.

Suggestions

Add an explicit 'Use when ...' clause naming natural triggers, e.g. 'Use when creating or refreshing the master architecture document from approved GDDs, before sprint planning or code.'

Soften internal jargon (e.g. 'systems index', 'engine reference library') or pair it with plain terms a user would actually say.

DimensionReasoningScore

Specificity

Names multiple concrete actions — 'section-by-section authoring', 'Reads all GDDs, the systems index, existing ADRs, and the engine reference library', 'flags knowledge gaps and validates decisions against the pinned engine version' — matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

Answers 'what' thoroughly but provides no explicit 'Use when...' or equivalent trigger guidance for 'when Claude should use it', which per the guidelines caps completeness at 2.

2 / 3

Trigger Term Quality

Contains relevant domain terms ('architecture document', 'blueprint', 'GDDs', 'ADRs') but leans on jargon ('systems index', 'engine reference library') and lacks breadth of the natural phrasings a user would say, fitting 'some relevant keywords but missing common variations'.

2 / 3

Distinctiveness Conflict Risk

Occupies a clear niche — 'the master architecture document for the game ... before any code is written' — and its engine-version-aware framing makes it unlikely to trigger for the wrong sibling skill.

3 / 3

Total

10

/

12

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

14

/

16

Passed

Repository
Donchitos/Claude-Code-Game-Studios
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.