CtrlK
BlogDocsLog inGet started
Tessl Logo

bmad-create-architecture

Deprecated — forwards to bmad-architecture (create intent)

45

Quality

48%

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 ./src/bmm-skills/v6-shims/bmad-create-architecture/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%Weight 40%Scale 1-5

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

The body is a well-structured, actionable deprecation shim with a clear numbered workflow and a concrete handoff to bmad-architecture. Its main weakness is modest verbosity in the deprecation notice and legacy-field listing rather than any structural problem.

DimensionReasoningScore

Conciseness

The body is mostly efficient with concrete commands and a clear forwarding sequence, but the embedded deprecation notice and the duplicated listing of legacy fields add some padding that could be tightened, matching 'mostly efficient but includes some unnecessary explanation'.

3 / 5

Actionability

It provides a concrete executable command (uv run resolve_customization.py with explicit args) and precise forwarding context to pass to bmad-architecture, leaving only minor gaps; it is mostly executable guidance.

4 / 5

Workflow Clarity

The four numbered activation steps form a clear sequence ending in an explicit handoff ('Do not execute any further steps in this shim'), with most checkpoints present; this is a non-destructive forwarding skill so the validation-cap exceptions do not apply.

4 / 5

Progressive Disclosure

This is a short single-purpose shim under 50 lines with no need for external references; its well-organized sections (On Activation, numbered steps) satisfy the simple-skill exception for a top progressive_disclosure score.

5 / 5

Total

16

/

20

Passed

Description

25%Weight 40%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 deprecation-shim description that conveys its forwarding purpose but is too terse to function as effective trigger guidance. It lacks natural user keywords and any explicit 'use when' clause, so it would rarely surface on its own when a user actually needs it.

Suggestions

Add an explicit 'Use when...' clause stating when this shim should be selected (e.g., legacy invocations or override files that reference bmad-create-architecture by name).

Include natural trigger keywords users might say, such as 'architecture', 'create architecture', or 'BMAD architecture', rather than only the technical term 'create intent'.

Briefly state the concrete action the skill performs in third person (e.g., 'Forwards create-architecture requests to bmad-architecture') to raise specificity above the minimal-action level.

DimensionReasoningScore

Specificity

The description names the domain ('forwards to bmad-architecture') and one action ('forwards') but lists no concrete capabilities of the skill itself, matching the 'names the domain but actions are minimal' anchor rather than the 1-2 concrete actions needed for a 3.

2 / 5

Completeness

It gives a vague 'what' (forwards to bmad-architecture) and entirely omits any 'when/use' trigger guidance; per the rubric a missing 'Use when...' clause caps completeness at 3, and here the 'what' is also only weakly stated, landing at 2.

2 / 5

Trigger Term Quality

The terms present ('Deprecated', 'forwards', 'bmad-architecture', 'create intent') are technical jargon a user would not naturally utter when needing this skill, matching the 'only technical jargon' anchor.

1 / 5

Distinctiveness Conflict Risk

The named, deprecated shim with a specific create-intent forwarding target is clearly distinct from unrelated skills with only minor overlap risk against its successor 'bmad-architecture', matching the 'mostly distinct' anchor.

4 / 5

Total

9

/

20

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

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository
bmad-code-org/BMAD-METHOD
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.