CtrlK
BlogDocsLog inGet started
Tessl Logo

bmad-create-architecture

Deprecated — forwards to bmad-architecture (create intent).

54

Quality

60%

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

85%

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, highly actionable forwarding shim with a clear sequenced workflow and self-contained organization; its only weakness is a somewhat over-long deprecation notice that could be tightened.

DimensionReasoningScore

Conciseness

The steps themselves are efficient, but the deprecation notice in step 3 is padded — it enumerates the entire new customization surface (spine_template, run_folder_pattern, doc_standards, etc.) and full migration guidance that could be trimmed; matches 'mostly efficient but includes some unnecessary explanation or could be tightened'. Not a 1 because it avoids explaining concepts Claude already knows; not a 3 because the notice could be materially shortened.

2 / 3

Actionability

It gives a concrete executable command ("python3 {project-root}/_bmad/scripts/resolve_customization.py --skill {skill-root} --key workflow"), specific config file paths, and an explicit enumerated list of fields to forward, leaving nothing abstract. Reaches the 'fully executable commands; specific examples; copy-paste ready' anchor rather than the pseudocode/incomplete level below.

3 / 3

Workflow Clarity

A clear, linear four-step sequence (resolve customization → load config → emit notice → invoke bmad-architecture) with an explicit 'do not execute any further steps' terminator; this is a low-risk forward with no destructive or batch operation, so the missing-validation cap does not apply. The destructive/batch cap is inapplicable to a pure forward, and the simple-skills note permits a 3 for clear, well-organized sequences.

3 / 3

Progressive Disclosure

The skill is under 50 lines, self-contained, with well-organized sections (header, On Activation, numbered steps) and no external references needed; per the guidelines this qualifies for a 3 'with just well-organized sections'. No bundle files exist (references/, scripts/, assets/ absent), so there is nothing to verify or navigate.

3 / 3

Total

11

/

12

Passed

Description

35%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description accurately signals that this is a deprecated shim, but it reads as internal plumbing rather than a user-facing capability statement: it lacks natural trigger terms and any 'when to use' guidance, and it overlaps with the skill it forwards to.

Suggestions

Add a 'Use when...' clause (e.g., 'Use when existing invocations or _bmad/custom/bmad-create-architecture.toml overrides must still resolve to bmad-architecture') so the trigger is explicit rather than implied.

Replace internal jargon ('forwards to bmad-architecture (create intent)') with user-facing language that describes the practical capability, while keeping the deprecation signal.

Add a natural keyword or two that a user would actually say (e.g., 'create architecture', 'BMad architecture') to improve trigger_term_quality from technical jargon toward natural terms.

DimensionReasoningScore

Specificity

The description names a concrete action ("forwards to bmad-architecture") and its domain, but offers only a single action rather than a list of multiple specific capabilities, matching the 'names domain and some actions, but not comprehensive' anchor.

2 / 3

Completeness

It conveys a partial 'what' (forwards to bmad-architecture with create intent) but lacks any 'Use when...' trigger guidance, so per the guidelines completeness is capped at 2 ('has what, but when is missing or only implied').

2 / 3

Trigger Term Quality

Terms like "Deprecated", "forwards", and "create intent" are internal/technical jargon a user would not naturally say; there are no natural user-facing keywords, matching the 'no natural keywords; technical jargon' anchor.

1 / 3

Distinctiveness Conflict Risk

It targets a specific niche (bmad architecture creation) but is explicitly defined as overlapping with bmad-architecture, the very skill it forwards to, matching 'somewhat specific but could still overlap with similar skills'.

2 / 3

Total

7

/

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
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.