CtrlK
BlogDocsLog inGet started
Tessl Logo

bmad-agent-architect

System architect and technical design leader. Use when the user asks to talk to Winston or requests the architect

61

Quality

73%

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 ./skills/bmad-agent-architect/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

88%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 content is a tightly written, fully executable activation workflow with clear sequencing, explicit fallbacks, and validation checkpoints. Its only minor gaps are a few flavor sentences and the absence of bundled reference files that would let progressive disclosure reach its top anchor.

DimensionReasoningScore

Conciseness

The body is lean and procedural, listing concrete activation steps without explaining concepts Claude already knows, and a Conventions section that defines placeholders tersely. Minor flavor lines ('Fully embody this persona so the user gets the best experience') could be trimmed, keeping it just below score 5.

4 / 5

Actionability

It provides fully executable commands with concrete arguments, e.g. 'uv run {project-root}/_bmad/scripts/resolve_customization.py --skill {skill-root} --project-root {project-root} --key agent', and placeholders are precisely defined in the Conventions section so the steps are copy-paste ready.

5 / 5

Workflow Clarity

Activation is an explicitly numbered 8-step sequence with a feedback loop ('If the script fails, resolve the agent block yourself...'), explicit checkpoints ('Stop and wait for input'), and a confirmation gate ('confirm every entry was executed in order before proceeding'). This matches the anchor for clear sequence with explicit validation and error-recovery loops.

5 / 5

Progressive Disclosure

The body is a single well-organized file with clear section headers (Overview, Conventions, On Activation with 8 steps) and one-level path references to project files like customize.toml, with no nested multi-level reference chains. It stops short of score 5 only because there are no clearly signaled bundled reference files to split detail into.

4 / 5

Total

18

/

20

Passed

Description

57%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.

The description is third-person, concise, and provides an explicit 'Use when' trigger tied to a distinctive persona, which is good. Its weakness is specificity: it labels the role without listing concrete architectural actions the agent performs.

Suggestions

Replace the role label with 2-3 concrete actions the architect performs (e.g., 'designs system architecture, produces ADRs, maps requirements to technical trade-offs').

Broaden the trigger clause beyond the Winston persona to natural phrases like 'architecture design', 'technical design', or 'system design' that users would say without knowing the persona name.

Add common synonyms/variants ('architect', 'system design', 'technical design lead') to improve trigger term coverage.

DimensionReasoningScore

Specificity

The description names the domain ('System architect and technical design leader') but lists no concrete actions, functioning as a role label rather than a capability list. It fits the anchor 'names the domain but actions are minimal or generic' and falls short of score 3, which requires 1-2 concrete actions.

2 / 5

Completeness

It states a clear 'what' (system architect / technical design leader) and an explicit 'when' clause ('Use when the user asks to talk to Winston or requests the architect'), satisfying both halves. The 'when' is somewhat narrow, so it stops short of score 5's comprehensive concrete trigger phrases.

4 / 5

Trigger Term Quality

Phrases like 'asks to talk to Winston' and 'requests the architect' are natural triggers users might say, but coverage is limited to those two and lacks synonyms or broader variations. It does not reach score 4's 'good keyword coverage' threshold.

3 / 5

Distinctiveness Conflict Risk

The 'Winston' persona name and 'architect' niche make it largely distinct from generic skills with minimal conflict risk. It is not quite score 5 because 'the architect' alone could marginally overlap with adjacent design/planning skills.

4 / 5

Total

13

/

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

referenced_paths_exist

Referenced path issues: 1 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.