CtrlK
BlogDocsLog inGet started
Tessl Logo

oma-architecture

Architecture specialist for software/system design, module and service boundaries, tradeoff analysis, and stakeholder synthesis. Uses context-aware methods such as diagnostic routing, design-twice comparison, ATAM-style risk analysis, CBAM-style prioritization, and ADR-style decision records.

56

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./benchmarks/runs/oma/.agents/skills/oma-architecture/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

60%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 well-structured with a coherent scene-based workflow and clear routing to resource files, but it reads more like a routing specification than an operational skill: concrete executable guidance is thin, and the resource listing is repeated three times. Consolidating references and inlining a minimal worked example of one method would materially improve it.

Suggestions

Consolidate the Dependencies, References-prose, and References-bullet lists into a single deduplicated reference list to remove two redundant enumerations of the same files.

Inline a minimal worked example of one method (e.g., a short ADR template or a two-option design-twice comparison skeleton) so the skill is actionable even before resources/ files are opened.

Make VERIFY operational: replace 'check assumptions, validation steps' with a concrete check (e.g., 'run resources/checklist.md and confirm every recommendation states assumptions, tradeoffs, risks, and validation steps').

DimensionReasoningScore

Conciseness

Mostly terse and free of explanations of known concepts, but the resource file list is repeated three times (Dependencies, References prose, References bullets), and spec-metadata tables (SSL primitives, Resource scope) add tokens without actionable value. Not anchor 4 because the duplication is a clear, removable inefficiency; not anchor 2 because there is no padded conceptual explanation.

3 / 5

Actionability

Concrete executable content is limited to two rg commands and a method-selection summary; the actual analytical work ('Use ATAM-style analysis', 'compare at least two genuinely different options') is direction, not steps, and the detailed method content is deferred to resources/ files not present in the bundle. Not anchor 4 because the core instructions lack concrete, copy-paste-ready guidance.

3 / 5

Workflow Clarity

A clear five-scene sequence (PREPARE→ACQUIRE→REASON→VERIFY→FINALIZE) with explicit Transitions, a Failure-and-recovery section, and success/partial-success exit criteria; VERIFY acts as a checkpoint. Not anchor 5 because validation is named ('check assumptions, validation steps') rather than operationalized — no concrete verify commands or inline checklist steps.

4 / 5

Progressive Disclosure

References are clearly signaled and one level deep (resources/*.md plus ../_shared/core/*.md), with the body staying at overview level. Not anchor 5 because the reference list is duplicated across three sections and scheduling metadata (intent signature, SSL primitive table) is inlined where it could live in a resource file; the referenced bundle files are also absent, so the structure cannot be fully verified.

4 / 5

Total

14

/

20

Passed

Description

66%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.

A specific, third-person description that clearly communicates what the skill does and names its methods, but it omits any 'Use when...' trigger guidance, which caps its completeness and leaves invocation conditions implicit. Adding explicit trigger phrases and a few more natural synonyms would lift it substantially.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user asks about architecture, system design, service boundaries, ADRs, or design tradeoffs, or reports pain like change amplification or unclear ownership.'

Add natural synonyms users actually say — 'microservices', 'design review', 'refactor prioritization', 'monolith vs. services' — to broaden trigger coverage beyond method jargon.

Tighten the opener from 'Architecture specialist for software/system design' to action verbs ('Analyzes and documents software architecture decisions...') to sharpen the 'what'.

DimensionReasoningScore

Specificity

Lists several concrete actions ('tradeoff analysis', 'stakeholder synthesis', 'module and service boundaries') plus five named methods (diagnostic routing, design-twice, ATAM, CBAM, ADR). It falls short of anchor 5 because the opening 'Architecture specialist for software/system design' names a role rather than actions, but clearly exceeds anchor 3's '1-2 concrete actions'.

4 / 5

Completeness

The 'what' is clear (architecture analysis, tradeoffs, decision records), but there is no 'Use when...' clause or equivalent explicit trigger guidance, capping completeness at 3 per the judging guidelines. Not anchor 4 because the 'when' is entirely absent rather than merely imprecise.

3 / 5

Trigger Term Quality

Includes natural terms users would say ('architecture', 'system design', 'tradeoff', 'ADR', 'service boundaries'), but misses common variations like 'microservices', 'design review', or 'refactor prioritization', and leans on jargon-leaning method names (ATAM-style, CBAM-style). Not anchor 3 since coverage is genuinely good, not partial.

4 / 5

Distinctiveness Conflict Risk

Clear niche (architecture decisions, ADRs, tradeoff analysis) with distinct triggers that would not fire for unrelated skills; minor overlap risk with 'software/system design' phrasing versus visual-design or PM skills. Not anchor 5 because 'system design' is broad enough to occasionally collide with a general design skill.

4 / 5

Total

15

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
first-fluke/oh-my-agent
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.