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.

53

Quality

59%

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 a well-structured, sequenced architecture workflow with explicit validation and recovery steps, leaning appropriately on referenced resource files. Its main weaknesses are moderate redundancy and deferred output templates/examples that are not bundled, which limits in-body actionability.

Suggestions

De-duplicate the References section (remove the repeated narrative + bullet listing) and consolidate overlapping 'When to use', 'Intent signature', and 'Control-flow features' wording to tighten conciseness.

Inline a minimal ADR/output template or one concrete example so the skill is actionable without requiring the unbundled `resources/output-templates.md`.

Either bundle the referenced `resources/*.md` and `../_shared/core/*.md` files or note they are external, so progressive disclosure navigates to real materials.

DimensionReasoningScore

Conciseness

The body is dense and assumes Claude's architectural knowledge (no padding explaining ATAM/CBAM), but contains redundancy such as the References section listing resources twice (narrative + bullet list) and overlapping 'When to use'/'Intent signature'/'Control-flow features' content, fitting the 'mostly efficient but could be tightened' anchor rather than the 4 anchor's only minor trims.

3 / 5

Actionability

It gives a concrete process (named modes, transitions, guardrails, an `rg` search snippet), but the actual artifact templates and examples are deferred to unbundled `resources/*.md` files, leaving the in-body guidance with key output details missing; this matches the 'some concrete guidance but incomplete' anchor rather than the 4 anchor's mostly-executable guidance.

3 / 5

Workflow Clarity

A clear sequence is present (Entry -> Scenes PREPARE/ACQUIRE/REASON/VERIFY/FINALIZE -> Transitions -> Failure and recovery -> Exit) with an explicit VERIFY checkpoint and recovery feedback loops, fitting the 'clear sequence with most checkpoints' anchor; it is not a 5 because the checklist for this complex process is referenced externally rather than embedded.

4 / 5

Progressive Disclosure

Content is well organized into signaled sections with one-level-deep references to `resources/*.md` and `../_shared/core/*.md`, matching the 'good structure; references mostly clear' anchor; the minor gap is the double-listed References section and that referenced files are not actually bundled here.

4 / 5

Total

14

/

20

Passed

Description

58%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 conveys a clear, fairly specific capability set for an architecture specialist, but omits an explicit 'Use when...' trigger clause and leans on technical terminology over natural user phrasing. Adding concrete trigger phrases and synonyms would raise both completeness and trigger-term quality.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user asks about system architecture, module/service boundaries, ADRs, design tradeoffs, or architecture pain like change amplification and hidden dependencies.'

Add natural synonyms users actually say ('refactoring', 'tech debt', 'design review', 'service decomposition') to broaden trigger-term coverage.

Briefly signal the boundary against sibling skills (e.g. 'not for visual design or Terraform delivery') to sharpen distinctiveness within the description.

DimensionReasoningScore

Specificity

Names the domain and several concrete capability areas ('software/system design, module and service boundaries, tradeoff analysis, and stakeholder synthesis') plus named methods, matching the 'several specific actions; minor gaps' anchor; not a 5 because the actions are capability categories rather than a fully comprehensive enumeration of concrete operations.

4 / 5

Completeness

It clearly states what the skill does ('Architecture specialist for...') but provides no explicit 'Use when...' trigger clause, so per the guideline a missing trigger caps completeness at 3 ('clear what but when is missing or only weakly implied').

3 / 5

Trigger Term Quality

Relevant terms like 'architecture', 'system design', and 'tradeoff analysis' are present but lean technical; common natural variations a user would say (e.g. 'refactoring', 'tech debt', 'design review') are missing, fitting the 'some relevant keywords but missing variations' anchor rather than the 4 anchor's fuller coverage.

3 / 5

Distinctiveness Conflict Risk

The architecture/system-design niche is mostly distinct with minor overlap risk against closely related skills (oma-design, oma-pm); the description itself does not name those boundaries (the body does), so it falls short of the 5 anchor's clear distinct triggers.

4 / 5

Total

14

/

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.

Validation16 / 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.