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.

58

Quality

66%

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 ./.agents/skills/oma-architecture/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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 well-structured orchestration skill: efficient, actionable, with a clearly sequenced workflow that includes verification and recovery steps, and it appropriately defers detail to one-level-deep resource files. Main weakness is redundancy between the Dependencies and References sections and somewhat abstract validation wording.

Suggestions

Collapse the Dependencies and References sections into a single deduplicated reference list to remove repetition and tighten the token budget.

Make the VERIFY scene and validation guardrail concrete (e.g., name the checklist items or the exact `resources/checklist.md` checks) rather than 'check assumptions and validation steps'.

Add one short worked example of selecting a mode (e.g., a vague-pain input -> Diagnostic Mode -> Design-Twice) to ground the Method Selection Summary.

DimensionReasoningScore

Conciseness

The body is mostly efficient, assumes Claude's competence, and uses compact tables/lists rather than explaining concepts Claude already knows; minor redundancy between the Dependencies and References sections could be trimmed.

4 / 5

Actionability

Provides concrete executable guidance — specific serena MCP calls (get_symbols_overview, find_symbol), bash rg/ls commands, a YAML outputs block, and a method-selection summary — with only minor gaps where the real execution lives in referenced resource files.

4 / 5

Workflow Clarity

Clear sequenced workflow (Entry -> Scenes PREPARE/ACQUIRE/REASON/VERIFY/FINALIZE -> Exit) with an explicit VERIFY step, Failure-and-recovery feedback, and a checklist reference; validation checkpoints are present but stated somewhat abstractly rather than as concrete checks.

4 / 5

Progressive Disclosure

The SKILL.md acts as an overview with well-signaled, one-level-deep references to resources/ and _shared/core/ files and a clear References section; organization is good with minor redundancy and no bundle files present to verify further.

4 / 5

Total

16

/

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 clearly conveys the skill's purpose and lists concrete methods, but it omits any explicit "Use when..." trigger guidance and leans on method jargon (ATAM/CBAM) that users would not naturally voice, capping completeness and trigger-term quality.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers (e.g., 'Use when the user asks about system design, service boundaries, architecture tradeoffs, or writing an ADR').

Lead with plain-language trigger phrases users actually say (architecture, system design, module/service boundaries, ADRs) and demote ATAM/CBAM/diagnostic-routing jargon or move it after the triggers.

Include common synonyms/file cues (architecture decisions, ADRs, ownership boundaries, API contracts) to improve trigger coverage and distinctiveness.

DimensionReasoningScore

Specificity

Lists several specific actions/methods ("tradeoff analysis", "stakeholder synthesis", "diagnostic routing", "design-twice comparison", "ATAM-style risk analysis", "CBAM-style prioritization", "ADR-style decision records") with broad coverage, though they lean toward method names rather than user-facing concrete actions, leaving minor gaps.

4 / 5

Completeness

The "what" is clearly stated (architecture specialist for design, boundaries, tradeoffs, stakeholder synthesis) but there is no "Use when..." clause or equivalent explicit trigger guidance, so per the rubric completeness is capped at 3.

3 / 5

Trigger Term Quality

Includes some natural keywords ("architecture", "software/system design", "module and service boundaries", "tradeoff analysis") but pads heavily with jargon users rarely say ("ATAM-style", "CBAM-style", "diagnostic routing", "design-twice comparison"), missing common variations and synonyms.

3 / 5

Distinctiveness Conflict Risk

The architecture niche is mostly distinct from sibling skills (design, pm, infra, debug, qa) with only minor overlap risk against system-design vs feature-planning domains.

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.