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.

60

Quality

69%

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

67%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, actionable, and sequenced with validation checkpoints, supported by concrete commands and tool primitives. Its main weakness is redundancy between the Dependencies and References sections and slightly implicit feedback loops.

Suggestions

Merge the Dependencies and References sections into a single resource list to remove the duplicated file references and tighten token usage.

Make the validation feedback loop explicit (e.g., 'If the checklist fails: fix assumptions/evidence and re-run VERIFY before finalizing') to push workflow clarity higher.

Format resource references as markdown links and group them (workflow / methods / templates / shared) so navigation is unambiguous.

DimensionReasoningScore

Conciseness

The body is dense and avoids explaining concepts Claude already knows, but the Dependencies (lines 55-61) and References (lines 165-181) sections largely duplicate the same resource list, which could be tightened into a single section.

3 / 5

Actionability

Provides concrete executable guidance: a runnable bash block (ls/rg) and named serena MCP primitives (get_symbols_overview, find_symbol, search_for_pattern), plus a YAML output spec and discrete method modes, with only minor gaps in full ADR-producing examples.

4 / 5

Workflow Clarity

A clear Entry -> Scenes (PREPARE/ACQUIRE/REASON/VERIFY/FINALIZE) -> Exit sequence with an explicit VERIFY checkpoint, a Failure-and-recovery section, and a referenced checklist; the validate->fix->retry loop is implied rather than fully explicit, leaving a minor gap.

4 / 5

Progressive Disclosure

SKILL.md stays an overview and pushes detail to one-level-deep resource files (resources/*.md, ../_shared/core/*.md) clearly signaled in a References section; no bundle files are present to verify against, and the duplicate dependency/reference listing is a minor organization gap.

4 / 5

Total

15

/

20

Passed

Description

71%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 specific and method-rich, clearly stating what the skill does, but it lacks any explicit 'Use when...' trigger guidance, which caps its completeness and slightly weakens trigger-term and distinctiveness scores.

Suggestions

Add an explicit 'Use when...' clause naming concrete trigger phrases (e.g., 'Use when the user asks for architecture, system design, module/service boundaries, ADRs, or design tradeoffs').

Include common synonyms users actually say ('tech design', 'design docs', 'service boundaries') to improve trigger-term coverage.

Reinforce distinctiveness by contrasting with adjacent skills (e.g., '...not visual design or feature planning') directly in the description.

DimensionReasoningScore

Specificity

Lists multiple concrete capabilities ('software/system design, module and service boundaries, tradeoff analysis, and stakeholder synthesis') plus named methods ('diagnostic routing, design-twice comparison, ATAM-style risk analysis, CBAM-style prioritization, and ADR-style decision records'), giving comprehensive coverage of specific actions.

5 / 5

Completeness

Has a clear 'what' (architecture specialist for the listed domains and methods) but no 'Use when...' clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 3.

3 / 5

Trigger Term Quality

Includes natural terms a user would say ('architecture', 'system design', 'module and service boundaries', 'tradeoff', 'ADR'), but omits common synonyms such as 'tech design', 'design docs', or 'service boundaries' variations, so coverage is good rather than comprehensive.

4 / 5

Distinctiveness Conflict Risk

The 'Architecture specialist' framing with ADR/ATAM/CBAM methods carves a clear niche, but without explicit trigger phrases there is minor overlap risk with general system-design or planning skills.

4 / 5

Total

16

/

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.