CtrlK
BlogDocsLog inGet started
Tessl Logo

oma-qa

Review changes for correctness, security, accessibility, and performance. Use for scoped quality reviews or verification plans; bug fixes use oma-debug.

67

Quality

80%

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

SKILL.md
Quality
Evals
Security

Quality

Content

73%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, actionable QA workflow with explicit validation checkpoints and feedback loops. Its main weaknesses are mild verbosity from an abstract primitive table and repeated priority/severity content, plus references to bundle files that are not actually present.

Suggestions

Remove or collapse the "SSL primitive" action table, which restates obvious read/run/compare actions in abstract framework jargon that does not aid execution.

De-duplicate the Security > Performance > Accessibility > Code Quality priority order and the severity definitions, which appear in both Transitions and Guardrails.

Either add the referenced resources/*.md and ../_shared/core/* files to the bundle or mark which references are external, so the References section is navigable and verifiable.

DimensionReasoningScore

Conciseness

The body is mostly efficient structured guidance, but the abstract "SSL primitive" action table adds framework jargon Claude does not need, and the priority order and severity definitions are repeated across the Transitions and Guardrails sections.

3 / 5

Actionability

Provides concrete runnable commands (npm audit, bandit -r ., lighthouse <url>), a severity rubric, file:line evidence requirements, and ISO mappings, with only minor gaps around stack-specific command selection.

4 / 5

Workflow Clarity

The PREPARE→ACQUIRE→REASON→VERIFY→FINALIZE sequence is explicit, with a dedicated VERIFY validation step (reproduce findings, reject false positives) and a failure-and-recovery section providing feedback loops; review work is read-heavy rather than destructive, so no cap applies.

5 / 5

Progressive Disclosure

A clear References section lists one-level-deep, well-signaled resources, but no references/scripts/assets bundle directory exists, so the cited resources/*.md and ../_shared/core/* files cannot be verified and some detail is inlined rather than split out.

4 / 5

Total

16

/

20

Passed

Description

87%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 clearly states both the capability and its trigger conditions with a useful disambiguation. It is strong overall, with minor room to add common synonyms like OWASP/WCAG/lint for richer trigger coverage.

DimensionReasoningScore

Specificity

Names the QA-review domain and several concrete review dimensions (correctness, security, accessibility, performance), which is more than 1-2 actions but a single action verb applied across dimensions rather than multiple distinct actions.

4 / 5

Completeness

Explicitly answers both what ("Review changes for correctness, security, accessibility, and performance") and when ("Use for scoped quality reviews or verification plans") with concrete trigger phrases plus a disambiguating boundary.

5 / 5

Trigger Term Quality

Includes natural terms users would say (security, accessibility, performance, quality reviews, verification plans, bug fixes), but omits common synonyms and extensions that appear in the body (OWASP, WCAG, lint, coverage).

4 / 5

Distinctiveness Conflict Risk

Occupies a clear QA-review niche with an explicit boundary clause ("bug fixes use oma-debug") that minimizes overlap with debugging skills.

5 / 5

Total

18

/

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.