CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

oma-qa

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

Quality

73%

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 ./skills/oma-qa/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 a well-structured, lean instruction set with a concrete command path, severity rubric, validation checkpoints, and error-recovery loops — strong on actionability and workflow clarity. Its critical defect is bundle integrity: the execution protocol, checklist, and error playbook it directs the reader to follow are missing from the bundle, breaking the progressive-disclosure chain at its most important links.

Suggestions

Ship the referenced files or fix the paths: resources/execution-protocol.md, resources/iso-quality.md, resources/checklist.md, and resources/error-playbook.md are all cited as load-bearing dependencies but are absent from the bundle.

Verify the cross-boundary paths (.agents/workflows/ultrawork/resources/*, ../oma-observability/SKILL.md) resolve from this skill's install location, or move that guidance into the body.

De-duplicate the Transitions/Guardrails overlap (security priority, reproducibility, oma-security routing are each stated twice) to tighten token usage.

DimensionReasoningScore

Conciseness

The body never explains concepts Claude already knows (OWASP, WCAG, and ISO standards are named, not taught) and is dense with directives. Minor trimming is possible: the security-first priority, reproducibility rule, and oma-security routing are each stated twice (Transitions/When NOT to use vs. Guardrails), which is why it does not reach anchor 5.

4 / 5

Actionability

Concrete commands are given ("npm audit", "bandit -r .", "lighthouse <url>"), a specific severity rubric (CRITICAL/HIGH/MEDIUM/LOW with definitions), and hard output requirements ("Every finding must include file:line, description, and fix"). It stops short of anchor 5 because the tool invocations are illustrative examples ("e.g.") rather than a copy-paste-ready command sequence for the common case.

4 / 5

Workflow Clarity

The 7-step canonical command path is clearly sequenced with explicit validation checkpoints ("Reproduce each candidate finding and reject false positives", "Do not issue PASS while required checks remain unverified") and a dedicated failure-and-recovery section with feedback loops. It misses anchor 5 because the checklist for complex processes is only referenced (in a file absent from the bundle) rather than embedded or verified, and the primary execution protocol is delegated to a missing file.

4 / 5

Progressive Disclosure

Scored against the actual bundle: the references are well signaled and one level deep, but the core resources the body instructs the reader to follow — "resources/execution-protocol.md", "resources/iso-quality.md", "resources/checklist.md", "resources/error-playbook.md", and the two ".agents/workflows/ultrawork/resources/" paths — do not exist in the bundle (only the four references/_shared/core/ files resolve). Dead-ending on the primary "Execution steps (follow for the selected task)" reference makes navigation minimally functional, fitting anchor 2 more than 3 despite the good signaling.

2 / 5

Total

14

/

20

Passed

Description

67%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 answers both what and when, uses third person, and includes useful cross-skill disambiguation against oma-debug. Its main weakness is thin trigger-term coverage: it relies on abstract categories ("scoped quality reviews", "verification plans") rather than the natural phrases (code review, QA, security audit) users would say when they need this skill.

Suggestions

Add natural trigger terms users would actually say, e.g. "Use when the user asks for a code review, QA pass, security audit, accessibility check, or pre-deployment review".

Include the test-coverage and standards dimensions (OWASP, WCAG) that the body covers, so the description's capability list is not missing a core function.

Make the oma-debug boundary bidirectional and concrete, e.g. "use oma-qa to review existing changes; use oma-debug to diagnose and fix a specific bug".

DimensionReasoningScore

Specificity

"Review changes for correctness, security, accessibility, and performance" names several concrete review dimensions with only minor coverage gaps (e.g., test coverage analysis from the body is absent). It is above anchor 3 because it goes beyond a bare domain-plus-one-action statement, but below anchor 5 because "review changes" is a single action rather than a comprehensive list of distinct capabilities.

4 / 5

Completeness

Both parts are present: the "what" ("Review changes for correctness, security, accessibility, and performance") is clear, and the "when" is explicit ("Use for scoped quality reviews or verification plans") with disambiguation ("bug fixes use oma-debug"). It falls short of anchor 5 because the trigger phrases ("scoped quality reviews", "verification plans") are task-category abstractions rather than concrete user-language triggers like "when the user mentions security audits or WCAG".

4 / 5

Trigger Term Quality

The only natural triggers are "quality reviews", "verification plans", and "bug fixes"; common phrases users would actually say — "code review", "QA", "security audit", "review my PR", "accessibility check" — are missing. It has some relevant keywords but misses common variations, matching anchor 3 rather than 4.

3 / 5

Distinctiveness Conflict Risk

The explicit boundary "bug fixes use oma-debug" plus the scoped-review framing carves a mostly distinct niche with minor overlap risk against generic code-review or security-audit skills. It is below anchor 5 because "review changes for correctness/security/performance" still overlaps broadly with any general code-review skill, but well above anchor 3's vague overlap territory.

4 / 5

Total

15

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 4 deeper-than-1-level

Warning

Total

15

/

16

Passed

Repository

first-fluke/oh-my-agent

Path

skills/oma-qa/SKILL.md

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.