CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

opik-backend

Java backend patterns for Opik. Use when working in apps/opik-backend, designing APIs, database operations, or services.

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/opik-backend/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%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.

A dense, highly actionable conventions guide: nearly every rule is backed by concrete good/bad code examples and project-specific gotchas Claude could not infer. Its weaknesses are minor verbosity in the SQL section, basic-Java content like immutable collections, and a Reference Files section whose links point to files missing from the bundle.

Suggestions

Ship the five referenced files (clickhouse.md, mysql.md, testing.md, migrations.md, permissions.md) in a references/ directory, or remove the Reference Files section — every link is currently dangling.

Trim or move the extended SQL-construction narrative (the 'Why' paragraph and TOKEN_USAGE example) into a reference file, keeping only the binding-vs-fragment rule table inline.

Drop or compress sections teaching knowledge Claude already has, such as the Immutable Collections (Set.of vs Arrays.asList) example.

DimensionReasoningScore

Conciseness

The bulk is project-specific knowledge Claude cannot know (plural/singular naming tables, StringTemplate leak, SQL construction rules, log format conventions) presented as tight good/bad pairs. Minor over-explanation of basics (e.g. Set.of vs Arrays.asList) and a wordy SQL narrative paragraph keep it below anchor 5's 'every token earns its place'.

4 / 5

Actionability

Nearly every section pairs executable ✅/❌ code with exact identifiers: 'TemplateUtils.newST(QUERY)', '@RequiredArgsConstructor(onConstructor_ = @Inject)', '@Size(max = Project.NAME_MAX_LENGTH, message = "cannot exceed {max} characters")', and named exception classes. The examples are copy-paste adaptable and cover the common cases for each convention.

5 / 5

Workflow Clarity

Mostly declarative conventions rather than a multi-step process, but sections are clearly organized, and the user-named-resources section is a sequenced 6-step checklist with an explicit validation step ('Test create and rename with a max + 1 name (422) and with exactly max (accepted)'). Not 5 because no other workflow offers sequencing with feedback loops; not lower because nothing risky lacks validation.

4 / 5

Progressive Disclosure

The Reference Files section is clearly signaled with one-line descriptions and one-level-deep links, but none of the five cited files (clickhouse.md, mysql.md, testing.md, migrations.md, permissions.md) exist in the bundle — no references/ directory is present. Broken navigation is more than the 'minor organization gaps' of anchor 4, while the inline content itself is well structured above anchor 2's inlining problem.

3 / 5

Total

16

/

20

Passed

Description

73%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.

A concise, third-person description with an explicit 'Use when' trigger clause tied to a specific repository, making it highly distinctive. Its main weakness is the what-clause, which names the domain but never enumerates the concrete actions or pattern areas the skill covers.

Suggestions

Enumerate concrete actions in the what-clause, e.g. 'Write Opik resources, DAOs, services, SQL queries, and Liquibase migrations following layered architecture and naming conventions.'

Add natural trigger terms users would say, such as 'endpoints', 'migrations', 'DAOs', or 'ClickHouse/MySQL queries', to broaden keyword coverage.

DimensionReasoningScore

Specificity

The what-clause is a domain statement ('Java backend patterns for Opik') with no enumerated actions; the concrete activities ('designing APIs, database operations, or services') appear only in the trigger clause. This sits between anchor 2 (domain named, actions generic) and anchor 4 (several specific actions listed), matching anchor 3's 'names domain and 1-2 concrete actions, but not comprehensive'.

3 / 5

Completeness

Both what ('Java backend patterns for Opik') and when ('Use when working in apps/opik-backend, designing APIs, database operations, or services') are explicitly present. Not 5 because the what is a terse domain-level phrase rather than an enumeration of concrete actions with trigger phrases.

4 / 5

Trigger Term Quality

Includes natural terms a developer would say: 'Java backend', 'Opik', 'apps/opik-backend', 'APIs', 'database operations', 'services'. Missing common variations like endpoints, migrations, ClickHouse/MySQL, or DAOs, so not the comprehensive coverage of anchor 5.

4 / 5

Distinctiveness Conflict Risk

'Opik' and the repo path 'apps/opik-backend' carve a clear project-specific niche with distinct triggers; the generic backend terms in the when-clause are anchored to the Opik context, giving minimal conflict risk with other skills.

5 / 5

Total

16

/

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

relative_links

Relative link issues: 5 missing

Warning

Total

15

/

16

Passed

Repository

comet-ml/opik

Path

.agents/skills/opik-backend/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.