CtrlK
BlogDocsLog inGet started
Tessl Logo

python-sdk

Python SDK patterns for Opik. Use when working in sdks/python, on SDK APIs, integrations, or message processing.

62

Quality

78%

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/python-sdk/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 tight, dense patterns reference with strong actionability and excellent token efficiency. The two real weaknesses are the missing bundle files behind the 'Reference Files' section, which breaks progressive disclosure and removes the testing/validation guidance that would strengthen workflow clarity.

Suggestions

Ship the three referenced files (testing.md, error-handling.md, good-code.md) in the bundle or remove the 'Reference Files' section — as written, all three links are dead ends.

Add a brief validation step for SDK changes, e.g. 'After modifying integrations, run the fake_backend-based tests (see testing.md)' to close the workflow feedback loop.

Complete the truncated snippets (e.g. batch_create_items) or mark them explicitly as signature-only examples so they read as intentional rather than gaps.

DimensionReasoningScore

Conciseness

The body is lean and dense — short sections, minimal prose, and code/diagrams that assume Claude's competence (e.g. the three-layer ASCII diagram, the async/sync operation lists, batching thresholds). No padding or explanations of concepts Claude already knows; every section earns its place.

5 / 5

Actionability

Most guidance is executable: copy-paste-ready snippets for track_anthropic, OpikTracer, @opik.track, concrete flush thresholds (1s/100/50MB), and CRUD naming conventions. Minor gaps keep it below 5 — a few snippets are illustrative with ellipses ('client.batch_create_items(...)') and the lazy-import 'BAD' example is not runnable as written.

4 / 5

Workflow Clarity

This is a patterns/reference skill rather than a stepwise workflow, and it is well organized with one explicit critical checkpoint ('client.flush() # Must call before exit!'). It is not a 5 because there is no validation/verification guidance for code changes (e.g. run the SDK's tests after modifying integrations), and the section that would supply it (testing.md) is a broken reference.

4 / 5

Progressive Disclosure

The in-body content is a well-organized overview and the 'Reference Files' section clearly signals one-level-deep references with one-line descriptions. However, all three cited files (testing.md, error-handling.md, good-code.md) are absent from the bundle — the references are clearly signaled but broken, so the intended split is not actually realized and navigation dead-ends.

3 / 5

Total

16

/

20

Passed

Description

68%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, distinctive description with an explicit and well-targeted 'Use when...' trigger clause. Its main weakness is the 'what' half: it names the domain but lists no concrete capabilities, which also weakens trigger-term breadth.

Suggestions

Add 1-2 concrete capabilities to the 'what' half, e.g. 'Document the three-layer architecture, integration patterns (callback/patching/decorator), and batching behavior of the Opik Python SDK.'

Include a few more natural trigger terms users would say, such as 'opik.track', 'Opik tracing', or 'Opik Python client'.

DimensionReasoningScore

Specificity

"Python SDK patterns for Opik" names the domain clearly but lists no concrete actions or capabilities (compare anchor 3's '1-2 concrete actions'). It is not entirely vague (not a 1) because it pins a specific domain and repo path, but 'patterns' alone gives Claude nothing actionable to expect.

2 / 5

Completeness

Both parts are present: the 'what' ("Python SDK patterns for Opik") and an explicit 'when' clause ("Use when working in sdks/python, on SDK APIs, integrations, or message processing"). Not a 5 because the 'what' is thin — 'patterns' doesn't state what it does with them (architecture, integrations, batching) — while anchor 5 requires both halves to be concrete.

4 / 5

Trigger Term Quality

"Use when working in sdks/python, on SDK APIs, integrations, or message processing" provides good keyword coverage with natural terms a developer would say, including a concrete path. Not a 5 because it misses common variations users might naturally say, e.g. 'opik.track', 'tracing', or 'Opik Python client'.

4 / 5

Distinctiveness Conflict Risk

"Python SDK patterns for Opik" plus the repo-scoped trigger "sdks/python" carves out a clear niche with distinct triggers and minimal overlap risk with other skills. Neither the 4 nor 3 anchor (generic 'document files' style overlap) fits better.

5 / 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

relative_links

Relative link issues: 3 missing

Warning

Total

15

/

16

Passed

Repository
comet-ml/opik
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.