CtrlK
BlogDocsLog inGet started
Tessl Logo

logging

Use when adding logs, debugging, or working with the Logger across the SDK and container runtime. Covers the constructor-injection pattern, child loggers, env-var configuration, and test mocking. (project)

74

Quality

91%

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

100%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.

An exemplary skill body for a simple logging-convention skill: lean, fully executable, and clearly organized with no filler or over-explanation. Every instruction is concrete (code, env vars, level guidance) and the structure matches the skill's size — no external files are needed or referenced. No weaknesses worth penalizing were found.

DimensionReasoningScore

Conciseness

Every section earns its place: one compact code example, a two-row env-var table, and terse bullets ('Log at info for significant lifecycle events', 'Log at debug for fine-grained tracing'). It assumes Claude's competence — no explanation of what logging or DI is — matching the anchor-5 'lean and efficient; every token earns its place' example rather than anchor 4, which would require trimmable over-explanation.

5 / 5

Actionability

All guidance is copy-paste ready: a complete TypeScript constructor-injection example with `logger.child({ operation: 'work' })`, exact env vars with their value sets (`SANDBOX_LOG_LEVEL`, `SANDBOX_LOG_FORMAT`), `createNoOpLogger()` from `@repo/shared` for tests, and a concrete error-logging pattern `logger.error('Failed', { err })`. This matches anchor 5's fully executable guidance covering the common cases.

5 / 5

Workflow Clarity

This is a simple, single-purpose reference skill (how to log correctly), and each context's single action is unambiguous: constructor-inject the logger, use `child()` at unit-of-work boundaries, use `createNoOpLogger()` in tests, and follow the per-level bullet list. Per the rubric's simple-skill exception, unambiguous single-action content can score 5; there are no destructive or batch operations that would require validation checkpoints.

5 / 5

Progressive Disclosure

The skill is a short (~55-line) self-contained body with no bundle files (references/, scripts/, assets/ absent), so nothing needs external disclosure. Sections are well-organized and clearly headed ('Pattern', 'Configuration', 'In Tests', 'When Adding Logs'), which satisfies the rubric's guidance that short skills with no need for external references can score 5 on well-organized sections alone.

5 / 5

Total

20

/

20

Passed

Description

83%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 strong skill description: explicit 'Use when...' trigger clause, concrete coverage list, and a clearly bounded scope with the '(project)' marker. It is written in the standard imperative skill style with no vague filler. The only weaknesses are a few missing natural logging synonyms and the slightly generic 'debugging' trigger.

Suggestions

Add common user phrasings like 'log levels', 'structured logging', or 'silencing logs in tests' to broaden natural trigger coverage.

Narrow or contextualize the 'debugging' trigger (e.g., 'debugging log output') to reduce overlap with generic debugging skills.

DimensionReasoningScore

Specificity

The description names a concrete scope ('across the SDK and container runtime') and lists four specific coverage areas ('constructor-injection pattern, child loggers, env-var configuration, and test mocking'). It falls just below the anchor-5 example, which lists multiple concrete user-facing actions rather than topic coverage, and well above anchor 3's 1-2 concrete actions.

4 / 5

Completeness

It explicitly answers 'when' with concrete trigger phrases ('Use when adding logs, debugging, or working with the Logger across the SDK and container runtime') and 'what' with explicit coverage ('Covers the constructor-injection pattern, child loggers, env-var configuration, and test mocking'). This matches anchor 5's requirement for both an explicit what and when with concrete triggers, and exceeds anchor 4 where the 'when' is less specific.

5 / 5

Trigger Term Quality

Natural trigger phrases users would say are present: 'adding logs', 'debugging', 'working with the Logger'. A few common variations are missing (e.g., 'log levels', 'log output', 'verbose logging', 'structured logging'), which matches anchor 4's 'good keyword coverage; a few natural terms missing' rather than anchor 5's comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

The '(project)' marker plus the specific 'Logger' proper noun and 'SDK and container runtime' scope give it a clear niche with distinct triggers. The generic word 'debugging' creates minor overlap risk with general debugging skills, matching anchor 4 ('mostly distinct; minor overlap risk') rather than anchor 5's minimal conflict risk.

4 / 5

Total

17

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
cloudflare/sandbox-sdk
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.