CtrlK
BlogDocsLog inGet started
Tessl Logo
PluginPublic

testland/timezone-test-matrix-builder

Use for any question or task about which time zones, DST dates and leap-year cases to test, including bugs such as dates shown a day early or late for users in another zone. Finds where the codebase stores, computes, displays, schedules or bills times, picks the edge cases that matter and writes test stubs with the language's fake-clock library.

Quality

93%

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

Overview
Quality
Evals
Security
Files

Quality

Content

92%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 well-engineered skill body: executable commands and tests at every step, a seven-step workflow with an explicit run-and-fix validation loop, and clean one-level-deep reference structure verified against the actual bundle. The only improvement space is trimming the worked-example recap and 'When to use' redundancy.

DimensionReasoningScore

Conciseness

The body is dense and table-driven with no explanation of concepts Claude already knows (no DST tutorial, no library intros), but the worked-example paragraph re-narrates Steps 1-7 already shown, and 'When to use' partially repeats the description. Not 5: those minor instances could be trimmed; not 3: the padding is marginal, not 'unnecessary explanation'.

4 / 5

Actionability

Fully executable throughout: copy-paste grep commands (Step 1), a category-to-test mapping table, a concrete matrix.yaml schema, runnable freezegun tests with real assertions, and explicit run commands ('pytest tests/time/', 'mvn test'). Not 4: the examples cover the common cases (Python billing leap-day/DST) with complete, correct code rather than leaving minor gaps.

5 / 5

Workflow Clarity

Steps 1-7 are clearly sequenced, and Step 6 is an explicit validation checkpoint with a feedback loop: 'If a case errors instead of asserting, the fake-clock wiring is wrong - fix the harness mapping... and re-run until the matrix is green.' This satisfies the batch-operation validation requirement, so no cap applies. Not 4: error recovery guidance is explicit, not merely implied.

5 / 5

Progressive Disclosure

The bulk per-category catalog is properly split into references/test-catalog.md (verified present, one level deep, clearly linked), per-language harness detail is delegated to the companion fake-clock-testing skill with its location stated up front, and the body keeps only overview, steps, and examples. Not 4: navigation is clean with no inlined content that belongs in a separate file and no buried references.

5 / 5

Total

19

/

20

Passed

Description

92%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 description: concrete third-person actions covering the whole workflow, an explicit 'Use for...' trigger clause with symptom-level phrasing, and a clear niche. The only gap is modest synonym coverage (e.g., 'timezone' as one word, 'daylight saving').

DimensionReasoningScore

Specificity

The description lists multiple concrete actions covering the full workflow — "Finds where the codebase stores, computes, displays, schedules or bills times", "picks the edge cases that matter", "writes test stubs with the language's fake-clock library" — all in third person, matching the comprehensive multi-action anchor. Not 4: coverage is complete across inventory, case selection, and stub generation with no notable gaps.

5 / 5

Completeness

Explicitly answers both: what ("Finds... picks the edge cases... writes test stubs with the language's fake-clock library") and when ("Use for any question or task about which time zones, DST dates and leap-year cases to test, including bugs such as dates shown a day early or late"), with concrete trigger phrasing. Not 4: the 'when' clause is already explicit and symptom-level, not merely present.

5 / 5

Trigger Term Quality

Natural triggers include "time zones", "DST dates", "leap-year cases" and the user-voiced symptom "dates shown a day early or late for users in another zone", giving good keyword coverage. Not 5: misses common synonyms such as the unspaced "timezone", "daylight saving", or "time-handling" variations.

4 / 5

Distinctiveness Conflict Risk

The niche — selecting timezone/DST/leap-year test cases and emitting fake-clock test stubs — is distinct from generic test-writing or DST-bug-reference skills, with triggers anchored to test-selection and cross-zone date symptoms. Not 4: overlap risk with closely related skills is minimal because the description scopes itself to building the test matrix rather than explaining time bugs or harnesses.

5 / 5

Total

19

/

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: 8 missing

Warning

Total

15

/

16

Passed

Reviewed

On this page