CtrlK
BlogDocsLog inGet started
Tessl Logo
PluginPublic

testland/currents-integration

Use for any question about seeing Playwright flakiness, slowest tests or pass-rate trends across CI runs, or which tool tracks them. Sets up Currents.dev with @currents/playwright, currents.config.ts, the reporter, traces, videos and screenshots, and runs via npx pwc.

Quality

84%

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

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 highly actionable, well-structured skill body: every step is executable with copy-paste code, the workflow is clearly sequenced, and detail is properly deferred to a real, well-signaled reference file. The main weakness is redundancy — the worked example reprints config/reporter blocks and the reference-file pointer is repeated three times.

Suggestions

Trim the Worked example: replace the reprinted currents.config.ts and reporter/artifact code blocks with one-line references back to the Configure/Register/Enable artifacts sections, keeping only the new content (the export CURRENTS_RECORD_KEY step and the outcome description).

Consolidate the three near-identical pointers to references/ci-and-cypress-integration.md (in Overview, How to use, and Operating in CI) into one clearly signaled link plus a single mention of what it covers.

Add an explicit validation checkpoint after the first run — e.g., "Confirm the printed dashboard URL shows the run and its traces; if no URL prints or auth fails, check CURRENTS_RECORD_KEY and the projectId" — to close the workflow's validation gap.

DimensionReasoningScore

Conciseness

The body is mostly efficient, but the Worked example duplicates the full currents.config.ts block and the reporter/artifact lines already shown in their own sections, the pointer to references/ci-and-cypress-integration.md is repeated three times, and the Overview quote plus "The reporter forwards every test event ..." add explanation that could be trimmed — matches "mostly efficient but includes some unnecessary explanation or could be tightened".

3 / 5

Actionability

Fully executable and copy-paste ready: npm install command, complete currents.config.ts file, currentsReporter() registration snippet, use: artifact block, npx pwc with --key/--project-id variants, and export CURRENTS_RECORD_KEY in the worked example — covering all common cases from install through CI wiring.

5 / 5

Workflow Clarity

"How to use" gives a clear 6-step sequence reinforced by a worked example, with partial checkpoints ("open the dashboard URL it prints", the if: always() HTML-report fallback, anti-pattern fixes), but validation is implicit — there is no explicit step to confirm the run landed on the dashboard or how to recover from a failed/missing record key. Not a destructive or batch operation, so the cap-3 rule does not apply.

4 / 5

Progressive Disclosure

The body is a well-sectioned overview and the single bundle file (references/ci-and-cypress-integration.md, verified to exist) is one level deep, clearly signaled each time with what it contains (full CI workflow, per-PR-vs-main rationale, Cypress integration); CI detail is appropriately deferred rather than inlined — clear overview with well-signaled one-level-deep references.

5 / 5

Total

17

/

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 description: it explicitly states both what the skill does (with named tools, config files, and the run command) and when to use it, using natural trigger phrases tied to Playwright flakiness and CI trends. The only deductions are bundled action phrasing and a slightly broad "which tool tracks them" trigger that poses minor overlap risk.

DimensionReasoningScore

Specificity

"Sets up Currents.dev with @currents/playwright, currents.config.ts, the reporter, traces, videos and screenshots, and runs via npx pwc" names concrete tools and files, but bundles most setup under a single verb ("Sets up ... with") and leaves "the reporter" generic — several specific actions with minor gaps, not the comprehensive multi-action coverage of the top anchor.

4 / 5

Completeness

Both halves are explicit: the "what" ("Sets up Currents.dev with @currents/playwright ... runs via npx pwc") and a concrete "when" clause ("Use for any question about seeing Playwright flakiness, slowest tests or pass-rate trends across CI runs, or which tool tracks them") — clearly and explicitly answers both with concrete trigger phrases.

5 / 5

Trigger Term Quality

"Playwright flakiness", "slowest tests", "pass-rate trends across CI runs" are natural phrases a user would say, but common synonyms like "flaky tests", "test analytics", or "Cypress" are absent — good coverage with a few natural terms missing, short of the comprehensive synonym coverage of the top anchor.

4 / 5

Distinctiveness Conflict Risk

The Currents/Playwright longitudinal-analytics niche is distinct with specific triggers, but "any question about ... which tool tracks them" is a broad tool-selection trigger that could overlap with generic test-reporting or analytics skills — mostly distinct with minor overlap risk rather than 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.

Reviewed

On this page