CtrlK
BlogDocsLog inGet started
Tessl Logo

playwright-ci

Production-ready CI/CD configurations for Playwright — GitHub Actions, GitLab CI, CircleCI, Azure DevOps, Jenkins, Docker, parallel sharding, reporting, code coverage, and global setup/teardown.

62

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/playwright/ci/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

76%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 lean index-style SKILL.md: concise, well-organized, with concrete golden rules and a clean one-level-deep guide index. Weaknesses are the missing guide files in the bundle (broken references), the absence of any complete executable snippet, and the lack of an explicit sequenced workflow with validation checkpoints.

Suggestions

Ship the 9 referenced guide files (or relocate them) so every link in the Guide Index resolves — currently the entire skill's substance is unreachable.

Include one complete copy-paste-ready example in the body (e.g., a minimal GitHub Actions workflow YAML with caching and sharding) so the skill is useful even before opening a guide.

Add a short 'Start here' sequence (e.g., pick provider guide → apply sharding rule → wire reporting → verify artifact upload) to turn the index into an explicit workflow with a verification checkpoint.

DimensionReasoningScore

Conciseness

The 47-line body is lean with zero padding: it assumes knowledge of Playwright and CI systems, offers no 'what is CI' explanations, and every line is either a golden rule with a concrete value or a navigation entry. Matches the 5 anchor — every token earns its place.

5 / 5

Actionability

The Golden Rules give concrete, executable values ('retries: 2 in CI only', "traces: 'on-first-retry'", '--shard=N/M', '~/.cache/ms-playwright keyed on Playwright version', 'mcr.microsoft.com/playwright:v*', 'storageState'). Not 5 because there is no complete copy-paste-ready snippet (no YAML config block, cache-action invocation, or globalSetup example) — the rules are key/value directives rather than executable examples; not 3 because the guidance is concrete and directly usable, not pseudocode.

4 / 5

Workflow Clarity

The body is a navigational index: the Guide Index groups topics into 'CI Providers → Execution & Scaling → Reporting & Setup', which implies a path but no explicit multi-step sequence with checkpoints exists. Not 4 because there is no stated order of operations or validation checkpoint for applying the rules (e.g., verify sharding splits evenly, confirm artifacts uploaded before debugging); not 2 because the guide tables do organize navigation by task category.

3 / 5

Progressive Disclosure

Structure matches the 5-anchor pattern: a clear overview with 9 well-signaled, one-level-deep references presented in labeled tables with descriptive topic rows. Not 5 because scoring against the actual bundle shows none of the referenced guide files (ci-github-actions.md, ci-gitlab.md, ci-other.md, parallel-and-sharding.md, docker-and-containers.md, projects-and-dependencies.md, reporting-and-artifacts.md, test-coverage.md, global-setup-teardown.md) exist in the provided bundle — no references/, scripts/, or assets/ directories are present, so every link is unresolvable as given. Not 3 because the in-file structure and signaling are excellent.

4 / 5

Total

16

/

20

Passed

Description

71%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 tight, specific description with strong trigger keywords and comprehensive capability enumeration. Its one real weakness is the complete absence of a 'Use when...' trigger clause, which caps completeness and leaves invocation guidance implicit.

Suggestions

Append an explicit trigger clause, e.g. 'Use when setting up or debugging Playwright tests in a CI pipeline, sharding test runs, or containerizing test execution.'

Add a few natural synonyms users say — 'pipeline', 'workflow', 'flaky tests' — to broaden trigger coverage.

Consider a brief clarifier that the skill covers CI infrastructure (not test authoring) to reduce overlap with a general Playwright testing skill.

DimensionReasoningScore

Specificity

The description enumerates concrete deliverables across the full domain: 'GitHub Actions, GitLab CI, CircleCI, Azure DevOps, Jenkins, Docker, parallel sharding, reporting, code coverage, and global setup/teardown' — comprehensive, specific coverage with no padding. Not 4 because coverage is essentially complete rather than having minor gaps; the enumerated list matches the 5 anchor's comprehensiveness.

5 / 5

Completeness

The 'what' is explicit and concrete ('Production-ready CI/CD configurations for Playwright — ...') but there is no 'Use when...' clause or equivalent trigger guidance anywhere in the description, which caps completeness at 3 per the judging guidelines. Not 4 because the 'when' is entirely absent rather than merely imprecise.

3 / 5

Trigger Term Quality

Natural terms users would say are present: 'GitHub Actions', 'GitLab CI', 'CircleCI', 'Jenkins', 'Docker', 'CI/CD', 'Playwright'. Not 5 because common synonyms users actually use are missing — 'pipeline', 'workflow files'/'yml', 'headless', 'flaky tests'. Not 3 because the provider and tool names are the primary natural triggers and are all covered.

4 / 5

Distinctiveness Conflict Risk

'CI/CD configurations for Playwright' carves a clear niche (CI integration, not test authoring) and names specific providers. Not 5 because it could still trigger for general Playwright test-writing or generic 'GitHub Actions setup' requests where this CI-specific skill is only partially relevant; not 3 because the Playwright + CI/CD pairing is much more specific than the 'Works with document files' overlap example.

4 / 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: 9 missing

Warning

Total

15

/

16

Passed

Repository
zebbern/claude-code-guide
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.