skytest
skytest is an End-to-end & browser testing skill for AI agents, published by oursky in the skytest-agent repository on GitHub. Skillspace rates skytest F (51/100) and it passed the safety scan; the rating is based on static analysis only.
Create, update, run, and manage SkyTest test cases via MCP — directly from the user's instructions, with no separate explore/plan phase. Accepts short prompts ("add a test that creates a product and verifies it in the list") or exact step lists; fills in element detail from existing test cases, screenshots, or a quick browser-tool pass. Writes playwright-code steps for deterministic interactions (clicks, fills, dropdowns, datepickers) and ai-action for visual verification. Also handles section coverage design, project configs, runner inventory, run monitoring, and stop operations. For diagnosing a failed run, use skytest-fix.
- Grade
- F
- Quality
- 51 / 100
- Safety
- Passed
- GitHub stars
- 29
Unproven: rated by static analysis only, not yet compared head-to-head.
This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.
Our review
- Architecture
- 76 / 100
- Maturity
- Basic: a single SKILL.md
- Security scan
- Low-risk patterns
- License
- MIT
- Adoption
- Adopted by 0 other repositories, in 0 collections
What the scanner flagged
- mentions secrets in text
Not checked yet
- Not judged on the rubric yet (not a contender in its category)
- No blind task eval yet
- Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.