dep-major
dep-major is a Dependency & version upgrades skill for AI agents, published by jellyrock in the jellyrock repository on GitHub. Skillspace rates dep-major F (45/100) and the safety scan rated it risky; the rating is based on static analysis only.
Risky. This skill has patterns associated with unsafe behaviour. Read the source carefully before running it.
Walk a MAJOR dependency-version bump (a Renovate major PR — possibly a GROUPED one carrying several deps — or a package you name) through JellyRock's major-bump SOP so the judgment steps run the same way every time. Resolves each package + from→to version range, fetches the upstream changelog/migration guide for that range, classifies the breaking changes, greps the codebase for the call sites those breaks actually hit, runs the mechanical gate that fits the dependency's TYPE (runtime BrightScript lib → validate/build/lint:bs + on-device test:unit/test:rta; JS/Node tooling → test:scripts + run the affected script; GitHub Actions → the PR's own CI plus a trace of the conditional paths CI doesn't exercise), and returns a go/no-go with any required migration surfaced (and applied on request). Majors never automerge (Renovate org policy), so this is the human-review path. Use when a Renovate major PR appears, or before bumping a dependency's major version by hand. NOT for patch/minor bumps…
- Grade
- F
- Quality
- 45 / 100
- Safety
- Risky
- GitHub stars
- 35
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.
Our review
- Architecture
- 89 / 100
- Maturity
- Basic: a single SKILL.md
- Security scan
- High-risk patterns
- License
- GPL-2.0
- Adoption
- Adopted by 0 other repositories, in 0 collections
What the scanner flagged
- base64 decode (possible obfuscation)
- over-broad allowed-tools ('*')
Not checked yet
- Category is a classifier prediction; no model has read this skill 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.