new-release
new-release is a Release cutting & versioning skill for AI agents, published by zeropsio in the zcli repository on GitHub. Skillspace rates new-release 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.
Cut a new zcli release end-to-end. Two phases - first opens a `release/vX.Y.Z` PR adding the `CHANGELOG.md` entry, then (once the user merges that PR) creates the GitHub Release on main which triggers `.github/workflows/release.yml`, watches goreleaser + npm publish + smoke tests, and reports the outcome. Use when the user says "cut a release", "new release", "release", "ship a new version", "tag and release", "release an rc", "promote to stable", "publish v1.0.x", or anything similar - even if they don't name a specific version. **Also re-trigger when the user says the release PR is merged**, "continue the release", "finish the release", "PR is in - ship it", or re-asks about a release they already started; in that case skip to step 4 (Resume after the PR merges).
- Grade
- F
- Quality
- 45 / 100
- Safety
- Risky
- GitHub stars
- 37
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
- 96 / 100
- Maturity
- Basic: a single SKILL.md
- Security scan
- High-risk patterns
- License
- MIT
- Adoption
- Adopted by 0 other repositories, in 0 collections
What the scanner flagged
- references sensitive credential env
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.