stabilize
stabilize is an Execution & autonomous loops skill for AI agents, published by daintreehq in the daintree repository on GitHub. Skillspace rates stabilize 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.
USE ONLY WHEN A HUMAN EXPLICITLY INVOKES IT — never auto-select or run this proactively: not after adding a feature, fixing a bug, or finishing a task, not as a routine or ambient health check, and not as a step inside another workflow. This is a deliberate, multi-hour overnight workflow. Once a human explicitly starts it with /stabilize (Claude Code) or $stabilize (Codex) — typically the night before a release, or as a one-off whole-tree validation — it drives Daintree to a fully green, stable state across every check we can run: typecheck/lint/format, unit, integration, knip, build, smoke, and the full Playwright E2E surface (core, all seven full-* buckets, online, and the nightly memory-leak soak). Local-first and strictly serial by OS — the local Mac (macOS) to green first, then the cross-platform stabilize.yml GitHub workflow one OS at a time, Linux to green then Windows to green — fixing real failures and intelligently re-running flaky E2E at each stage, plus release dry-runs…
- Grade
- F
- Quality
- 45 / 100
- Safety
- Risky
- GitHub stars
- 48
Unproven: rated by static analysis only, not yet compared head-to-head.
Our two independent classifiers differ on this skill's category, so treat the placement as provisional.
This rating describes the version of the repository we crawled; it may have changed since.
Our review
- Architecture
- 80 / 100
- Maturity
- Basic: a single SKILL.md
- Security scan
- High-risk patterns
- License
- Not declared. Check the repository before reusing it.
- Adoption
- Adopted by 0 other repositories, in 0 collections
What the scanner flagged
- references sensitive credential env
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.