spike-and-stabilize
spike-and-stabilize is a Test-driven development skill for AI agents, published by msbaek in the dotfiles repository on GitHub. Skillspace rates spike-and-stabilize D (59/100) and it passed the safety scan; the rating is based on static analysis only.
Use when user explicitly triggers spike mode for uncertain problems. Trigger phrases (any of these signals intent): "/spike", "스파이크로 가자", "퀵 앤 더티로 한 번 풀어보자", "일단 끝까지 한 번 가보자", "tracer bullet", "학습용으로 한 번 만들어보자". Fuzzy match: phrases meaning "let's try it once end-to-end quickly" or "explore before building properly" also qualify. Apply only when domain or solution path is uncertain — NOT for simple CRUD, clearly-specified features, or straightforward additions. NEVER auto-trigger: requires explicit user signal. Two-phase: Phase 1 (quick & dirty E2E + acceptance test as safety net) -> Transition Gate (explicit user approval) -> Phase 2 (stabilize via superpowers:writing-plans + superpowers:executing-plans).
- Grade
- D
- Quality
- 59 / 100
- Safety
- Passed
- GitHub stars
- 40
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, so go by its current files.
Our review
- Architecture
- 84 / 100
- Maturity
- Basic: a single SKILL.md
- Security scan
- No issues found
- License
- Not declared. Check the repository before reusing it.
- Adoption
- Adopted by 0 other repositories, in 0 collections
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.