Repository
zscole/adversarial-spec agent skills
- skill
- 1
- GitHub stars
- 556
GitHub description: “A Claude Code plugin that iteratively refines product specifications by debating between multiple LLMs until all models reach consensus.”
- Stars
- 556 (50 forks)
- Licence
- MIT
- Last push
- Jan 2026
- Created
- Jan 2026
- claude-ai
- claude-code
- anthropic
- claude-code-plugin
- claude-skills
- llm
- orchestration
Install all skills
npx skills add zscole/adversarial-specAdd --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in zscole/adversarial-spec, ranked
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Iteratively refine a product spec by debating with multiple LLMs (GPT, Gemini, Grok, etc.) until all models agree. | zscole/ | 556 | — | ~8.3k | Automated safety check: Notes | MIT | 8 mo ago |
Questions, answered from the data.
What is the best skill in zscole/adversarial-spec?
Adversarial Spec from zscole/adversarial-spec ranks first of the 1 skills in zscole/adversarial-spec listed here, with the highest score: its repository has 556 GitHub stars, its SKILL.md loads about 8.3k tokens and it has informational notes only in the automated safety check.
Are the skills in zscole/adversarial-spec official?
None yet. All 1 skills in zscole/adversarial-spec listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
How do I install all skills from zscole/adversarial-spec?
Run npx skills add zscole/adversarial-spec in your project: the open-source skills CLI installs the repository's skills into your coding agent's skills folder. To install a single skill, open its page here for the exact command.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.