Repository
antonbabenko/deliberation agent skills
- skills
- 9
- GitHub stars
- 169
GitHub description: “Ask Codex, Gemini, Grok, and 400+ OpenRouter models (Qwen, Kimi, DeepSeek) for second opinions or arbiter-mediated consensus. One MCP server for Claude Code, Codex, Cursor, Kiro, OpenCode. Measures the models' usefulness, too.”
- Stars
- 169 (11 forks)
- Licence
- MIT
- Last push
- Oct 2026
- Created
- May 2026
- claude-code
- code-review
- codex
- gemini
- grok
- llm
- plan-review
- security-review
- ai-agents
- ai-coding
- consensus
- multi-agent
- xai
- developer-tools
- mcp
- claude
Install all skills
npx skills add antonbabenko/deliberationAdd --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in antonbabenko/deliberation, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | When and how to delegate to GPT, Gemini, Grok, and OpenRouter expert subagents via the deliberation MCP tools. | antonbabenko/ | 169 | — | ~3.4k | Automated safety check: Pass | MIT | today |
| 2 | System design, tradeoffs, and complex technical decisions. An agent skill from antonbabenko/deliberation. | antonbabenko/ | 169 | — | ~1.4k | Automated safety check: Pass | MIT | today |
| 3 | Find bugs, security holes, and maintainability issues in a diff or file. | antonbabenko/ | 169 | — | ~881 | Automated safety check: Pass | MIT | today |
| 4 | 4.Debugger Rank root-cause hypotheses and propose the smallest safe fix. | antonbabenko/ | 169 | — | ~554 | Automated safety check: Pass | MIT | today |
| 5 | Validate that a work plan is executable before work starts. An agent skill from antonbabenko/deliberation. | antonbabenko/ | 169 | — | ~931 | Automated safety check: Pass | MIT | today |
| 6 | Research external libraries, APIs, and best practices, with evidence. | antonbabenko/ | 169 | — | ~840 | Automated safety check: Pass | MIT | today |
| 7 | Catch ambiguities and hidden requirements before planning. An agent skill from antonbabenko/deliberation. | antonbabenko/ | 169 | — | ~1.4k | Automated safety check: Pass | MIT | today |
| 8 | Threat-model and find vulnerabilities, with practical remediation. | antonbabenko/ | 169 | — | ~1.1k | Automated safety check: Pass | MIT | today |
| 9 | Gracefully cycle dashboard and audit MCP processes after deliberation is updated. | antonbabenko/ | 169 | — | ~208 | Automated safety check: Pass | MIT | today |
Questions, answered from the data.
What is the best skill in antonbabenko/deliberation?
Deliberation from antonbabenko/deliberation ranks first of the 9 skills in antonbabenko/deliberation listed here, with the highest score: its repository has 169 GitHub stars, its SKILL.md loads about 3.4k tokens and it passes the automated safety check with no findings. Next come Architect and Code Reviewer.
Are the skills in antonbabenko/deliberation official?
None yet. All 9 skills in antonbabenko/deliberation 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 antonbabenko/deliberation?
Run npx skills add antonbabenko/deliberation 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.