00 INDEX
95+ agent skills, 19 UI components, 7 system prompts from Claude Fable 5, GPT-5.5, Gemini CLI & more. Self-fine-tune your agent: paste one prompt and it reads every skill, internalizes patterns, and becomes elite. Works with Claude Code, Codex, Cursor, OpenCode + 60 more agents.From the repository description
npx -y skills add subhansh-dev/agent-maxxing --skill 00-INDEXAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
2.2 KB, 744 tokens by cl100k_base, as published. Nobody here has run it
Extra Skills — Agent & Workflow
| # | Skill | Purpose |
|---|---|---|
| 1 | Adapt | Self-adaptation to context |
| 2 | Arrange | Task arrangement and planning |
| 3 | Audit | Security/quality audit |
| 4 | Clarify | Clarification of ambiguity |
| 5 | Code Generator | Code generation |
| 6 | Distill | Summarization and distillation |
| 7 | Extract | Information extraction |
| 8 | Find Skills | Discover new skills |
| 9 | GitHub | GitHub CLI operations |
| 10 | Harden | Security hardening |
| 11 | Healthcheck | System health checks |
| 12 | Normalize | Data normalization |
| 13 | Onboard | Onboarding flows |
| 14 | Optimize | Performance optimization |
| 15 | Overdrive | Maximum effort mode |
| 16 | Quieter | Minimal/terse responses |
| 17 | Self Improvement | Agent self-improvement |
| 18 | Skill Creator | Create new skills |
| 19 | Skill Vetter | Review/vet skills |
| 20 | Skillhub Preference | Skillhub config |
| 21 | Spike | Quick spike/POC |
| 22 | Taskflow | Task workflow management |
| 23 | Taskflow Inbox Triage | Inbox triage |
| 24 | Teach Impeccable | Design context gathering |
| 25 | Node Inspect Debugger | Node.js debugging |
| 26 | Python Debugpy | Python debugging |
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.