End-to-end Sophia competency self-review assistant — phased chat that configures auth + MCPs, harvests a year of evidence in parallel, builds an evidence map, surfaces next-level rubric differentials, drafts rubric-aligned answers, and submits + verifies them via the Sophia API.
A personal library of AI agent skills for Claude Code and other harnesses.
ai-agent-skills/
├── .claude-plugin/
│ └── marketplace.json Plugin marketplace catalog — lists all installable plugins
├── skills/ Standalone skills — one per directory
│ └── <skill-name>/
│ ├── <skill-name>.md Skill definition
│ └── .claude-plugin/
│ └── plugin.json Plugin manifest
| Skill | File | Description |
|---|---|---|
delegate | skills/delegate/delegate.md | Delegates grunt work (search, review, refactor, tests) to opencode running free LiteLLM models. Saves Claude tokens by routing non-reasoning tasks to free models. |
sophia-review | skills/sophia-review/sophia-review.md | End-to-end Sophia competency self-review assistant. Phased chat: configures auth + MCPs, harvests a year of evidence (GitHub/Plane/Slack/Calendar/Claude+Cursor sessions) in parallel, builds an evidence map, surfaces next-level rubric differentials, asks targeted gap questions, drafts rubric-aligned answers, and submits + verifies them via the Sophia API. |
Step 1 — Add marketplace (one-time)
/plugin marketplace add Waleed-Mujahid/ai-agent-skills
Step 2 — Install a skill
/plugin install delegate@ai-agent-skills
/plugin install sophia-review@ai-agent-skills
Keep up to date:
/plugin marketplace update ai-agent-skills
Pull directly into your project:
mkdir -p .cursor/rules
gh api repos/Waleed-Mujahid/ai-agent-skills/contents/skills/delegate/delegate.md \
--jq '.content' | base64 --decode > .cursor/rules/delegate.mdc
Standalone Skill:
skills/
└── my-new-skill/
├── my-new-skill.md
└── .claude-plugin/
└── plugin.json
{
"name": "my-new-skill",
"description": "One sentence: what this skill does and when to use it.",
"version": "1.0.0",
"author": {
"name": "First Last (github_username)"
},
"commands": ["./my-new-skill.md"]
}
skills/my-new-skill/ with my-new-skill.md and .claude-plugin/plugin.json.my-new-skill.md:---
name: my-new-skill
description: "<one sentence describing what this skill does and when to use it>"
---
.claude-plugin/marketplace.json.Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub waleed-mujahid/ai-agent-skills --plugin sophia-reviewDelegates grunt work (search, review, refactor, tests) to opencode running free LiteLLM models — saves Claude tokens.
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.
Next.js development expertise with skills for App Router, Server Components, Route Handlers, Server Actions, and authentication patterns
Comprehensive .NET development skills for modern C#, ASP.NET, MAUI, Blazor, Aspire, EF Core, Native AOT, testing, security, performance optimization, CI/CD, and cloud-native applications
Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, and rules evolved over 10+ months of intensive daily use