Agent Skills Phoebe Picks — AI skill for Claude Code
Which AI agent Skills survive a real build.
How to install Agent Skills Phoebe Picks
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open phoebefu6/agent-skills-phoebe-picks and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Agent Skills Phoebe Picks does
Which AI agent Skills survive a real build? Every pick is field-tested by building a product from scratch, then rated on a public rubric - 15 published picks, 16 field tests, every demo live and open. by Phoebe Fu
Alternatives in AI
- Anthropic Quickstarts — by Anthropic - Offers comprehensive development guides for three distinct AI-powered demo projects with standa 15.4k ★
- Claw0 — 0 - 1 learn OpenClaw: sections to build an claw-AI agent from scratch 2.6k ★
- Obsidian + Claude Code: Rebuild Your Second Brain With AI — Build an AI-powered personal knowledge management system from scratch 540 ★
README
[](https://phoebefu6.github.io/agent-skills-phoebe-picks/) [](https://github.com/phoebefu6/agent-skills-phoebe-picks/stargazers)
▶︎ [Open the live gallery →](https://phoebefu6.github.io/agent-skills-phoebe-picks/)
Free and open. Every build links to its source.
Agent Skills Phoebe Picks
[](#published-products) [](#field-tested-artifacts) [](unexplored-wishlist.md) [](#repo-map)
A public shelf of AI agent Skills that survived a real build.
Instead of another long list of tools, this repo answers one practical question:
Which Skills are actually useful when you build with Codex, Claude Code, Hermes AI, and other AI agents?
Why Star This Repo
Star this repo if you want a growing shortlist of Skills that show their work:
- Exact Skill names, not vague tool lists.
- Demo proof built from scratch.
- Verified source repository, exact Skill path, and credibility gate.
- Rating, strengths, limits, and day
Related Skills
Key Learning
Field-agnostic AI tutor skill for Claude. Explains how and why from first principles, diagnoses your Bloom's t
Agent Config Harness
Agent instruction files, scored and regression-tested like code. CLAUDE.md / AGENTS.md / skills managed via a
Pear Skills
Battle-tested Agent Skills that give AI coding agents (ZCode, Claude Code, Cursor, etc.) plug-and-play domain
Claude Code Patterns
Field-tested Claude Code patterns & anti-patterns for personal agents — an AI workflow that compounds: knowled
Empire AI Best Practices
Field-tested runbook + Claude Code skill for the Empire AI Alpha cluster: SSH/TOTP auth pattern for agents, Sl
CodeJoust
Pit AI coding agents against the same bug. Score them on tests, diff, cost, and time — pick the winning patch.
Related Agents
Next Issue Finder
Scout for undirected /orc runs — surveys the GitHub issue board, picks the next issue with orc's four-signal r
Matcher
Score each queued role 0-100 against the profile using the scoring rubric; pick a resume category; flag inelig
Output Auditor
The quality gate. Scores artifacts against a published rubric, verifies every citation against the ledger, and