Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Skills for AI agents
| Date | Stars |
|---|---|
| 2026-07-31 | 270 |
| 2026-08-11 | 273 |
| 2026-08-18 | 280 |
| 2026-08-19 | 280 |
| 2026-08-21 | 281 |
| 2026-08-23 | 282 |
| 2026-08-24 | 284 |
| 2026-08-26 | 285 |
| 2026-08-27 | 284 |
| 2026-08-28 | 285 |
| 2026-08-29 | 287 |
| 2026-08-31 | 288 |
| 2026-09-01 | 289 |
| 2026-09-02 | 290 |
| 2026-09-04 | 291 |
| 2026-09-05 | 292 |
| 2026-09-08 | 293 |
| 2026-09-10 | 294 |
| 2026-09-12 | 295 |
| 2026-09-15 | 295 |
| 2026-09-17 | 296 |
| 2026-09-18 | 298 |
| 2026-09-19 | 300 |
| 2026-09-20 | 302 |
Today
+2 stars today
This week
+7 stars this week
This month
+21 stars this month
Momentum
15.0
growth rate 2.37%/day
# pskoett-ai-skills A collection of skills for AI agents. Follows the [Agent Skills specification](https://agentskills.io/specification) and ships an [Agent Plugins 1.0](https://agent-plugins.org/specification) portable package. This repository is my personal skill testing ground. ## Philosophy Every skill in this collection is built around a philosophy — a principle that addresses a specific failure mode in how agents work today. `plan-interview` is about collaborative planning: before codebase exploration starts, user and agent run a structured interview to align on constraints, scope, risk, and success criteria — and to surface whether a preparatory refactor should come before the main change. `intent-framed-agent` makes execution intent explicit so scope drift becomes visible. `context-surfing` monitors context quality and exits cleanly before degradation corrupts output. `verify-gate` runs compile, test, and lint checks so the agent doesn't need you to tell it the output was wrong if a test can. `self-healing` turns mid-task failures into verified, reusable artifacts instead of swept-under-the-rug retries. `simplify-and-harden` uses the peak context at end-of-task for a focused quality and security review. `self-improvement` turns repeated mistakes into durable rules that persist across sessions. The common thread: agents have peak context at specific moments — after planning, mid-execution, at completion, after learning — and these skills are designed to exploit those peaks. Each skill encodes a philosophy that agents struggle to internalize on their own, turning it into a structured workflow they can follow reliably. If you want to improve agent output over time, you need two loops, not one. The inner loop catches failures during a running session: the agent detects a problem, verifies its work against machine signals, and — with `self-healing` — recovers, files the verified fix as a reusable artifact, and continues, without you touching anything. The outer loop closes gaps across sessions: you capture where the agent failed, figure out what knowledge was missing, and encode it somewhere the agent can reach next time. `learning-aggregator` reads accumulated learnings across sessions and surfaces patterns. `harness-updater` encodes those patterns as permanent rules in project instruction files. `eval-creator` turns promoted rules into regression tests. `pre-flight-check` surfaces all of this at the start of the next session — closing the loop. The knowledge gaps get smaller with every cycle as it compounds. `skill-pipeline` ties these pieces together by classifying the task and routing it through the right combination at the right depth. One skill sits outside the two loops by design: `control-session-orchestrator` is an orchestration-layer skill, not an inner/outer-loop step. It runs *above* the pipeline — coordinating multi-agent, multi-session work from a Codex, Copilot, or agent-app control session — and is invoked directly rather than routed by `skill-pipeline`. ## Install ### Agent Plugins 1.0 The portable package entrypoint is [`agent-plugin/plugin.json`](agent-plugin/plugin.json). Point an Agent Plugins-compatible client or packager at the `agent-plugin/` directory. The portable package contains the curated Agent Skills bundle only. Agent Plugins 1.0 does not standardize hooks, agents, commands, or installation UX, so the native Claude Code, Codex, and GitHub Copilot adapters below remain the supported way to load those client-specific capabilities. A `hooks/` directory inside an individual portable skill is a skill resource, not an automatically registered plugin hook. This repository does not publish a portable `mcp.json` because it provides no MCP server. ### Claude Code Install as a Claude Code plugin from this repo's marketplace. Run each command from inside Claude Code: 1. Register this repo as a plugin marketplace: ``` /plugin marketplace add pskoett/pskoett-skills ``` 2. Install the
Excerpt of 17,734 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:a9ad2dc1f7c7e69d, llm:Repository name and description: 'pskoett-ai-skills' with description 'Skills for AI agents' (no README provided).