continual-learning agents

249 tagged continual-learning, measured the same way as everything else here.

letta-ai/letta-code

Instructions file CodexOpenCode

AGENTS.md instructions for letta-ai/letta-code, covering letta-code — agent guide, workflow, runtime validation, rules and why they exist and no ../ parent imports — use @/.

3.2k +22 today A 10,832 tokens original Apache-2.0

letta-ai/letta-code

Instructions file

Claude Code instructions for letta-ai/letta-code, a project described as: Stateful agents that are like people, with memory, identity, and the ability to learn and adapt.

3.2k +22 today A 3 tokens copy · 100% Apache-2.0

creating-skills

04

letta-ai/letta-code

Skill Claude CodeCodex

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Letta Code's capabilities with specialized knowledge, workflows, or tool integrations.

3.2k +22 today A 47 tokens original Apache-2.0

letta-ai/letta-code

Skill Claude CodeCodex

Dispatch stateless coding agents through Claude Code or Codex. Model catalog checked 2026-08-25: Claude Code includes Sonnet 5, Opus 5, and Fable 5; Codex includes GPT-5.6 Luna, Terra, and Sol. Use when you're stuck, need a second opinion, or need parallel research on a hard problem. They have no memory, so you must…

3.2k +22 today A 0 tokens original Apache-2.0

initializing-memory

06

letta-ai/letta-code

Skill Claude CodeCodex

Comprehensive guide for initializing or reorganizing agent memory. Load this skill when running /init, when the user asks you to set up your memory, or when you need guidance on creating effective memory files.

3.2k +22 today A 45 tokens original Apache-2.0

a-evolve CLAUDE.md

07

A-EVO-Lab/a-evolve

Instructions file

Claude Code instructions for A-EVO-Lab/a-evolve, covering claude.md, project overview, repository structure, arc-agi-3 key concepts and game environment (arc-agi sdk).

769 +4 11d ago A 1,475 tokens

harness-optimizer

08

A-EVO-Lab/a-evolve

Skill Claude CodeCodex

Optimize an AI agent's harness for MCP-Atlas benchmark. Use when analyzing execution traces, diagnosing failures, and proposing improved prompts, skills, or harness code.

769 +4 11d ago A 37 tokens

A-EVO-Lab/a-evolve

Skill Claude CodeCodex

When to prefer GUI mouse clicks over keyboard shortcuts — especially for formatting, multi-step visual tasks, and cross-application workflows.

769 +4 11d ago A 31 tokens

data-formats

10

A-EVO-Lab/a-evolve

Skill Claude CodeCodex

Reading, writing, and converting common data formats (CSV, Excel, JSON, YAML) with correct handling of encoding, types, and edge cases.

769 +4 11d ago A 34 tokens

slack-gif-creator

11

ECNU-ICALK/AutoSkill

Skill Claude CodeCodex

Toolkit for creating animated GIFs optimized for Slack, with validators for size constraints and composable animation primitives. This skill applies when users request animated GIFs or emoji animations for Slack from descriptions like "make me a GIF for Slack of X doing Y".

570 +2 3mo ago A 57 tokens

algorithmic-art

12

ECNU-ICALK/AutoSkill

Skill Claude CodeCodex

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright…

570 +2 3mo ago A 62 tokens

skill-creator

13

ECNU-ICALK/AutoSkill

Skill Claude CodeCodex

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

570 +2 3mo ago A 63 tokens

analyzer

14

ECNU-ICALK/AutoSkill

Agent

Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.

570 +2 3mo ago A 0 tokens

grader

16

ECNU-ICALK/AutoSkill

Agent

Evaluate expectations against an execution transcript and outputs.

570 +2 3mo ago A 0 tokens

ECNU-ICALK/AutoSkill

Plugin Claude Code

Plugin marketplace listing 3 plugins: content-skills, ai-generation-skills, utility-skills.

570 +2 3mo ago A tokens not measured

stash AGENTS.md

18

Fergana-Labs/stash

Instructions file CodexOpenCode

Instructions for Fergana-Labs/stash, a project described as: Automatically create new skills based on past agent traces.

327 4d ago A 4 tokens copy · 100% MIT

stash CLAUDE.md

19

Fergana-Labs/stash

Instructions file

Instructions for Fergana-Labs/stash, covering write simple code, be self-sufficient, pr hygiene, stash and what a skill is.

327 4d ago A 3,428 tokens original MIT

static

20

Fergana-Labs/stash

Skill Claude CodeCodex

Stash is your personal home for agent work. Everything you create is scoped to your account — it is yours alone, with nothing to pick or set up first. Your Stash has three primary surfaces.

327 4d ago A 0 tokens original MIT

brief

21

Fergana-Labs/stash

Skill Claude CodeCodex

Brief the user on what they saved in a period — the thread running through it, not a list.

327 4d ago A 23 tokens original MIT

slides

22

Fergana-Labs/stash

Skill Claude CodeCodex

How to build presentation slide decks as HTML pages. Covers the slide format, canvas dimensions, and recommended libraries.

327 4d ago A 24 tokens original MIT

claude-plugin

23

Fergana-Labs/stash

Plugin Claude Code

Connect Claude Code to Stash — stream activity to your Stash and collaborate with your other agents.

327 4d ago A tokens not measured original MIT

SessionStart

24

Fergana-Labs/stash

Hook

Runs when a session starts, executing ensure_cli.sh via bash. From Fergana-Labs/stash.

327 4d ago A tokens not measured original MIT

At most 3 mods per repository are shown here — the rest are on their repository pages: