LLM Skills
HiggsfieldGenerate images and videos from a single promptTry HiggsfieldSponsored
~/catalog/specialized ai agents//memory-manager

Memory Manager

/memory-manager

Local memory management for agents. Compression detection, auto-snapshots, and semantic search. Use when agents need to detect compression risk before memory loss, save context snapshots, search historical memories, or t

ClawHub communityClawHub community
★93
May 11, 2026
// skill content

Skill created by the community and listed at ClawHub. Canonical source: https://clawhub.ai/skills/memory-manager Version: 1.0.0 Source changelog: Initial release: Semantic/procedural/episodic memory architecture for agents. Knowledge graphs outperform flat retrieval by 18.5%. Never lose context again.

// original public source
https://clawhub.ai/skills/memory-manager
License: License not specified. Review the repository before reusing it.
Independent project, not affiliated with Anthropic. This skill remains the property of its original author.
// install this skill
Paste this command in your terminal at the root of your project:
mkdir -p .claude/commands && curl -o ".claude/commands/memory-manager" "https://clawhub.ai/skills/memory-manager"
Then in Claude Code, type /memory-manager to activate it.
open_in_newOpen original source
// save
Save available after sign in.
loginSign in to save
// information
Stars★ 93
UpdatedMay 11, 2026
Format.md
AccessFree
HiggsfieldSponsored

AI avatars that stay themselves

Give your projects a face: build a consistent AI character, keep it identical from one video to the next, change the outfit, the set or the scene without ever losing the likeness.

Create an avatar
// similar

Skills Specialized AI agents

View allarrow_forward

Subagent Driven Development

★305.3k

Execute plan by dispatching fresh subagent per task, with two-stage review after each: spec compliance review first, then code quality review.

Specialized AI agents
Agentobra

Requesting Code Review

★305.3k

Dispatch a code reviewer subagent to catch issues before they cascade. The reviewer gets precisely crafted context for evaluation - never your session's history. This keeps the reviewer focused on t

Specialized AI agents
obra

Dispatching Parallel Agents

★305.3k

You delegate tasks to specialized agents with isolated context. By precisely crafting their instructions and context, you ensure they stay focused and succeed at their task. They should never inherit

Specialized AI agents
Agentobra

Autonomous Loops

★289.2k

Models and architectures for Claude Code autonomous loops, from simple sequential pipelines to RFC-driven multi-agent DAG systems.

Specialized AI agents
Agentaffaan-m