slim-project-memoryUse when a project's project memory file is over ~300 lines, when starting a new project from scratch, or when the user mentions context bloat, lost env URLs...
Install via ClawdBot CLI:
clawdbot install adelvillar1/slim-project-memoryGrade Limited — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
http://localhost:3000Audited May 10, 2026 · audit v1.0
Generated Jul 31, 2026
A team of developers notices their CLAUDE.md has grown to over 2,000 lines, causing high token usage and slow session starts. They use this skill to audit, restructure into a slim router-style file, and offload reference material to topical docs/ files, reducing context load by 80%.
An indie developer begins a new SaaS project and wants to avoid future context bloat. They use NEW mode to initialize a CLAUDE.md with hard rules, branch topology, env var references in gitignored CLAUDE.local.md, and a docs/ tree from day one, ensuring clean project memory from the start.
A development team frequently loses track of which environment variables to use for different deployment stages (develop, staging, production). The skill centralizes env var name references into a gitignored file, reducing misconfiguration and session errors.
A growing startup onboards a new engineer who needs to quickly understand project topology and housekeeping rules. The slim CLAUDE.md acts as a clear entry point, with pointers to docs/ for deep dives, accelerating onboarding while keeping the memory file maintainable.
A team inherits a legacy codebase with a massive, disorganized project memory file that mixes technical specs, session logs, and environment details. They use EXISTING mode to systematically categorize and move content into a structured docs/ tree, improving project maintainability and AI agent performance.
The skill is released under MIT license, attracting users who then purchase consulting services from the author for custom implementations, team training, or integration into existing workflows.
The basic skill package is free, but premium templates (e.g., for large enterprises with complex multi-branch setups or custom housekeeping protocols) are sold as add-ons.
The skill is packaged as a plugin for AI agent platforms like Claude or Copilot, where platform users pay for access to curated skill libraries; revenue shared with skill authors.
💬 Integration Tip
Before running, identify if the project already has a CLAUDE.md or .gitignore; copying the templates from references/ may require path adjustment if your environment doesn't include them.
Scored Jun 3, 2026
Meta-skill for AI agent self-improvement. Analyzes runtime logs to detect error patterns, regressions, and inefficiencies, then generates structured improvem...
Stop waiting for prompts. Keep working.
Turn OpenClaw into a learning-loop agent with seeded workspace rules, skill promotion, reflective memory, and proactive maintenance.
Meta-agent skill for orchestrating complex tasks through autonomous sub-agents. Decomposes macro tasks into subtasks, spawns specialized sub-agents with dynamically generated SKILL.md files, coordinates file-based communication, consolidates results, and dissolves agents upon completion. MANDATORY TRIGGERS: orchestrate, multi-agent, decompose task, spawn agents, sub-agents, parallel agents, agent coordination, task breakdown, meta-agent, agent factory, delegate tasks
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 Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Complete toolkit for creating autonomous AI agents and managing Discord channels for OpenClaw. Use when setting up multi-agent systems, creating new agents, or managing Discord channel organization.