Skills for Real Engineers. Straight from my .agents directory.
memory-management
Agent skill fromThinkInAIXYZ/deepchat
Guide the agent to recall, remember, and route durable learning into Memory, Skills, Scheduled Tasks, or Tape.
How to install memory-management
npx skills add ThinkInAIXYZ/deepchat# or add only this skill to Claude Code: copy the folder
resources/skills/memory-management/
# into
~/.claude/skills/memory-management/ (all projects)
.claude/skills/memory-management/ (one project)
1# Memory Management23Use this skill when a task may produce durable learning or when the user asks you to recall, remember, continue earlier work, preserve an exact statement, capture a reusable procedure, or handle a recurring need.45## Recall67Rely on automatic memory injection for ordinary context. Use `memory_recall` when the user refers to previous work with cues such as again, last time, before, continue, same project, remember, or asks what you already know.89Use `tape_search` and then `tape_context` when the user needs source evidence, exact wording, logs, command output, file snippets, or why a prior decision was made. Memory is a durable conclusion layer, not the raw transcript.1011## Remember1213Use `memory_remember` only for durable conclusions that should change future behavior. Choose the most specific category:1415- `user_preference`: stable user preferences, constraints, communication style, environment choices.16- `project_fact`: durable project conventions, architecture entry points, commands, dependencies, paths, or operational constraints.17- `task_outcome`: completed, blocked, or deliberately deferred task results. Include status, outcome, and blocker in prose when relevant.18- `heuristic`: reusable troubleshooting strategy, workflow, decision rule, or engineering lesson.19- `anti_pattern`: repeated mistake, unsafe approach, brittle pattern, stale assumption, or thing to avoid.20…
Excerpt shown under the repository's Apache-2.0 license.
More skills in deepchat
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
