본문으로 건너뛰기
cccskills
무료GitHub에 공개

memory-management

Recall earlier work and organize lasting preferences, project facts, outcomes, and lessons. The skill distinguishes concise memory from original records, reusable procedures that belong in skills, and recurring requests that need scheduled tasks.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

원문원문 설명 보기

Guide the agent to recall, remember, and route durable learning into Memory, Skills, Scheduled Tasks, or Tape.

설치 방법 보기

이럴 때 유용합니다

  • Resume earlier work using remembered context
  • Save lasting preferences and project conventions
  • Find exact wording and evidence in past records
  • Separate reusable procedures from recurring tasks

포함된 파일(1)

  • SKILL.md3.3 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

Memory Management

Use 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.

Recall

Rely 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.

Use 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.

Remember

Use memory_remember only for durable conclusions that should change future behavior. Choose the most specific category:

  • user_preference: stable user preferences, constraints, communication style, environment choices.
  • project_fact: durable project conventions, architecture entry points, commands, dependencies, paths, or operational constraints.
  • task_outcome: completed, blocked, or deliberately deferred task results. Include status, outcome, and blocker in prose when relevant.
  • heuristic: reusable troubleshooting strategy, workflow, decision rule, or engineering lesson.
  • anti_pattern: repeated mistake, unsafe approach, brittle pattern, stale assumption, or thing to avoid.

Do not remember raw tool results, bash output, grep output, file contents, transient mechanics, one-off failures, secrets, credentials, hidden reasoning, or anything only useful for the current turn.

Verbatim Scope

Store exact wording only when the user explicitly asks you to remember a sentence or phrase verbatim. In that case, keep the requested text intact and make the surrounding content minimal.

Automatic extraction is different: it should normalize durable facts into concise memory content, deduplicate related entries, and avoid preserving raw transcript text.

Procedures -> Skill

When the useful learning is a reusable multi-step procedure, prefer drafting a skill with skill_manage instead of stuffing the full procedure into Memory. Memory may keep a short pointer or heuristic, but the repeatable workflow belongs in a Skill.

Use skill_manage for draft skills only. Do not modify installed skills unless the user explicitly asks through the supported review flow.

Recurring -> Scheduled Task

When the user asks for a periodic, low-frequency, or future recurring action, suggest creating a Scheduled Task in settings. Memory does not wake the agent, schedule future work, or create automation side effects.

End-of-task Learning Check

Before finishing a non-trivial task, check whether there is one durable lesson to save:

  1. Did the user reveal a stable preference or constraint?
  2. Did you learn a durable project fact?
  3. Is there a task outcome, blocker, or explicit deferral worth preserving?
  4. Did a reusable heuristic work?
  5. Did an anti-pattern or stale assumption become clear?
  6. Is this actually a reusable procedure for skill_manage or a recurring need for Scheduled Tasks rather than Memory?

Remember only the smallest durable conclusion. Leave raw process in Tape.

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

Add an LLM provider to DeepChat by choosing a suitable API connection method, updating authentication and model configuration, and making focused source changes with tests for the affected behavior.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Adding an OpenAI-compatible provider
  • Connecting a provider through an existing transport
  • Implementing provider-specific authentication
ThinkInAIXYZ/deepchat6.4천2026년 10월 13일 업데이트

Create original generative art with p5.js, using code to produce patterns and motion. Receive a written artistic concept and an interactive HTML viewer with adjustable parameters, reproducible random variations, seed navigation, and PNG downloads.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Create art from particle motion and flow fields
  • Explore patterns by adjusting sliders
  • Reproduce a favorite variation with the same seed
ThinkInAIXYZ/deepchat6.4천2026년 10월 13일 업데이트

Review code for readability, maintainability, security, and performance. Receive an overview, issues grouped by severity, concrete improvements with code examples, and positive feedback on parts of the implementation that work well.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Reviewing an implementation before sharing it
  • Checking code for security weaknesses
  • Finding performance improvement opportunities
ThinkInAIXYZ/deepchat6.4천2026년 10월 13일 업데이트

Operate desktop applications through DeepChat's built-in Computer Use tools. Inspect windows, click controls, enter text, use menus, and arrange windows, checking the visible result after each action.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Entering text and using controls in desktop apps
  • Opening files or URLs in an application
  • Arranging application windows
ThinkInAIXYZ/deepchat6.4천2026년 10월 13일 업데이트

Use DeepChat's bundled command-line interface to compare models, generate media, transcribe audio, and extract text from images. Also inspect runtime status, artifact metadata, public settings, installed Skills, and MCP connections to external tools.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Comparing models and collecting benchmark results
  • Generating images, video, or speech
  • Transcribing audio and extracting text from images
ThinkInAIXYZ/deepchat6.4천2026년 10월 13일 업데이트

Build third-party tools to inspect, extract, migrate, or analyze DeepChat's local settings and conversations. Work through data locations, database encryption, and table relationships while favoring read-only copies and redacted output.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Building an importer for another application
  • Inspecting provider, model, and MCP settings
  • Extracting conversations for analysis
ThinkInAIXYZ/deepchat6.4천2026년 10월 13일 업데이트

ThinkInAIXYZ의 스킬 모두 보기

이 스킬의 문제 신고