memory-manage

Name: memory-manage
Author: IIIIQIIII

38stars2forks

How to install memory-manage?

iiiiqiiii/memoryagent/memory-manage

$npx -y skills add IIIIQIIII/MemoryAgent --skill memory-manage

Installs into the current project.

Summary

Manage agent memory stored as files. Record, recall, search, update, and analyze memory content. Supports exploratory analysis for building context before complex tasks.

Files · 1

View on GitHub

SKILL.md

1	# Memory Management Skill
2
3	A Claude Code skill that implements the Memory as File concept — treating conversation knowledge as persistent files, managed entirely through the Coding Agent's native tools.
4
5	## Default Behavior
6
7	- Default memory file: `memory.txt` in the current working directory
8	- The user can specify a custom file path as the last argument to any command
9	- If the memory file does not exist yet, create it automatically on the first `record`
10
11	## Commands
12
13	Parse `$ARGUMENTS` to determine which operation to perform. The first word is the command, the rest are arguments.
14
15	### `recall` — Read Memory
16
17	Usage: `/memory recall [file]`
18
19	Read the full contents of the memory file using the Read tool and display it to the user.
20
21	- If the file does not exist, inform the user that no memory has been recorded yet.
22	- If the file is large (over 200 lines), provide a summary of its structure first, then ask if the user wants the full content.
23
24	### `record` — Append to Memory
25
26	Usage: `/memory record <content> [file]`
27
28	Append new information to the memory file.
29
30	Format each entry as:
31	```
32	## [YYYY-MM-DD HH:MM] <short topic>
33	<content>
34	```
35
36	- Use the current date and time for the timestamp
37	- Derive a short topic label (3-5 words) from the content
38	- If the file does not exist, create it with a header line: `# Memory File`
39	- Use the Read tool to get existing content, then Write to append the new entry
40	- Do NOT overwrite existing content — always append
41
42	### `update` — Modify Memory
43
44	Usage: `/memory update <old> -> <new> [file]`
45
46	Replace specific content in the memory file.
47
48	- Use the Read tool to find the content
49	- Use the Edit tool to perform the replacement
50	- Confirm the change to the user by showing the before and after
51
52	### `search` — Search Memory
53
54	Usage: `/memory search <query> [file]`
55
56	Search the memory file for matching content.
57
58	- Use the Grep tool to find lines matching the query
59	- Display matching entries with surrounding context (2 lines before and after)
60	- If no matches are found, suggest alternative search terms based on the query
61
62	### `forget` — Remove from Memory
63
64	Usage: `/memory forget <content> [file]`
65
66	Remove specific content from the memory file.
67
68	- Use the Read tool to locate the content
69	- Use the Edit tool to remove the matching section (including its timestamp header if it is a complete entry)
70	- Confirm what was removed
71
72	### `analyze` — Exploratory Analysis
73
74	Usage: `/memory analyze [file]`
75
76	This is the most important command. Perform a comprehensive exploratory analysis of the memory file to build context for subsequent work.
77
78	Steps:
79	1. Read the entire memory file using the Read tool
80	2. Produce a structured analysis report with the following sections:
81
82	```
83	## Memory Analysis Report
84
85	### Summary
86	One-paragraph overview of what the memory contains — its scope, depth, and overall theme.
87
88	### Topics
89	Bulleted list of distinct topics and themes found in the memory, ordered by frequency or importance.
90
91	### Key Entities
92	People, projects, tools, technologies, and decisions mentioned. Group by category.
93
94	### Timeline
95	Chronological progression of events or knowledge, if timestamps or temporal references exist.
96
97	### Relationships
98	Connections between topics — how different pieces of memory relate to each other.
99
100	### Knowledge Gaps
101	What information is missing, incomplete, or unclear. What questions remain unanswered.
102
103	### Suggested Next Steps
104	Concrete, actionable recommendations for what the agent (or user) could do next based on the memory content. These should be specific enough to serve as task descriptions.
105	```
106
107	3. This report is designed to give the agent (or a sub-agent) a basic info foundation — enough context to understand the situation and continue working on downstream tasks without needing to re-read the full memory file.
108
109	## When No Command Is Specified
110
111	If `/memory` is invoked without arguments or with an unrecognized command:
112	- Display a brief help message listing all available commands with one-line descriptions
113	- Default to `analyze` if the memory file exists, or inform the user to start with `record` if it does not
114
115	## Design Principles
116
117	- Files are memory — all knowledge is persisted as human-readable text files
118	- Native tools only — use Read, Write, Edit, Grep, and Glob; no external dependencies
119	- Human-auditable — users can open and edit memory files directly at any time
120	- Timestamp everything — every recorded entry gets a timestamp for chronological tracking
121	- Analyze before acting — the `analyze` command provides the foundation for informed decision-making

People who liked this also viewed

6 picks

Type

lark-drive飞书云空间（云盘/云存储）：管理 Drive 文件和文件夹，包含上传/下载、创建文件夹、复制/移动/删除、查看元数据、评论/权限/订阅、标题、版本、飞书文档密级标签（secure labels）和本地文件导入。用户需要整理云盘目录、处理云空间资源 URL/token、判断链接类型/真实 token/标题，或导入 Word/Markdown/Excel/CSV/PPTX/.base 为 docx/sSkillsJul 2026382k16k
lark-sharedUse for lark-cli setup/auth tasks: auth login/status/logout, user vs bot identity, business-domain permissions (--domain, including all/docs/drive), missing scopes, revoking authorization, or handlingSkillsJul 2026382k16k
lark-whiteboard飞书画板：查询和编辑飞书云文档中的画板。支持导出画板为预览图片、导出原始节点结构、使用多种格式更新画板内容。当用户需要查看画板内容、导出画板图片、编辑画板时使用此 skill。不负责：飞书云文档内容编辑（lark-doc）、文档内嵌电子表格/Base（lark-sheets / lark-base）。SkillsJul 2026380k16k
lark-task飞书任务：管理任务、清单和任务智能体。创建待办任务、查看和更新任务状态、拆分子任务、组织任务清单、分配协作成员、上传任务附件、注册或注销任务智能体、更新任务智能体的主页数据、写入智能体任务记录。当用户需要创建待办事项、查看任务列表、跟踪任务进度、管理项目清单或给他人分配任务、为任务上传附件文件、注册注销任务智能体、更新智能体主页数据、写入任务记录时使用。SkillsJul 2026380k16k
lark-attendance飞书考勤打卡：查询自己的考勤打卡记录SkillsJul 2026330k16k
lark-apps妙搭（Spark/Miaoda）应用开发与托管：应用创建、本地全栈开发、云端生成迭代、创意设计（UI mockup / 可交互原型 / 线框图 / 落地页 / 仪表盘 / 幻灯片 deck / 视觉探索）、AI相关能力和飞书平台能力或者其他外部能力集成、日志/Trace/监控指标/PV/UV 查询、环境变量管理、应用角色与成员管理、自动化触发器（定时/记录变更/Webhook/飞书审批）。当用户要SkillsJul 2026227k16k

memory-manage

38stars2forks

View on GitHub

How to install memory-manage?

iiiiqiiii/memoryagent/memory-manage

$npx -y skills add IIIIQIIII/MemoryAgent --skill memory-manage

Installs into the current project.

Summary

Manage agent memory stored as files. Record, recall, search, update, and analyze memory content. Supports exploratory analysis for building context before complex tasks.

Files · 1

View on GitHub

SKILL.md

1	# Memory Management Skill
2
3	A Claude Code skill that implements the Memory as File concept — treating conversation knowledge as persistent files, managed entirely through the Coding Agent's native tools.
4
5	## Default Behavior
6
7	- Default memory file: `memory.txt` in the current working directory
8	- The user can specify a custom file path as the last argument to any command
9	- If the memory file does not exist yet, create it automatically on the first `record`
10
11	## Commands
12
13	Parse `$ARGUMENTS` to determine which operation to perform. The first word is the command, the rest are arguments.
14
15	### `recall` — Read Memory
16
17	Usage: `/memory recall [file]`
18
19	Read the full contents of the memory file using the Read tool and display it to the user.
20
21	- If the file does not exist, inform the user that no memory has been recorded yet.
22	- If the file is large (over 200 lines), provide a summary of its structure first, then ask if the user wants the full content.
23
24	### `record` — Append to Memory
25
26	Usage: `/memory record <content> [file]`
27
28	Append new information to the memory file.
29
30	Format each entry as:
31	```
32	## [YYYY-MM-DD HH:MM] <short topic>
33	<content>
34	```
35
36	- Use the current date and time for the timestamp
37	- Derive a short topic label (3-5 words) from the content
38	- If the file does not exist, create it with a header line: `# Memory File`
39	- Use the Read tool to get existing content, then Write to append the new entry
40	- Do NOT overwrite existing content — always append
41
42	### `update` — Modify Memory
43
44	Usage: `/memory update <old> -> <new> [file]`
45
46	Replace specific content in the memory file.
47
48	- Use the Read tool to find the content
49	- Use the Edit tool to perform the replacement
50	- Confirm the change to the user by showing the before and after
51
52	### `search` — Search Memory
53
54	Usage: `/memory search <query> [file]`
55
56	Search the memory file for matching content.
57
58	- Use the Grep tool to find lines matching the query
59	- Display matching entries with surrounding context (2 lines before and after)
60	- If no matches are found, suggest alternative search terms based on the query
61
62	### `forget` — Remove from Memory
63
64	Usage: `/memory forget <content> [file]`
65
66	Remove specific content from the memory file.
67
68	- Use the Read tool to locate the content
69	- Use the Edit tool to remove the matching section (including its timestamp header if it is a complete entry)
70	- Confirm what was removed
71
72	### `analyze` — Exploratory Analysis
73
74	Usage: `/memory analyze [file]`
75
76	This is the most important command. Perform a comprehensive exploratory analysis of the memory file to build context for subsequent work.
77
78	Steps:
79	1. Read the entire memory file using the Read tool
80	2. Produce a structured analysis report with the following sections:
81
82	```
83	## Memory Analysis Report
84
85	### Summary
86	One-paragraph overview of what the memory contains — its scope, depth, and overall theme.
87
88	### Topics
89	Bulleted list of distinct topics and themes found in the memory, ordered by frequency or importance.
90
91	### Key Entities
92	People, projects, tools, technologies, and decisions mentioned. Group by category.
93
94	### Timeline
95	Chronological progression of events or knowledge, if timestamps or temporal references exist.
96
97	### Relationships
98	Connections between topics — how different pieces of memory relate to each other.
99
100	### Knowledge Gaps
101	What information is missing, incomplete, or unclear. What questions remain unanswered.
102
103	### Suggested Next Steps
104	Concrete, actionable recommendations for what the agent (or user) could do next based on the memory content. These should be specific enough to serve as task descriptions.
105	```
106
107	3. This report is designed to give the agent (or a sub-agent) a basic info foundation — enough context to understand the situation and continue working on downstream tasks without needing to re-read the full memory file.
108
109	## When No Command Is Specified
110
111	If `/memory` is invoked without arguments or with an unrecognized command:
112	- Display a brief help message listing all available commands with one-line descriptions
113	- Default to `analyze` if the memory file exists, or inform the user to start with `record` if it does not
114
115	## Design Principles
116
117	- Files are memory — all knowledge is persisted as human-readable text files
118	- Native tools only — use Read, Write, Edit, Grep, and Glob; no external dependencies
119	- Human-auditable — users can open and edit memory files directly at any time
120	- Timestamp everything — every recorded entry gets a timestamp for chronological tracking
121	- Analyze before acting — the `analyze` command provides the foundation for informed decision-making

People who liked this also viewed

6 picks

Type