M
milad-ahmd/agent-memory-keeper
🧠 Project memory (MEMORY.md) plus session handoffs (HANDOFF.md) so the next session picks up where this one…
在 GitHub 查看 ↗链接已于 2026-11-12 核查 · HTTP 200 · 打开的是厂商自己的官网
- ★ 数取值
- 0 ★ · milad-ahmd/agent-memory-keeper · 取自 GitHub 搜索 API · (2026-11-13 20:00:50 核对)
- 来源明细
- 从该仓库的 GitHub 页面直接读取 · 条目类型:开源项目
- 收录与活跃
- 收录于 2026-10-30 · 最近见到 2026-11-14 · 共见到 16 次 · 被 1 个来源列出
- 评分构成
- 综合分 103 · 1 个来源 · repo
常见问题(答案都来自我们的记录)
它适合谁 / 用来做什么?
我们把它归在这些标签下: Agent 技能。标签来自条目自身,不是我们强加的分类。
谁维护它、还在更新吗?
仓库
milad-ahmd/agent-memory-keeper;我们收录于 2026-10-30;最近见到 2026-11-14。这里没有"官方认证"或"质量评级"——我们只记录来源与时间。> [!NOTE]
以下摘录自该仓库的 README(片段) · 在 GitHub 读完整 README →
> This skill lives in the main collection: milad-ahmd/agent-skills. Please ⭐ star it there; that's where updates land first.
> Docs: https://milad-ahmd.github.io/agent-skills/skills/agent-memory-keeper/ · Claude Code: /plugin install all-skills --marketplace milad-ahmd/agent-skills
# 🧠 agent-memory-keeper
Project memory (MEMORY.md) plus session handoffs (HANDOFF.md) so the next session picks up where this one stopped. An Agent Skill for Claude Code, Cline, Cursor, Codex and other AI coding agents.
Install · Usage · How it works · All skills
> Part of agent-skills, a growing collection of practical skills for AI coding agents.
## 📦 Install
One command (installs the whole collection):
bash
curl -fsSL https://raw.githubusercontent.com/milad-ahmd/agent-skills/main/install.sh | bash -s -- agent-memory-keeper
Manually (Claude Code):
bash
git clone https://github.com/milad-ahmd/agent-memory-keeper /tmp/agent-memory-keeper
mkdir -p ~/.claude/skills && cp -r /tmp/agent-memory-keeper/skills/agent-memory-keeper ~/.claude/skills/
Per project: copy skills/agent-memory-keeper into /.claude/skills/.
Any other agent: paste SKILL.md into your rules or system prompt.
## 💬 Usage
Just ask your agent:
text
Remember that we use pnpm, not npm
Write a handoff, I'm running out of context
The full workflow, rules and output format are in SKILL.md.
## 🔎 Sample output
handoff.py is plain Python 3 with no dependencies and never touches your working tree. Real output halfway through a bug fix:
text
$ python3 handoff.py
Handoff facts for ~/code/shop
Repo: shop
Branch: fix/discount-rounding
HEAD: aa578d8 test: failing case for per-line discount rounding
Upstream: none
Base: main (merge-base f496d7e; 1 commits on this branch, 1 files changed)
In progress: none
Stash: 0
Uncommitted: 1 (0 staged, 1 unstaged, 0 untracked, 0 conflicted)
.M cart.py
Commits on this branch (newest first):
aa578d8 test: failing case for per-line discount rounding
Files changed on this branch:
A testdiscount.py
TODO/FIXME/XXX added:
cart.py:2 (uncommitted) # TODO: confirm with finance whether coupons round per line or per order
MEMORY.md: none · HANDOFF.md: none
--write HANDOFF.md turns these facts into a skeleton for the agent to fill in, and --check HANDOFF.md at the start of the next session reports if the repo no longer matches.
> Docs: https://milad-ahmd.github.io/agent-skills/skills/agent-memory-keeper/ · Claude Code: /plugin install all-skills --marketplace milad-ahmd/agent-skills
# 🧠 agent-memory-keeper
Project memory (MEMORY.md) plus session handoffs (HANDOFF.md) so the next session picks up where this one stopped. An Agent Skill for Claude Code, Cline, Cursor, Codex and other AI coding agents.
Install · Usage · How it works · All skills
> Part of agent-skills, a growing collection of practical skills for AI coding agents.
## 📦 Install
One command (installs the whole collection):
bash
curl -fsSL https://raw.githubusercontent.com/milad-ahmd/agent-skills/main/install.sh | bash -s -- agent-memory-keeper
Manually (Claude Code):
bash
git clone https://github.com/milad-ahmd/agent-memory-keeper /tmp/agent-memory-keeper
mkdir -p ~/.claude/skills && cp -r /tmp/agent-memory-keeper/skills/agent-memory-keeper ~/.claude/skills/
Per project: copy skills/agent-memory-keeper into /.claude/skills/.
Any other agent: paste SKILL.md into your rules or system prompt.
## 💬 Usage
Just ask your agent:
text
Remember that we use pnpm, not npm
Write a handoff, I'm running out of context
The full workflow, rules and output format are in SKILL.md.
## 🔎 Sample output
handoff.py is plain Python 3 with no dependencies and never touches your working tree. Real output halfway through a bug fix:
text
$ python3 handoff.py
Handoff facts for ~/code/shop
Repo: shop
Branch: fix/discount-rounding
HEAD: aa578d8 test: failing case for per-line discount rounding
Upstream: none
Base: main (merge-base f496d7e; 1 commits on this branch, 1 files changed)
In progress: none
Stash: 0
Uncommitted: 1 (0 staged, 1 unstaged, 0 untracked, 0 conflicted)
.M cart.py
Commits on this branch (newest first):
aa578d8 test: failing case for per-line discount rounding
Files changed on this branch:
A testdiscount.py
TODO/FIXME/XXX added:
cart.py:2 (uncommitted) # TODO: confirm with finance whether coupons round per line or per order
MEMORY.md: none · HANDOFF.md: none
--write HANDOFF.md turns these facts into a skeleton for the agent to fill in, and --check HANDOFF.md at the start of the next session reports if the repo no longer matches.
收录徽章(可选)
想把收录标记放进 README 就复制这行,可选,不影响收录。
[](https://anclum.com/zh/s/milad-ahmd-agent-memory-keeper/)
- 来源
- github · https://github.com/milad-ahmd/agent-memory-keeper
- 按领域浏览
- Agent 技能
- 收录于
- 今天
同类推荐
所属领域与标签
每个标签都能点进去看同类的全部条目。数字是当前库里的真实条数。