npx skills add https://github.com/alirezarezvani/claude-skills --skill resume恢复已暂停或受上下文限制的实验。读取所有历史记录并从上次中断处继续。
/ar:resume # 列出实验,让用户选择
/ar:resume engineering/api-speed # 恢复特定实验
如果未指定实验:
python {skill_path}/scripts/setup_experiment.py --list
显示每个实验的状态(根据 results.tsv 的修改时间判断为活跃/暂停/完成)。让用户选择。
# 检出实验分支
git checkout autoresearch/{domain}/{name}
# 读取配置
cat .autoresearch/{domain}/{name}/config.cfg
# 读取策略
cat .autoresearch/{domain}/{name}/program.md
# 读取完整的结果历史记录
cat .autoresearch/{domain}/{name}/results.tsv
# 读取该分支最近的 git 日志
git log --oneline -20
为用户总结:
正在恢复:engineering/api-speed
目标:src/api/search.py
指标:p50_ms(越低越好)
实验:总计 23 个 — 8 个保留,12 个丢弃,3 个崩溃
最佳结果:185ms(相较于基线 320ms 降低 42%)
最近一次实验:"添加了响应缓存" → 保留 (185ms)
近期模式:
- 缓存更改:3 个保留,1 个丢弃(持续有效)
- 算法更改:2 个丢弃,1 个崩溃(高风险,目前回报低)
- I/O 优化:2 个保留(有前景的方向)
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
您希望如何继续?
1. 单次迭代 (/ar:run) — 我将进行一次更改并评估
2. 启动循环 (/ar:loop) — 按预定间隔自主运行
3. 仅显示结果 — 我将审阅并决定
如果用户选择循环,则移交至 /ar:loop 并预选该实验。如果选择单次,则移交至 /ar:run。
周安装量
174
代码仓库
GitHub 星标数
6.7K
首次出现
11 天前
安全审计
安装于
codex167
gemini-cli166
opencode166
amp165
kimi-cli165
cursor165
Resume a paused or context-limited experiment. Reads all history and continues where you left off.
/ar:resume # List experiments, let user pick
/ar:resume engineering/api-speed # Resume specific experiment
If no experiment specified:
python {skill_path}/scripts/setup_experiment.py --list
Show status for each (active/paused/done based on results.tsv age). Let user pick.
# Checkout the experiment branch
git checkout autoresearch/{domain}/{name}
# Read config
cat .autoresearch/{domain}/{name}/config.cfg
# Read strategy
cat .autoresearch/{domain}/{name}/program.md
# Read full results history
cat .autoresearch/{domain}/{name}/results.tsv
# Read recent git log for the branch
git log --oneline -20
Summarize for the user:
Resuming: engineering/api-speed
Target: src/api/search.py
Metric: p50_ms (lower is better)
Experiments: 23 total — 8 kept, 12 discarded, 3 crashed
Best: 185ms (-42% from baseline of 320ms)
Last experiment: "added response caching" → KEEP (185ms)
Recent patterns:
- Caching changes: 3 kept, 1 discarded (consistently helpful)
- Algorithm changes: 2 discarded, 1 crashed (high risk, low reward so far)
- I/O optimization: 2 kept (promising direction)
How would you like to continue?
1. Single iteration (/ar:run) — I'll make one change and evaluate
2. Start a loop (/ar:loop) — Autonomous with scheduled interval
3. Just show me the results — I'll review and decide
If the user picks loop, hand off to /ar:loop with the experiment pre-selected. If single, hand off to /ar:run.
Weekly Installs
174
Repository
GitHub Stars
6.7K
First Seen
11 days ago
Security Audits
Gen Agent Trust HubPassSocketPassSnykPass
Installed on
codex167
gemini-cli166
opencode166
amp165
kimi-cli165
cursor165
AI Elements:基于shadcn/ui的AI原生应用组件库,快速构建对话界面
63,800 周安装