Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →tsinghua-fib-lab/daily-guidance
强制使用：凡是时间尺度在小时及以下的日常行为模拟，必须使用本 Skill 生成、评估、执行和修正每日 Story。
Passed 9 of 15 test cases with the skill, and 2 of 15 without it.
and 9 more in the full report
12 fixed1 passed either way7 still failing2 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.
An agent visits a park located close to their home address. Which location_policy enum string denotes searching POIs near the home zone?
| Checked | Without skill | With skill |
|---|---|---|
| Uses 'near_home_aoi' as the location policy string | Missed | Passed |
The instructions your model reads when the skill loads.
Daily Guidance 让 agent 先形成一天的完整 Story，再按 Story 指导每个仿真步的行为。
所有结构化操作都通过 scripts/daily_guidance.py 的 CLI 命令完成——你提交 JSON 内容，
脚本负责校验、序列化 YAML、以及从仿真时钟推导执行状态。
每天一个文件：state/daily_guidance/YYYY-MM-DD/story.yaml（由脚本生成和维护）。
plan --json 提交一天的安排。 提交 JSON 对象，脚本校验后写入 story.yaml。completed_segments / current_segment_id 是
(segments, 当前仿真时间) 的函数，由脚本在读取时计算。时间到了自然完成。active_segment
（含 activity 和 location_policy）。按此移动和回答问卷。每个 step 开始，pre_step hook 自动输出当前状态。两种情况：
情况 A：还没有有效 Story（ok: false）
hook 输出会包含 next 指引。立即提交一天的 Story：
python scripts/daily_guidance.py plan --date YYYY-MM-DD --json '<JSON对象>'
情况 B：已有有效 Story（ok: true）
hook 输出包含 active_segment 和 guidance，例如：
active_segment:
id: sleep_night
activity: sleep
location_policy: home_aoi
start: "00:00"
end: "07:00"
guidance: Your intended activity now is 'sleep' at location policy 'home_aoi'. ...
test cases passed, vs 2 / 15 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.