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。

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

92%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is lean, highly actionable, and has a clearly sequenced workflow with built-in validation and feedback loops. Its main weakness is progressive disclosure: existing reference files (examples, schema) are orphaned, with their content duplicated inline rather than linked from a concise overview.

Suggestions

Replace the inlined full JSON example with a pointer to references/examples.md, keeping only a minimal snippet in the body.

Move the detailed field/schema rules (Maslow/TPB/location_policy tables, segment requirements) into references/story_schema.yaml and link to it from a short overview, rather than reproducing the schema inline.

Add an explicit '## References' section linking examples.md and story_schema.yaml so the existing bundle files are discoverable from the body.

Dimension	Reasoning	Score
Conciseness	The body is dense and reference-oriented — CLI command tables, a concrete JSON example, field-spec tables, and rules — with no padding about concepts Claude already knows; the brief TPB/Maslow notes tie frameworks to this skill's custom schema and earn their place, matching the 'lean and efficient' anchor.	3 / 3
Actionability	It provides exact executable CLI syntax ('python scripts/daily_guidance.py plan --date D --json ...'), a complete copy-paste JSON example, fixed value tables for location_policy and Maslow needs, and explicit field requirements, matching the 'fully executable; copy-paste ready' anchor.	3 / 3
Workflow Clarity	The per-step flow is explicitly sequenced into 情况 A (no story → submit plan) and 情况 B (active segment → act), and the plan path has an explicit validation checkpoint with a feedback loop ('校验通过才写文件，否则返回逐字段修复提示') plus a check command, matching the 'clear sequence with explicit validation and feedback loops' anchor.	3 / 3
Progressive Disclosure	Bundle files references/examples.md and references/story_schema.yaml exist, but the body never links to them; the full JSON example, schema field rules, and Maslow/TPB tables are inlined instead of split out and signaled, matching the 'some structure but references not clearly signaled; content that should be separate is inline' anchor rather than a monolithic wall (the body has clear ## sections).	2 / 3
	Total	11 / 12 Passed

Description

85%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, complete, and distinctive, with explicit mandatory-use trigger guidance and a clear niche. Its only weakness is trigger-term naturalness: the activation condition is phrased technically rather than in terms a user would naturally say.

Suggestions

Soften the trigger condition into more natural phrasing a user might actually say, e.g. 'when simulating a day's behavior, daily routines, or hourly schedules' rather than '时间尺度在小时及以下的日常行为模拟'.

Add common surface variations of the trigger (e.g. 'daily schedule', 'daily routine', 'hourly behavior simulation') to broaden natural keyword coverage.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — '生成、评估、执行和修正每日 Story' (generate, evaluate, execute, revise daily Stories) — matching the anchor that rewards multiple specific concrete actions.	3 / 3
Completeness	It answers both 'what' (generate/evaluate/execute/revise daily Story) and 'when' with an explicit trigger ('凡是...必须使用本 Skill' = whenever daily behavior simulation at hour-or-finer scale, must use), which is an explicit 'Use when...' equivalent, so completeness is not capped at 2.	3 / 3
Trigger Term Quality	It names a relevant domain term ('日常行为模拟') but the trigger phrasing '时间尺度在小时及以下的' (time scale of hours or less) is technical and lacks common natural variations a user would naturally say, matching the 'some relevant keywords but missing common variations' anchor.	2 / 3
Distinctiveness Conflict Risk	The niche — daily behavior simulation at hour-or-finer time scale producing daily Story files — is narrow and distinct with a specific trigger, making conflict with other skills unlikely, matching the 'clear niche with distinct triggers' anchor.	3 / 3
	Total	11 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: tsinghua-fib-lab/AgentSociety
Path: packages/agentsociety2/agentsociety2/agent/skills/daily-guidance/SKILL.md
Commit: 1832bcb

Reviewed: about 5 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.