CtrlK
BlogDocsLog inGet started
Tessl Logo

event

事件管理:为 agent 启动、查询和停止行为事件。必须通过 ask_env 调用 EventSpace 工具。

60

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./packages/agentsociety2/agentsociety2/contrib/env/event_space/agent_skills/event/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

82%Weight 40%Scale 1-5

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

The content is a well-structured, highly actionable reference: concrete call syntax, parameters, reference values, and worked examples for every common operation, plus clear behavioral constraints. Minor conciseness redundancy and the lack of explicit error-recovery feedback loops are the only gaps.

Suggestions

Consolidate the 'keep the current same-type event' guidance into one place to remove the duplication between the start_event section and constraint #3.

Add a short error-recovery note for when an ask_env call fails or returns an unexpected event state, to make the workflow feedback loop explicit.

Consider moving the event-type table and seconds reference values into a reference file if the skill grows, keeping SKILL.md as a lean overview.

DimensionReasoningScore

Conciseness

The body is lean and well-sectioned with no padding about concepts Claude already knows; not a 5 because the 'keep current same-type event' rule is restated in both the start_event section and constraint #3, a minor redundancy that could be trimmed.

4 / 5

Actionability

Provides the exact ask_env call signature, concrete parameter lists, a seconds reference table (30min=1800, 1h=3600, etc.), and copy-ready example instructions covering query/start/keep/stop/switch cases — fully executable guidance for the common cases.

5 / 5

Workflow Clarity

Sequencing is clear with an explicit 'query current event before starting' checkpoint and same-type-state rules in the 约束 section; not a 5 because error-recovery feedback loops are implicit rather than spelled out, though event start/stop is not a destructive or batch operation that would mandate them.

4 / 5

Progressive Disclosure

Well-organized with clear section headers (环境概念, 可用工具, 示例, 约束) and no nested or buried references, and no bundle files are needed; not a 5 because the skill exceeds the under-50-line simple-skill threshold and inlines reference material (event-type table, reference values) that is appropriately placed but not split out.

4 / 5

Total

17

/

20

Passed

Description

58%Weight 40%Scale 1-5

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 states a clear 'what' with three concrete actions tied to a distinctive EventSpace tool, but omits any 'when to use' trigger guidance and relies on technical jargon over natural user phrases. It is functional but would benefit from explicit trigger conditions.

Suggestions

Add an explicit 'Use when…' clause stating when this skill should activate (e.g., when the agent needs to track or transition its ongoing behavioral activity).

Include natural-language trigger phrases a user or orchestrator would actually say, alongside the technical 'ask_env'/'EventSpace' terms.

Tighten the distinctiveness by naming what makes behavioral events unique versus other agent state, reducing overlap with related skills.

DimensionReasoningScore

Specificity

Names the event-management domain and three concrete actions — '启动、查询和停止行为事件' — matching the anchor that lists several specific actions with minor coverage gaps; not a 5 because it stops at three actions without further detail.

4 / 5

Completeness

The 'what' is clearly stated (start/query/stop behavioral events) but there is no 'Use when…' clause or equivalent trigger guidance, so per the judging guidelines completeness is capped at 3; not a 4 because 'when' is entirely missing rather than weakly implied.

3 / 5

Trigger Term Quality

Relevant domain keywords like '事件管理', '行为事件', 'ask_env', 'EventSpace' are present but these are system-internal jargon rather than natural phrases a user would say, missing common variations; not a 4 because natural-language trigger terms are largely absent.

3 / 5

Distinctiveness Conflict Risk

The specific 'EventSpace' + 'ask_env' event-management niche is mostly distinct with only minor overlap risk against related agent-behavior skills; not a 5 because the bare term '事件管理' is still somewhat broad without sharper trigger phrasing.

4 / 5

Total

14

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
tsinghua-fib-lab/AgentSociety
Reviewed

Table of Contents

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.