CtrlK
BlogDocsLog inGet started
Tessl Logo

trap-detector

杀猪盘检测器。当用户提到"朋友推荐"、"群里说"、"老师带"、"内幕消息"、"小红书 / 抖音看到推荐"等关键词,或显式要求"看看是不是杀猪盘 / 检测一下风险 / 这只票安全吗"时使用。扫描 8 个信号给出风险评级 🟢🟡🟠🔴。

70

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

86%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.

A tight, actionable skill body with concrete search templates, named tool calls, and a validating checklist. The main weakness is navigation: the bundled references/eight-signals.md is not referenced from the body.

Suggestions

Add an explicit pointer in the 8 信号扫描清单 section, e.g. '详细判定标准见 [references/eight-signals.md](references/eight-signals.md)', so the bundled reference is discoverable.

Add a brief error-recovery note (e.g. what to do when a signal returns 数据不足 — re-search with synonyms or mark insufficient) to turn the completion checklist into a true validate→fix→retry loop.

Reconcile the user-keyword weighting table between the body and the reference (the reference's USER_KEYWORDS dict lists terms like '包赚' not in the body) to avoid divergence.

DimensionReasoningScore

Conciseness

The body is lean throughout — one-line signal definitions, a compact rating table, a copy-paste JSON schema, and a checklist — with no padding or explanation of concepts Claude already knows; every section earns its place.

5 / 5

Actionability

Each signal ships a concrete search template (e.g. 搜 '{name} 即将爆发') or named tool call (fetch_financials, fetch_sentiment, fetch_kline), and the output JSON plus the reference's USER_KEYWORDS dict are copy-paste ready, matching the fully-executable anchor.

5 / 5

Workflow Clarity

The scan → weight → rate → output sequence is clear and the 完成检查 checklist supplies validation checkpoints (hit/miss/insufficient per signal, ≥1 evidence URL, mandatory recommendation, 强烈建议 prefix gate). It stops at 4 because there is no explicit error-recovery feedback loop, only a completion checklist.

4 / 5

Progressive Disclosure

Content is appropriately split (overview inline, detailed per-signal criteria in references/eight-signals.md, one level deep), but the body never links to or signals that reference file, so a reader would not know it exists — matching the 'references present but not clearly signaled' anchor.

3 / 5

Total

17

/

20

Passed

Description

90%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.

A strong, well-scoped description that crisply states purpose, trigger terms, and use-when guidance in third person. The only mild gap is action specificity, which stays at the '1-2 concrete actions' level.

DimensionReasoningScore

Specificity

Names the domain ('杀猪盘检测器') and two concrete actions ('扫描 8 个信号', '给出风险评级'), but does not enumerate several specific actions — matching the 'names domain and 1-2 concrete actions' anchor rather than the 'several specific actions' level above.

3 / 5

Completeness

Explicitly answers both what ('杀猪盘检测器...扫描 8 个信号给出风险评级') and when ('当用户提到...关键词,或显式要求...时使用') with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Includes exactly the natural phrases users say ('朋友推荐', '群里说', '老师带', '内幕消息', '小红书/抖音看到推荐', '看看是不是杀猪盘', '这只票安全吗') with synonyms and platform variants — comprehensive coverage of natural terms.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (杀猪盘/pump-and-dump detection) with highly specific Chinese-keyword and platform triggers, making conflict with other skills minimal.

5 / 5

Total

18

/

20

Passed

Validation

81%

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

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

13

/

16

Passed

Repository
wbh604/UZI-Skill
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.