CtrlK
BlogDocsLog inGet started
Tessl Logo

lead-hunting

通过自媒体平台按搜集策略探索潜在客户——策略 A 分析帖子发布者画像,策略 B 从评论区挖掘潜客。

56

Quality

64%

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

Fix and improve this skill with Tessl

tessl review fix ./crews/main/skills/lead-hunting/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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 body is a well-structured, actionable workflow with concrete shell commands, a dedup validation checkpoint, and a thoughtful error-handling table including a retry feedback loop. It is concise and clearly sequenced, with only minor gaps around write-success verification and slight opening redundancy.

Suggestions

Add a verification step after record-creator.sh (check exit code / re-query check-creator.sh) to confirm each database write succeeded before proceeding.

Remove or compress the opening paragraph that restates the frontmatter description to improve token efficiency.

Consider extracting the 错误处理 table into a reference file if the skill grows, to keep the main workflow scan-focused.

DimensionReasoningScore

Conciseness

The body is mostly lean and action-oriented with concrete script calls and an error-handling table; the only minor redundancy is the opening paragraph restating the frontmatter description, which could be trimmed.

4 / 5

Actionability

Provides concrete, copy-paste-ready commands with full flag sets (e.g. 'check-creator.sh --platform <平台> --creator-id <创作者ID>' and 'record-creator.sh' with all named flags); minor gap is that parameter placeholders still require user substitution.

4 / 5

Workflow Clarity

Clear four-step sequence (准备 → 逐平台搜索 → 策略 A/B → 汇总报告) with a dedup validation checkpoint (check-creator.sh returning {"exists": true} → skip) and a browser-error feedback loop (wait 30s → retry → close/reopen → stop); minor gap is no verification that record-creator.sh writes succeeded.

4 / 5

Progressive Disclosure

Well-organized into labeled sections (前置条件, 执行流程, 错误处理) with no bundle files needed; content is appropriately self-contained for a workflow skill, though at 143 lines a small split (e.g. error handling) could be considered.

4 / 5

Total

16

/

20

Passed

Description

53%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 clearly states what the skill does and distinguishes two concrete strategies, giving it a distinct niche. It is held back by the absence of an explicit 'Use when' trigger clause and limited synonym coverage of natural trigger terms.

Suggestions

Add an explicit 'Use when...' trigger clause, e.g. 'Use when the user needs to find potential customers / sales leads on social media platforms via creator profiles or comment sections.'

Include common synonyms users might say (销售线索, 客户线索, leads, 挖客) alongside 潜在客户 to broaden natural trigger coverage.

Optionally name the platforms or the output form (list report / Cold Touch / Email) to make the capability more concrete.

DimensionReasoningScore

Specificity

Names the domain (自媒体平台/潜在客户) and two concrete strategies ('策略 A 分析帖子发布者画像', '策略 B 从评论区挖掘潜客'), but coverage is limited to these two approaches and not comprehensive of lead-hunting actions.

3 / 5

Completeness

The 'what' is clear (explore leads via two collection strategies) but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

Contains relevant domain terms ('潜在客户', '自媒体平台', '评论区', '发布者画像') but misses common synonyms users might say such as 销售线索, 客户线索, leads, or 抓客/挖客.

3 / 5

Distinctiveness Conflict Risk

The phrase '通过自媒体平台按搜集策略探索潜在客户' carves a clear niche (social-media lead hunting with two named strategies) with only minor overlap risk against generic search or CRM skills.

4 / 5

Total

13

/

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
TeamWiseFlow/xiaobei
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.