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。

Quality

64%

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

Fix and improve this skill with Tessl

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

Quality

Content

70%

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 lead-hunting workflow with explicit validation checkpoints and error recovery for a batch operation. It is slightly verbose in places and the main search steps rely on delegated skills rather than inline executable code.

Dimension	Reasoning	Score
Conciseness	The flow is mostly lean operational guidance ('视频内容只需分析视频简介，不下载视频', '30-60 秒间隔避免平台风控') with no concept padding, but the intro/prerequisites mildly repeat the strategy framing and the browser-error row is padded with exclamatory prose, matching 'mostly efficient but could be tightened'.	2 / 3
Actionability	It gives concrete executable commands (init-db.sh, check-creator.sh, record-creator.sh with full args and expected {"exists": true} JSON), but the core search/extract flow is navigational instructional steps delegated to other skills rather than copy-paste executable code, matching 'some concrete guidance but incomplete'.	2 / 3
Workflow Clarity	A clearly sequenced prep→search→strategy→report flow carries explicit validation checkpoints (dedup check skips existing records, email-ops env-var validation with skip-and-record fallback) and a validate→wait→retry browser recovery loop, matching the 'clear sequence with explicit validation steps and feedback loops' anchor for a batch crawling operation.	3 / 3
Progressive Disclosure	No references/scripts/assets bundle exists, so there is no nested-reference structure to penalize; the single-file body is organized into well-signaled sections (前置条件, 执行流程, 错误处理), and per the scoring notes a skill with no need for external references scores 3 with well-organized sections.	3 / 3
	Total	10 / 12 Passed

Description

60%

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 names a concrete lead-hunting niche with two specific strategies, but lacks an explicit use-when trigger and leans on internal jargon over natural user phrasings. It is solid but not maximally distinctive or trigger-complete.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers (e.g. '找潜在客户/获客、挖掘评论区线索、分析创作者主页找客户').

Replace internal labels ('搜集策略', '策略 A/B') with user-facing terms and common variations of how the task is requested.

Sharpen distinctiveness by stating the concrete output (lead list with contact actions) so it cannot be confused with generic search skills.

Dimension	Reasoning	Score
Specificity	Quotes two distinct concrete actions — '策略 A 分析帖子发布者画像' and '策略 B 从评论区挖掘潜客' — alongside the lead-hunting domain, matching the 'lists multiple specific concrete actions' anchor rather than the score-2 'some actions' anchor.	3 / 3
Completeness	It clearly states what the skill does but has no explicit 'Use when...' / when-to-trigger clause; per the guidelines a missing 'Use when' clause caps completeness at 2, and it is not score 1 because the 'what' is explicitly stated.	2 / 3
Trigger Term Quality	Terms like '自媒体平台', '潜在客户', '评论区' are relevant but skew toward internal jargon ('搜集策略', '策略 A/B') and omit natural user phrasings like '找客户/获客', matching 'some relevant keywords but missing common variations' rather than broad natural-term coverage.	2 / 3
Distinctiveness Conflict Risk	'通过自媒体平台探索潜在客户' carves a specific niche, but the triggers are not crisp enough to rule out overlap with general search/contact skills, matching the 'somewhat specific but could still overlap' anchor rather than a clearly distinct niche.	2 / 3
	Total	9 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: TeamWiseFlow/xiaobei
Path: crews/main/skills/lead-hunting/SKILL.md
Commit: bcef823

Reviewed: 3 days 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.