CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

expert-bd

商务拓展与联络专家。承接潜客探索筛选、评论回复、私信、邮件、点赞收藏关注、直播间互动、客户触达与联络记录。商业情报、竞对监控、直播调研及市场研究走 expert-osbi;公开资料按平台使用文中列出的采集技能或公共 smart-search,融资推进走 expert-ir。

Quality

79%

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/expert-bd/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 body is a lean, well-structured routing overview with concrete tool allocations, explicit session and authorization rules, and real validation checkpoints for outward-facing write operations. Progressive disclosure is well handled through one-level-deep references, with only minor duplication between the tool table and the capability reference.

DimensionReasoningScore

Conciseness

The body is table-driven routing with zero padding: every line allocates a responsibility, a tool, a data location, or a boundary (e.g. "快手普通互动、私信与直播写操作未实现;微博互动写操作未实现"). No concept explanations to trim, matching the lean top anchor.

5 / 5

Actionability

Concrete, executable guidance throughout: named tools per platform, exact data paths (db/bd_record.db, bd/live/), session rules (douyin-login 独立 API 会话;小红书复用 xhs-hunter PC 会话,不混用 Creator 登录), and dedup/recording rules. Step-level execution detail is delegated to the workflow and tool files, leaving minor gaps — matching the 4 anchor.

4 / 5

Workflow Clarity

A clear routing decision rule ("找客户和筛选潜客按本包 Lead Hunting 执行;已有目标时直接核对语境、授权和实际能力") plus explicit validation checkpoints for risky write ops ("每次写操作核对真实目标和既有授权;预览后仅执行已授权动作…结果不明时先核实,不自动重发或换通道补发"). The batch-outreach validation cap at 3 does not apply since validation is present; detailed multi-step sequences live in the workflow files, so this fits 4 rather than 5.

4 / 5

Progressive Disclosure

The body is an overview with clearly signaled one-level-deep references: three workflow links in the routing table, twelve tool SKILL.md links, and [互动能力表](references/interaction-capabilities.md), which exists and matches its pointer. Minor gaps keep it at 4: the workflows/ and tools/ paths are not present in the provided bundle, and the tool table partially duplicates capability detail already in the references file.

4 / 5

Total

17

/

20

Passed

Description

71%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 is specific and comprehensive about what the skill does, with good domain keywords and clear boundaries against adjacent expert skills. Its main weakness is the absence of an explicit "Use when…" trigger clause and of platform-level trigger terms, which limits discoverability and keeps completeness at the cap of 3.

Suggestions

Add an explicit trigger clause, e.g. "用户需要找客户、回复评论/私信、点赞收藏关注、直播间互动或跟进联络潜客时使用本技能", so the "when" is stated rather than implied by routing-out rules.

Include natural platform trigger terms (抖音、小红书、TikTok、X) and synonyms like 找客户/拓客/获客 in the description so platform-specific outreach requests match without reading the body.

Clarify that email execution routes through the public email-ops skill (e.g. "邮件经公共技能 email-ops 执行") to reduce overlap/conflict risk with that skill.

DimensionReasoningScore

Specificity

The description lists many concrete actions — "潜客探索筛选、评论回复、私信、邮件、点赞收藏关注、直播间互动、客户触达与联络记录" — giving comprehensive coverage of the skill's capabilities, matching the top anchor. It uses third-person phrasing, so no voice penalty applies.

5 / 5

Completeness

The "what" is clear and concrete, but there is no explicit "Use when…" or equivalent trigger clause; the "when" is only weakly implied via routing-out statements (商业情报…走 expert-osbi;融资推进走 expert-ir). Per the rubric guideline, a missing explicit trigger clause caps completeness at 3.

3 / 5

Trigger Term Quality

Natural domain keywords are present (潜客筛选, 评论回复, 私信, 点赞收藏关注, 直播间互动, 客户触达), but platform names (抖音/小红书/TikTok/X) and common synonyms (找客户/拓客/获客) that users would naturally say appear only in the body, not the description. This is good coverage with a few natural terms missing, matching the 4 anchor rather than 5.

4 / 5

Distinctiveness Conflict Risk

The niche (BD outreach) is clear with explicit deferrals to expert-osbi and expert-ir, reducing conflict with those skills. However, it claims 邮件 while the body routes email execution to the public email-ops skill, creating minor overlap risk with a closely related skill — matching the 4 anchor rather than 5.

4 / 5

Total

16

/

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.

Validation — 13 / 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

relative_links

Relative link issues: 14 missing, 11 deeper-than-1-level

Warning

Total

13

/

16

Passed

Repository

TeamWiseFlow/xiaobei

Path

crews/main/skills/expert-bd/SKILL.md

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.