CtrlK
BlogDocsLog inGet started
Tessl Logo

exp-invite

Invite a qualified customer into the experience group when they want to understand the product form further after seeing demo materials. The invite is sent as an awada control message, and the customer status is updated to exp_invited to prevent duplicate invitations.

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 ./crews/sales-cs/skills/exp-invite/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 tight, single-purpose skill with fully executable command examples, clear validation rules via --force/ALREADY_INVITED/exit codes, and well-organized sections that delegate implementation to the bundled invite.sh script, with only minor room to tighten duplicated explanations and add an explicit recovery loop.

Suggestions

Merge the duplicate group-name content (inline in the message-format section and again under 当前体验群名称) into one place to remove redundancy and lift conciseness toward 5.

Make the validation/recovery loop explicit (check business_status -> if not free and no --force, return ALREADY_INVITED -> else send invite) as a numbered checklist so workflow_clarity reaches 5.

Add a one-line pointer to scripts/invite.sh from the body so the delegation to the bundle is clearly signaled for navigation.

DimensionReasoningScore

Conciseness

The body is efficient and assumes competence — it jumps straight into the command signature, behavior rules, and message format without explaining what a database or an invite is — with only minor trimming possible in the duplicated parameter explanations, matching the "efficient; minor instances of over-explanation" anchor rather than the lean score-5.

4 / 5

Actionability

It provides fully executable, copy-paste-ready command invocations with exact flags ("--peer", "--user-id-external", "--force"), the concrete control-message format "/invite//<user_external_id>//风暴眼(wiseflow情报小站)", and clear return/exit-code conventions ("ALREADY_INVITED", non-zero exit), covering the common cases exactly as the score-5 anchor describes.

5 / 5

Workflow Clarity

The workflow has a clear sequence with validation checkpoints — block non-free users unless --force, update business_status conditionally, emit the control message, and report ALREADY_INVITED with non-zero exit — but the recovery loop is implicit rather than an explicit validate-fix-retry checklist, so it sits at the score-4 "clear sequence with most checkpoints; minor validation gaps" rather than 5.

4 / 5

Progressive Disclosure

Content is well-organized into focused sections (用途, 客户标识提取规则, 行为规则, business_status 更新规则, 邀请消息格式, 返回约定) with the executable logic appropriately delegated to the bundled scripts/invite.sh; this is good structure with only minor organization gaps (e.g. the duplicate group-name section), matching score-4 rather than the fully one-level-deep-referenced score-5.

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 clearly states what the skill does with several concrete actions and a distinct niche, but it omits an explicit 'Use when...' trigger clause and natural user-facing trigger phrases, which caps trigger quality and completeness at the mid level.

Suggestions

Add an explicit 'Use when the customer explicitly asks to join the experience group after seeing demo materials' clause to satisfy the trigger-guidance requirement.

Include natural trigger phrases or synonyms a user might actually say (e.g. 'experience group', 'trial group', 'join the group', 'invite me') to improve trigger term coverage.

Tighten the 'when' from a relative clause inside the first sentence into its own explicit trigger sentence so completeness reaches 4-5.

DimensionReasoningScore

Specificity

It lists several concrete actions — "Invite a qualified customer into the experience group", "sent as an awada control message", "customer status is updated to exp_invited to prevent duplicate invitations" — with only minor gaps in coverage, matching the "lists several specific actions; minor gaps" anchor rather than the vague score-3 single-action anchor.

4 / 5

Completeness

The "what" is clear (invite into the experience group via awada control message, update status to exp_invited), but the "when" is only weakly implied ("when they want to understand the product form further after seeing demo materials") with no explicit "Use when..." trigger guidance, which per the judging guidelines caps completeness at 3.

3 / 5

Trigger Term Quality

It contains some relevant keywords ("experience group", "demo", "invite", "customer status") but lacks the natural conversational trigger phrases and synonyms a user would say, and has no "Use when..." trigger clause, fitting "some relevant keywords but missing common variations" rather than the comprehensive score-4 anchor.

3 / 5

Distinctiveness Conflict Risk

The niche is fairly specific — awada control-message invites into a named experience group with exp_invited status tracking — so it is mostly distinct with only minor overlap risk against other customer-status skills, matching the score-4 "mostly distinct; minor overlap risk" anchor rather than the broad score-3.

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
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.