CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

expert-ir

投资人关系(IR)专家。承接投资人发掘、融资沟通流水线(状态机跟进)、项目申报(认定/补贴/大赛)的完整工作。零散的投资人记录、进展查询等操作也可以直接做。公开商业研究走 expert-osbi,潜客探索筛选与客户联络走 expert-bd。

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-ir/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.

An efficient, well-structured index body that routes to pre-built workflows, names concrete commands and data rules, and enforces real safety gates (confirmation before outbound email, dedup before writes). Its remaining gaps are the absence of example tool invocations and explicit error-recovery loops, and name-based rather than path-based navigation to package resources.

DimensionReasoningScore

Conciseness

The body is lean and dense — workflow/tool tables, command names, paths, and hard rules with zero padding and no explanation of concepts Claude already knows (e.g. the 资源命名约定 and 红线 sections are pure operational necessity). Every token earns its place, matching the 5 anchor; there is no unnecessary explanation to trim for a 4.

5 / 5

Actionability

Concrete, executable guidance throughout: "ir-record init-db(幂等)", "check-investor 去重", "db/ir_record.db", "统一存放在…ir/ 文件夹下". It misses a 5 because no example invocations with arguments are shown and specifics are deferred to package workflow docs by name lookup — minor gaps rather than the 5 anchor's copy-paste-ready coverage of common cases.

4 / 5

Workflow Clarity

The pipeline sequence is explicit ("发掘 → 材料 → 触达 → 跟进 → 状态机推进") and genuine checkpoints exist for the risky operations: user confirmation before sending ("先出文案,用户确认后再走 email-ops"), dedup before db insert ("录入投资人前先 check-investor 去重"), and idempotent init. It stays at 4 rather than 5 because no explicit error-recovery/feedback loops are described (e.g. what to do when a db write or init fails), and above 3 because checkpoints are stated, not merely implicit.

4 / 5

Progressive Disclosure

The body is a well-organized index: five workflows routed by scenario table, tools listed, and a single clearly signaled one-level reference ("见包内 scheduling.md"). It misses 5 because navigation relies on logical-name lookup ("按工具名称查找对应说明,不要把工具名拼成路径") rather than explicit paths/links, and the referenced scheduling.md and workflow docs are not verifiable in the bundle — minor organization gaps typical of the 4 anchor.

4 / 5

Total

17

/

20

Passed

Description

70%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 distinctive, domain-rich description with explicit boundary routing to sibling skills, but it describes capability areas rather than concrete actions and lacks any explicit 'when to use' trigger clause. Adding a use-when clause and natural trigger phrases would resolve its main weaknesses.

Suggestions

Add an explicit trigger clause, e.g. "当用户提到融资、找投资人、跟进投资人进展、申报补贴/高企认定/创业大赛时使用", so the 'when' is explicit rather than implied.

Include common natural synonyms users say, such as 路演, BP/商业计划书, 高企认定, FA/对接资本, to broaden trigger-term coverage.

Convert domain nouns into concrete action verbs (e.g. "搜索并筛选匹配投资人、生成 Pitch Deck/One-Pager、跟进融资状态机") instead of "承接…的完整工作".

DimensionReasoningScore

Specificity

The description names several concrete workstreams — "投资人发掘", "融资沟通流水线(状态机跟进)", "项目申报(认定/补贴/大赛)", "零散的投资人记录、进展查询" — with minor gaps. It falls below the 5 anchor because capabilities are framed as domain nouns under "承接…完整工作" rather than multiple concrete action verbs, and above 3 because it lists far more than 1-2 specific items.

4 / 5

Completeness

The "what" is clear (investor discovery, fundraising pipeline with state-machine follow-up, project applications, ad-hoc recording/queries), but there is no explicit "Use when…" clause or equivalent trigger guidance — "零散的投资人记录、进展查询等操作也可以直接做" states scope, not when to invoke. Per the judging guideline, a missing trigger clause caps completeness at 3.

3 / 5

Trigger Term Quality

Good natural keyword coverage: "投资人", "融资", "补贴", "大赛", "项目申报", "进展查询" are phrases users would actually say. It sits below 5 because common variations like 路演, BP/商业计划书, an explicit 高企认定 trigger, or FA/对接 are missing, and above 3 because the present terms are relevant and natural rather than generic.

4 / 5

Distinctiveness Conflict Risk

It occupies a clear IR niche and actively disambiguates sibling skills ("公开商业研究走 expert-osbi,潜客探索筛选与客户联络走 expert-bd"), giving distinct triggers and minimal conflict risk — a better fit for the 5 anchor than the 4 anchor's "minor overlap risk".

5 / 5

Total

16

/

20

Passed

Validation

87%

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

Validation — 14 / 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

Total

14

/

16

Passed

Repository

TeamWiseFlow/xiaobei

Path

crews/main/skills/expert-ir/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.