investor-pipeline

当执行 IR（投资人关系）任务·模式 3 时使用。完整的融资沟通流水线：发掘潜在投资人 → 准备触达材料 → 发起接触 → 跟踪反馈 → 状态机推进。状态：new→contacted→ bp_sent→meeting→dd→ts→invested/passed。

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./crews/main/skills/investor-pipeline/SKILL.md

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A concise, well-structured workflow with concrete ir-record commands and a clear state machine, but its core sub-skill invocations are placeholder pseudocode and it lacks validation/feedback loops for the data-mutation steps.

Suggestions

Replace the commented-out sub-skill placeholders with concrete, executable invocation commands for investor-hunting, investor-materials, and investor-outreach so the central workflow is copy-paste ready.

Add validation/feedback loops around the ir-record mutations — e.g. verify the investor row was created, guard against duplicate investors, and confirm update-status succeeded before advancing the state machine.

Consider offloading the detailed pitfall workarounds and full state-machine semantics into a single one-level-deep reference file, keeping SKILL.md a lean overview that links to it.

Dimension	Reasoning	Score
Conciseness	The body is lean and token-efficient — tables, a state-machine diagram, and bash blocks — and assumes Claude's competence (BP/DD/TS/VC used without explanation), with every section earning its place.	3 / 3
Actionability	The ir-record commands are concrete and flag-complete, but the core sub-skill invocations are commented-out placeholders ('# agent 形式：sessions_spawn 或直接 exec 子 skill 脚本') rather than executable code, leaving key steps incomplete.	2 / 3
Workflow Clarity	Six steps are clearly sequenced with a Step 1 prerequisite gate and a feedback→status table, but there are no error-recovery feedback loops around the database-style state mutations, which caps workflow clarity at 2 per the rubric's feedback-loop note.	2 / 3
Progressive Disclosure	Content is well-sectioned but entirely inline in one monolithic SKILL.md with no bundle/reference files to offload detail into; the detailed pitfall workarounds and full state-machine semantics could be split out for a skill of this complexity.	2 / 3
	Total	9 / 12 Passed

Description

77%

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 specific, well-scoped description that answers both what and when, but its trigger relies on internal 'IR 模式 3' jargon instead of the natural phrases users actually say, weakening trigger quality and distinctiveness.

Suggestions

Replace the jargon trigger '当执行 IR 任务·模式 3 时使用' with natural user phrasing, e.g. 'Use when the user wants to find investors/angels, raise a funding round, or follow up with VCs they have already contacted'.

Add explicit natural trigger keywords to the description (找天使投资人/VC、融资、跟进投资人、约 meeting) so it fires on real language and stands apart from the sibling IR sub-skills.

Dimension	Reasoning	Score
Specificity	The description enumerates multiple concrete actions — '发掘潜在投资人 → 准备触达材料 → 发起接触 → 跟踪反馈 → 状态机推进' — rather than vague language, matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	It explicitly answers both what ('完整的融资沟通流水线：…') and when ('当…时使用'), providing an explicit 'Use when…' equivalent clause, so it is not capped at 2.	3 / 3
Trigger Term Quality	The primary trigger is internal jargon ('当执行 IR（投资人关系）任务·模式 3 时使用') that a user would not naturally say; natural terms like '找投资人/VC' or '融资' appear in the body but not the description, so coverage is partial.	2 / 3
Distinctiveness Conflict Risk	The pipeline/state-machine framing gives it a niche, but it overlaps with sibling IR sub-skills (investor-hunting, investor-materials, investor-outreach, ir-record) and the '模式 3' trigger presumes internal numbering, leaving overlap risk.	2 / 3
	Total	10 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
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/investor-pipeline/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.