CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

investor-panel

66 位投资大佬评审团。给定一只股票的 dimensions.json 和 raw_data.json,让 66 位投资者各自按自己的方法论打分并输出 Pydantic Signal(signal/confidence/score/verdict/comment)。覆盖经典价值派、成长投资派、宏观对冲派、技术趋势派、中国价投派、A股游资派、量化系统派、科技领袖派、AI 卡位猎手 9 大流派。当用户请求"评审团/65 大佬怎么看/某某会买吗/做一次大佬投票"时使用。

Quality

78%

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 ./skills/investor-panel/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%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 well-structured and mostly concise with a clear multi-step workflow and checklist, but its executability and navigation are undermined by references to non-existent scripts, orphaned bundle files, and investor/group count inconsistencies.

Suggestions

Ship the referenced scripts/lib/investor_db.py and scripts/lib/seat_db.py (or remove the import snippets and inline the needed INVESTORS/SEATS data) so the code is executable.

Reconcile the investor/group counts across frontmatter and body (66 vs 65 vs 50, 9 流派 vs 7-group table) and either add reference entries for group-i-serenity.md / serenity-voice.md and assets/investor-cards.json or remove the orphan files.

Add an explicit validate→fix→retry loop after the Step 2.5 JSON validity check (e.g., 'if invalid, regenerate the offending Signal and re-validate before proceeding') to reach the top workflow-clarity anchor.

DimensionReasoningScore

Conciseness

The body is mostly lean with concrete JSON schema, calibration rules, and per-investor style notes rather than padded explanation; the main waste is internal inconsistency (66/65/50 investors, 7-vs-9 流派) that could be tightened, keeping it at 4 not 5.

4 / 5

Actionability

Provides a concrete JSON output schema and import snippets, but the referenced modules 'scripts/lib/investor_db.py' and 'scripts/lib/seat_db.py' do not exist in the bundle, so the code is not executable as written — missing key details that pull it down from 4 to 3.

3 / 5

Workflow Clarity

Steps 1–4 are clearly sequenced with a completion checklist and a JSON-validity check (Step 2.5) plus the游资 pre-filter, satisfying the batch-operation validation requirement; it lacks an explicit validate→fix→retry feedback loop, so it stops at 4 rather than 5.

4 / 5

Progressive Disclosure

A clear group→reference table and one-level-deep '语料库(必读)' pointer give good navigation, but two referenced script files are missing from the bundle, two reference files (group-i-serenity.md, serenity-voice.md) and assets/investor-cards.json are orphaned/unsigaled, and the table's 7 groups contradict the frontmatter's 9 流派 — gaps beyond 'minor', so 3 not 4.

3 / 5

Total

14

/

20

Passed

Description

87%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, gives explicit 'use when' trigger phrases, and carves out a distinct niche. Its only weaknesses are a minor 66-vs-65 count inconsistency and slightly narrow action coverage.

DimensionReasoningScore

Specificity

Names the domain (stock investor panel) and a concrete composite action — '打分并输出 Pydantic Signal(signal/confidence/score/verdict/comment)' — plus coverage of 9 named schools, but it is essentially one composite action rather than a broad list, so it sits at 4 not 5.

4 / 5

Completeness

Explicitly states both what ('让 66 位投资者各自按自己的方法论打分并输出 Pydantic Signal…覆盖…9 大流派') and when ('当用户请求…时使用') with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Includes natural user phrases like '评审团', '65 大佬怎么看', '某某会买吗', '做一次大佬投票' that a user would actually say; not quite comprehensive (no file-extension or synonym variants), so 4 rather than 5.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (66-investor stock voting role-play) with highly specific triggers, making conflict with other skills minimal.

5 / 5

Total

18

/

20

Passed

Validation

75%

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

Validation — 12 / 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

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

referenced_paths_exist

Referenced path issues: 2 missing, 2 deeper-than-1-level

Warning

Total

12

/

16

Passed

Repository

wbh604/UZI-Skill

Path

skills/investor-panel/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.