sentiment-analysis

市场情绪分析——恐贪指数/Put-Call Ratio/融资融券/北向资金信号解读、社交媒体舆情量化框架

Quality

87%

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

Quality

Content

92%

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

The content is lean, highly actionable, and presents a clear single-pass analytical workflow with concrete thresholds and an output template, but it is a monolithic document that would benefit from splitting its reference tables into separate files.

Suggestions

Move the large threshold/signal tables (恐贪指数, PCR, 融资融券, 北向资金) into a reference file (e.g. references/indicators.md) and keep SKILL.md as an overview with one-level-deep links, improving progressive_disclosure.

Add an explicit verification step in the workflow (e.g. "Confirm at least 3 of 5 dimensions agree before mapping to a position") to make the cross-validation checkpoint a concrete numbered step.

Dimension	Reasoning	Score
Conciseness	The body is information-dense — concrete threshold tables, formulas, and an output template — and avoids lecturing on concepts Claude already knows (only one-line definitional asides like "融资 = 借钱买股"), matching the lean score-3 anchor.	3 / 3
Actionability	It provides specific operational thresholds (e.g. "融资余额月增>10% → 过热警示"), the weighted scoring formula, a position-mapping table, and a copy-paste-ready markdown output template; per the instruction-only scoring note, the absence of executable code is not penalized when guidance is this concrete.	3 / 3
Workflow Clarity	A single, unambiguous analytical workflow — gather each indicator → normalize → weighted sum → map to position → fill the output template — with explicit cross-validation guidance in 注意事项 ("与融资余额、ETF申赎交叉验证") serving as a checkpoint.	3 / 3
Progressive Disclosure	At ~268 lines with no bundle files, it is well-sectioned but monolithic: large inline reference tables (恐贪/PCR/融资/北向 thresholds) that could be split into separate reference files are kept inline, matching the score-2 anchor of structure present but content that should be separate is inline.	2 / 3
	Total	11 / 12 Passed

Description

82%

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 distinctive, naming concrete sentiment indicators a user would naturally request, but it omits an explicit "when to use" trigger clause, which caps completeness at 2. Adding a Use-when phrase would round it out.

Suggestions

Append a "Use when..." clause, e.g. "市场情绪分析——...量化框架。Use when the user asks about market sentiment, extreme greed/fear, or reverse-indicator signals across A-shares, US stocks, or crypto."

Add layman trigger variations alongside the domain jargon (e.g. "反向指标", "择时", "市场过热/恐慌") so non-specialist users also match this skill.

Dimension	Reasoning	Score
Specificity	Quotes: "恐贪指数/Put-Call Ratio/融资融券/北向资金信号解读、社交媒体舆情量化框架" — it lists multiple concrete, named capabilities (four distinct signal types plus a sentiment-quantification framework) rather than vague domain language, matching the score-3 anchor.	3 / 3
Completeness	It states clearly what the skill does (multi-dimension sentiment analysis and signal interpretation) but lacks any "Use when..." clause or explicit trigger guidance, so per the judging guideline completeness is capped at 2.	2 / 3
Trigger Term Quality	Named terms — 恐贪指数, Put-Call Ratio, 融资融券, 北向资金, 社交媒体舆情 — are precisely the natural keywords a user of this niche would say when they need the skill, satisfying the score-3 anchor of good coverage of natural terms.	3 / 3
Distinctiveness Conflict Risk	The specific combination of A-share/Crypto sentiment indicators (恐贪指数, PCR, 融资融券, 北向资金, 舆情) carves a clear niche unlikely to conflict with other analysis skills, matching the score-3 anchor.	3 / 3
	Total	11 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: HKUDS/Vibe-Trading
Path: agent/src/skills/sentiment-analysis/SKILL.md
Commit: 8643fcd

Reviewed: 2 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.