About this skill

Problem

Financial news feeds mix rumors, stale stories, clickbait, duplicate reposts, and pure opinions. Reading full text or feeding it directly into a summarizer can mistake weak evidence for confirmed facts. This skill scores a single news item or a merged event cluster to filter noise and set processing priority, not to generate summaries or trading advice.

How It Works and Limits

Input may be plain text, a headline, or structured JSON. It first identifies the subject, source, facts, time, and possible impact targets, then checks whether the item is rumor, duplicate, stale, or weak_evidence before applying the scoring model to five dimension scores and noise penalties.

Output: JSON by default, including filter_score, level, decision, status, dimension_scores, noise_penalties, missing_evidence, and follow_up.
Levels: S/A/B/C/D map to different keep policies, from strong keep or manual review to filtering.
Limits: Low-confidence rumors must not be presented as confirmed facts; heat alone without new facts, subject, or impact chain should not score high; batch scoring should emit one JSON per item rather than a merged summary.

Screenshots

Use Cases

Score overnight briefs before standup; keep S/A items, drop duplicates or rumors.
Triage event clusters as old-news rehashes and output keep, background, or drop decisions.
Flag weak evidence and list missing facts so rumors are not treated as confirmed.
Produce per-item JSON outputs in batch pipelines for routing by level.

Best For

Newsroom desk editor: pick follow-up priority stories from morning briefs and reject rumors.
Research analyst: rank event clusters by evidence and timeliness without treating rehashed old news as new signal.
Public-opinion monitoring engineer: flag weak-evidence items and emit follow-up verification fields.
Information-system developer: route incoming news by S/A/B/C/D level with auditable JSON results.

Related Skills

Professional Contract Review

@user_c3030ed3/accurlex-contract-review

Reviews Chinese-law contract text via the accurLex API, returns the full review opinion, and exports a Word document.

Professional 2026.08.29 ↓ 394

Active Comparator Single-SOC FAERS Safety Comparison Planner

@user_c7479c7a/active-comparator-single-soc-faers-safety-comparison

Generates executable FAERS active-comparator safety comparison research plans focused on one SOC or PT family.

Professional 2026.08.29 ↓ 398

Financial Data Analysis Expert

@user_15292d5a/yjkj-finance-data-analysis

A reference framework for financial data analysis covering statements, KPIs, visualization, and reporting templates, without executing code or collecting data.

Professional 2026.08.29 ↓ 362

Device Selection Advisor

@user_7a5540f4/device-selection-advisor

A knowledge-base-driven advisor for weak-current, network, and telecom equipment selection, covering parameter comparison, model recommendations, compatibility checks, and budgeting.