news-pulse

公司新闻脉搏：股价异动时快速归因。用 4 个并行 Agent 侦察公司事件/监管政策/行业对手/市场情绪，产出"事件时间线 + 异动主因判断 + 是否触发论文重审"。

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./codex-skills/news-pulse/SKILL.md

Quality

Content

71%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.

A highly actionable, well-sequenced workflow with concrete tool calls, an agent prompt template, and a structured report schema, but it is verbose for a 'rapid response' skill and inlines long reference-style content (agent specs, report template) that would benefit from being split into separate files.

Suggestions

Move the 8-section 归因报告 template (第七步) and the 4 agent task specifications into reference files (e.g. references/report-template.md, references/agent-tasks.md) and link to them one level deep, reducing the SKILL.md body and improving progressive_disclosure.

Tighten the 关键原则 section and the per-agent sub-point lists to reduce token load for a skill whose stated value is a 10–15 minute rapid response.

Add an explicit error-recovery checkpoint (e.g. what to do when <4 reports arrive, or when a source fails 独立信源验证) to raise workflow_clarity from a clear sequence to one with feedback loops.

Dimension	Reasoning	Score
Conciseness	The body is task-specific rather than explaining general concepts, but at ~245 lines for a '10-minute rapid response' skill it is noticeably heavy; the 关键原则 section, the detailed per-agent sub-points, and the 8-section report template could be tightened without losing clarity.	3 / 5
Actionability	Provides copy-paste-ready guidance throughout: a full agent prompt template, concrete tool calls with parameters (TeamCreate, TaskCreate, SendMessage, TaskUpdate), and an exact CLI command (python3 tools/xueqiu_scraper.py --user-id 1247347556 ...) covering the common cases.	5 / 5
Workflow Clarity	Nine explicitly numbered steps form a clear sequence with checkpoints (wait for all 4 reports, 独立信源验证, 数据缺口声明, TeamDelete cleanup), but there is no explicit if-fail-then-retry recovery loop for the source-gathering or synthesis stages.	4 / 5
Progressive Disclosure	No bundle files exist and the skill is a single self-contained ~245-line file with good internal section headers, but long inline blocks (the 4 agent task specs and the 8-section report template) that clearly belong in separate reference files are not split out.	3 / 5
	Total	15 / 20 Passed

Description

75%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 focused, well-scoped description that names concrete actions, outputs, and an explicit stock-price-move trigger. It is concise and distinguishable from sibling research skills, with only minor gaps in synonym coverage and explicitness of the 'when' clause.

Dimension	Reasoning	Score
Specificity	Names the domain (公司新闻/股价异动) and lists several concrete actions across four scouting dimensions plus three explicit outputs (事件时间线 + 异动主因判断 + 是否触发论文重审), though the core verb is essentially '侦察' applied across dimensions rather than a list of distinct operations.	4 / 5
Completeness	Clearly states what (4 parallel agents scouting 4 dimensions, producing timeline + attribution + thesis-review trigger) and an explicit when ('股价异动时快速归因'), which is equivalent to a 'Use when stock price moves abnormally' trigger; the when could be slightly more explicit.	4 / 5
Trigger Term Quality	Includes natural user-facing terms like '股价异动', '公司新闻', and '归因' that a user would actually say, but omits common synonyms/variations such as 大涨/大跌, 财报, or ticker-based phrasing.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (rapid news attribution for abnormal stock moves) with a distinct trigger that separates it from deep investment research, earnings review, or thesis tracking, with only minor overlap risk against those closely related skills.	4 / 5
	Total	16 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: xbtlin/ai-berkshire
Path: codex-skills/news-pulse/SKILL.md
Commit: be46832

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.