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

72%

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

77%

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

The body is a strong, highly actionable orchestration workflow with concrete commands, agent configs, prompt templates, and a well-sequenced 9-step process with explicit synchronization checkpoints. Its main weakness is monolithic structure — no bundle files offload the detailed task specs or report template — and some verbosity in the report template that could be tightened.

Suggestions

Move the 4 detailed task descriptions and/or the 8-section report template into separate reference files under references/ and link to them from SKILL.md to improve progressive disclosure.

Tighten the report template (step 7) by trimming example table rows and merging closely related sections to improve conciseness without losing clarity.

Verify the referenced repo paths (tools/xueqiu_scraper.py, tools/financial_rigor.py, investment-team.md, AGENTS.md, CLAUDE.md) resolve from the skill's runtime location, or note explicitly that they are sibling repo resources.

Dimension	Reasoning	Score
Conciseness	The body is actionable and avoids explaining known concepts, but at ~240 lines the 4 detailed task specs and the elaborate 8-section report template with example rows could be tightened, matching the 'mostly efficient but could be tightened' anchor.	2 / 3
Actionability	Provides fully executable guidance — concrete commands like 'python3 tools/xueqiu_scraper.py --user-id 1247347556 …', explicit agent configs (subagent_type, run_in_background, team_name), a full prompt template, and output-format tables — matching the copy-paste-ready anchor.	3 / 3
Workflow Clarity	A clear 9-step sequence with explicit checkpoints — info-availability grading, '必须在同一条消息中并行调用 4 次', '等待全部 4 份到齐', shutdown after synthesis, and a data-gap declaration — meeting the anchor for clear sequencing with explicit checkpoints and a checklist.	3 / 3
Progressive Disclosure	It is a single monolithic ~240-line file with no bundle files provided (references/scripts/assets absent) and referenced repo files not present in-bundle; the detailed task specs and report template are inline content that could be split out, matching the 'some structure but content that should be separate is inline' anchor.	2 / 3
	Total	10 / 12 Passed

Description

67%

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, clearly naming the 4-agent scouting workflow and its three outputs, but it lacks an explicit 'Use when…' trigger clause and broader trigger-term coverage. Adding explicit when-to-use guidance with more natural trigger variations would raise completeness and trigger quality.

Suggestions

Add an explicit 'Use when…' clause (e.g., 'Use when a held/watched stock moves sharply and you need a fast cause attribution') to satisfy the completeness anchor for both what AND when.

Broaden trigger terms to include natural variations a user might say — e.g. '股价异动', '涨跌原因', '新闻归因', 'stock price move attribution' — rather than relying on '公司新闻脉搏' alone.

Keep the concrete 4-agent + 3-output framing; it is the description's strongest dimension and should be preserved.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — '用 4 个并行 Agent 侦察公司事件/监管政策/行业对手/市场情绪' and outputs '事件时间线 + 异动主因判断 + 是否触发论文重审' — matching the anchor for multiple specific concrete actions.	3 / 3
Completeness	WHAT is explicit, but WHEN is only implied via '股价异动时快速归因' with no 'Use when…' or equivalent explicit trigger clause, which caps completeness at 2 per the guidelines.	2 / 3
Trigger Term Quality	Natural terms like '公司新闻脉搏' and '股价异动' appear, but coverage of common variations is thin and there are no English/code-style equivalents users might also say.	2 / 3
Distinctiveness Conflict Risk	Carves a clear niche — rapid anomaly attribution rather than deep research — with distinct outputs (cause judgment + thesis re-review trigger), making it unlikely to fire for sibling investment skills.	3 / 3
	Total	10 / 12 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: 634a399

Reviewed: 1 day 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.