stock-announcements

获取A股上市公司公告信息（真实数据）。基于AkShare从东方财富网获取当日全部公告，支持按股票代码筛选、关键词过滤。适用于监控重大事件、业绩快报、股东变动、重组公告等投资决策关键信息。数据源：东方财富网（稳定可靠）。

Quality

86%

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

Quality

Content

72%

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

The body is highly actionable with executable commands and a clean parameters table, and it references a real bundle script at one level of depth. It loses points for a marketing-fluff section that hurts token efficiency and for a workflow that lacks explicit validation/error-recovery checkpoints.

Suggestions

Remove or trim the "真实数据保证" section — the data source is already in the description, and phrases like "官方权威数据" / "稳定可靠" are reassurance rather than instruction.

Add a validation/feedback step to the Workflow, e.g. what to do when no announcements are returned or when akshare is missing, so Step 2→3 has an explicit checkpoint.

Mention the --detail (PDF extraction/summary) capability in the description or a brief callout, since it is a real feature not surfaced in the overview.

Dimension	Reasoning	Score
Conciseness	Most of the body is efficient (copy-paste commands, a Parameters table), but the "真实数据保证" section is marketing fluff ("官方权威数据", "稳定可靠") that repeats the data source already stated in the description and does not help Claude act. It is not a 3 because not every token earns its place.	2 / 3
Actionability	The Usage section gives fully executable, copy-paste-ready bash commands covering every flag (--days, --keyword, --format, --detail), backed by a concrete Parameters table pointing to the real scripts/announcements.py. It is not a 2 because the examples are complete and executable rather than pseudocode.	3 / 3
Workflow Clarity	The three Workflow steps are clearly sequenced (identify code → query → interpret), but there are no explicit validation checkpoints or feedback loops (e.g., what to do on empty results or an akshare ImportError). It is above a 1 because the sequence is present, but below a 3 because error-recovery checkpoints are missing.	2 / 3
Progressive Disclosure	The SKILL.md is a clear overview that signals a single one-level-deep reference (scripts/announcements.py, which exists in the bundle) with well-organized sections and no nested reference chains. It is not a 2 because references are clearly signaled and content is appropriately inline rather than dumped into a monolithic block.	3 / 3
	Total	10 / 12 Passed

Description

100%

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, uses natural trigger terms, and explicitly pairs a 'what' statement with a '适用于' 'when' clause, with no first/second-person voice issues. It is distinctive and low-conflict. The only minor gap is that secondary capabilities (JSON output, --detail PDF extraction) are not surfaced, but core actions are clearly named.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — "获取…公告", "按股票代码筛选", and "关键词过滤" — rather than vague language, matching the multi-action anchor. It is not the level below, which only names a domain and partial actions.	3 / 3
Completeness	It explicitly answers both what ("获取A股上市公司公告信息") and when via the explicit trigger clause "适用于监控重大事件、业绩快报…", so it is not capped at 2 for a missing 'Use when' clause. It is written in third person, so no voice penalty applies.	3 / 3
Trigger Term Quality	It covers natural terms a Chinese investor would actually say — "公告", "业绩快报", "股东变动", "重组公告", "重大事件" — giving good coverage rather than just a few relevant keywords.	3 / 3
Distinctiveness Conflict Risk	The niche is highly specific (A-share announcements via AkShare from 东方财富网) with distinct announcement-type triggers, making it unlikely to fire for the wrong skill.	3 / 3
	Total	12 / 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: netease-youdao/LobsterAI
Path: SKILLs/stock-announcements/SKILL.md
Commit: 2921c1e

Reviewed: about 10 hours 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.