sn-search-year-report

用于搜索免费官方年报、年度报告、定期报告、上市公司披露文件、债券发行人报告和海外公司年度账目。

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 ./skills/sn-search-year-report/SKILL.md

Quality

Content

87%

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

The body is concise, highly actionable, and well-structured with executable commands and curated resource tables, and the referenced script is real. The only gap is an explicit validation/verification checkpoint for confirming a located PDF is the correct report before outputting it.

Suggestions

Add an explicit verification step to the workflow, e.g. 'After locating a PDF, confirm the report period and issuer match the request before returning it; if mismatched, refine the search.'

Optionally note how to handle a missing-PDF fallback to the official detail page as a checked step rather than only in the output spec.

Dimension	Reasoning	Score
Conciseness	Lean and efficient: it jumps straight into credential handling, a numbered workflow, executable CLI examples, and compact tables — no padding or explanations of concepts Claude already knows.	3 / 3
Actionability	Provides fully executable, copy-paste-ready commands ('python scripts/year_report_api.py cninfo "平安银行" --year 2023 --page-size 5') plus a concrete command table mapping free/no-key interfaces to use cases.	3 / 3
Workflow Clarity	A clear numbered workflow and a 'discard non-official sources' guard exist, but for a batch/download task there is no explicit validate-then-fix feedback loop (e.g. verify the PDF opened/is the right period before accepting), which caps this at 2.	2 / 3
Progressive Disclosure	Well-organized single-file overview with clear sections (workflow, API script, browser-use resources, discarded sources, output spec); the one referenced bundle file 'scripts/year_report_api.py' exists and is one level deep.	3 / 3
	Total	11 / 12 Passed

Description

57%

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 clearly scopes a distinctive niche (free official annual reports across multiple markets) but stops at the 'what' without an explicit 'Use when...' trigger and without naming concrete retrieval actions. Adding a trigger clause and verbs like 'locate and download' would raise completeness and specificity.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user asks for annual reports, 10-K/20-F filings, or listed-company disclosure PDFs for a specific company and period.'

Replace the single verb '搜索' with concrete actions such as 'locate, filter, and download PDFs / detail pages for'.

Add common trigger variations ('10-K', 'annual report', 'IR', '财务报表', '披露公告') to improve natural-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (free official annual reports) and enumerates several specific source categories ('上市公司披露文件、债券发行人报告和海外公司年度账目'), but does not list concrete actions like locating, downloading, or extracting — it only says '搜索'.	2 / 3
Completeness	Clearly states what the skill does but lacks an explicit 'Use when...' trigger; the 'when' is only implied by the domain, which per guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	Contains relevant natural terms ('年报、年度报告、定期报告、上市公司披露文件、债券发行人报告') but misses common user variations like '10-K', 'annual report', 'IR', '财务报表', so coverage is partial.	2 / 3
Distinctiveness Conflict Risk	The niche is clearly bounded to free official annual/periodic reports across named markets, with explicit exclusions (no commercial/subscription sources), making it unlikely to trigger for the wrong skill.	3 / 3
	Total	9 / 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: OpenSenseNova/SenseNova-Skills
Path: skills/sn-search-year-report/SKILL.md
Commit: 179fea1

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.