nsfc-code

根据 NSFC 标书正文内容，结合申请代码推荐库，为你给出 5 组申请代码1/2（主/次）推荐与理由；输出到 NSFC-CODE-vYYYYMMDDHHmm.md（只读，不修改标书）

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/nsfc-code/SKILL.md

Quality

Content

75%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.

The content is highly actionable with executable commands and a well-sequenced workflow, and it makes good use of one-level-deep bundle references. The main drag on conciseness is the tangential workspace/bug-collaboration boilerplate, and workflow clarity loses a point for lacking an explicit verification step that the final codes are valid and exactly five were produced.

Suggestions

Trim or move the "BenszAPI 任务工作区" and "与 bensz-collect-bugs 的协作约定" sections into a separate shared reference, since they are organizational overhead unrelated to the NSFC-code task.

Add an explicit validation checkpoint after step 4: verify each of the 5 recommended codes exists as a section key in nsfc_code_recommend.toml and that exactly 5 pairs were produced, looping back if not.

Add short 'see X for Y' labels next to the bundle references (e.g. the TOML and scripts) to make navigation more explicit and push progressive disclosure toward 5.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete commands and paths, but the "BenszAPI 任务工作区" and "与 bensz-collect-bugs 的协作约定" sections are tangential organizational overhead not needed to perform the NSFC-code task, which is more than minor padding.	3 / 5
Actionability	It provides fully executable, copy-paste-ready bash commands with concrete flags (--input, --top-k, --output-dir, --prefix, --ts) and real referenced scripts, covering the common cases from input to deliverable.	5 / 5
Workflow Clarity	A clear 5-step sequence (timestamp/workspace → read-only read → deterministic ranking → AI 5-pick → write deliverable) with an uncertainty-handling checkpoint, but there is no explicit validation step confirming the final codes exist in the TOML library or that exactly 5 were produced — a minor validation gap.	4 / 5
Progressive Disclosure	The SKILL.md acts as an overview pointing to one-level-deep, clearly signaled bundle files (the 3425-line nsfc_code_recommend.toml, rank.py, new_report.py, plus a demo/ folder), with content appropriately split; navigation could be slightly more explicit with per-reference 'see X for Y' labeling to reach 5.	4 / 5
	Total	16 / 20 Passed

Description

65%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.

The description is specific and clearly niche-scoped with strong natural trigger terms, but it lacks an explicit 'Use when...' clause and uses second-person voice ("为你给出"), which caps completeness and lowers specificity. Adding an explicit trigger clause and switching to third-person voice would raise both dimensions.

Suggestions

Add an explicit 'Use when...' clause (e.g. 'Use when the user has an NSFC proposal and needs to choose 申请代码1/2') to lift completeness above 3.

Rewrite in third person (replace '为你给出' with '给出' / '生成') to avoid the voice penalty on specificity.

Include a couple of common synonyms (e.g. 国自然/国家自然科学基金, 申报代码) to broaden trigger-term coverage toward 5.

Dimension	Reasoning	Score
Specificity	The description lists several concrete actions ("给出 5 组申请代码1/2（主/次）推荐与理由", "输出到 NSFC-CODE-vYYYYMMDDHHmm.md", "只读，不修改标书") which would anchor at 4, but the second-person phrasing "为你给出" triggers the third-person voice penalty, reducing specificity by 1.	3 / 5
Completeness	The "what" is clearly stated (produce 5 code pairs with reasons, write to a named file, read-only), but there is no explicit "Use when..." trigger clause, so per the missing-trigger cap completeness cannot exceed 3; the "when" is only weakly implied.	3 / 5
Trigger Term Quality	It includes natural terms a Chinese NSFC applicant would actually say ("NSFC", "标书", "申请代码", "基金代码") with good coverage, but lacks broader synonyms (e.g. "国自然", "申报代码") or file extensions that would push it to 5.	4 / 5
Distinctiveness Conflict Risk	It occupies a clear, narrow niche (NSFC application-code recommendation) with distinct trigger terms and minimal overlap risk against other skills.	5 / 5
	Total	15 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: huangwb8/ChineseResearchLaTeX
Path: skills/nsfc-code/SKILL.md
Commit: f9a7f2c

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.