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

66%

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

65%

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 clear sequenced workflow, and it correctly externalizes a large reference file; the main weaknesses are implicit verification checkpoints and references signaled as plain paths rather than navigable links.

Suggestions

Add an explicit verification checkpoint that confirms every recommended code is an existing section key in nsfc_code_recommend.toml before writing the deliverable (validate→fix→retry loop).

Convert inline file path strings into signaled markdown references (e.g., 'see [nsfc_code_recommend.toml](references/nsfc_code_recommend.toml)') with a short navigation note.

Consider trimming the BenszAPI workspace and bug-collection convention sections or moving them to a separate file, since they add tokens not essential to the core recommendation task.

Dimension	Reasoning	Score
Conciseness	The core process steps are lean and avoid explaining concepts Claude knows, but the 'BenszAPI 任务工作区' and 'bensz-collect-bugs 协作约定' sections add organizational boilerplate not strictly needed for the recommendation task, matching 'mostly efficient but could be tightened'; not 1 because there is no concept over-explanation, not 3 due to the non-essential overhead.	2 / 3
Actionability	Provides fully executable bash commands with exact script paths and flags (e.g., 'python3 skills/nsfc-code/scripts/nsfc_code_rank.py --input ... --top-k 50 --prefix A --output-dir ...') plus a copy-paste-ready Markdown output template, matching the 'fully executable, copy-paste ready' anchor.	3 / 3
Workflow Clarity	A clear 5-step sequenced process with timestamp/workspace isolation exists, but verification checkpoints are implicit: there is no validate→fix→retry loop and no wired-in step that confirms each recommended code actually exists in the TOML before output, so it sits at the 'sequence present but checkpoints missing or implicit' anchor rather than 3.	2 / 3
Progressive Disclosure	References are real and appropriately externalized (nsfc_code_recommend.toml, nsfc_code_rank.py, nsfc_code_new_report.py all exist, with the large TOML correctly kept out of the body), but they are inline path strings rather than signaled/navigable references and there is no explicit 'see X for details' navigation block, matching 'references present but not clearly signaled'.	2 / 3
	Total	9 / 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 concrete and action-specific with a clearly distinctive niche, but it lacks an explicit 'Use when…' trigger clause and leans on domain jargon rather than natural user-facing trigger terms, capping completeness and trigger quality at 2.

Suggestions

Add an explicit 'Use when…' clause naming natural user triggers (e.g., 'Use when the user has an NSFC proposal and needs to pick application codes / 基金代码 / 申请代码').

Broaden trigger terms toward phrasing a user would actually say ('基金代码选哪个', 'NSFC 报什么代码') rather than only 'NSFC 标书正文' jargon.

Keep the concrete action list but lead with the trigger context so 'what' and 'when' are both explicit.

Dimension	Reasoning	Score
Specificity	Lists multiple 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' — matching the 'multiple specific concrete actions' anchor; not 2 because it goes beyond naming just a domain and a few actions.	3 / 3
Completeness	Clearly answers 'what' (5 code-pair recommendations with reasons, output file) but has no explicit 'when to use it' clause; per the guidelines a missing 'Use when…' trigger caps completeness at 2.	2 / 3
Trigger Term Quality	Relevant domain keywords ('NSFC 标书正文', '申请代码', '推荐库') appear but only as niche jargon with no natural 'Use when…' variations in the description itself; missing common trigger phrasing, so not 3, but the terms are on-topic so above 1.	2 / 3
Distinctiveness Conflict Risk	A sharply narrow niche (NSFC application-code recommendation) with distinct triggers unlikely to overlap with other skills, matching the 'clear niche with distinct triggers' anchor.	3 / 3
	Total	10 / 12 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: 01044a6

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.