nsfc-budget

当用户明确要求“写/生成 NSFC 预算说明书”“写预算说明”“生成 budget.tex / budget.pdf”“写国自然预算 justification”时使用。基于用户标书正文或补充材料，输出一份可提交的预算说明书 LaTeX 项目并渲染 `budget.pdf`。若用户未指定工作目录，必须暂停并先要求其指定。⚠️ 不适用：用户只是想了解预算原则；用户仅要预算表数字而不写说明书；或用户是 2026 青年 A/B/C 默认包干制且无需预算说明书的场景。

Quality

92%

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

Quality

Content

85%

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 well-structured, highly actionable workflow with executable scripts, explicit validation feedback loops, and clean one-level-deep references. The only weakness is mild verbosity from project-convention boilerplate and rhetorical flourishes that could be trimmed for token efficiency.

Suggestions

Trim or move the BenszAPI workspace and bensz-collect-bugs collaboration boilerplate into a separate reference file so the core budget workflow stays lean.

Remove rhetorical flourishes like '经得起财务与学术双重审视' and '财务散文' in favor of direct statements to improve token efficiency.

Verify the referenced 'models/01/.template.yaml' key file actually exists in the bundle, or note it as a runtime-installed artifact, to keep the '关键文件' index accurate.

Dimension	Reasoning	Score
Conciseness	Mostly task-specific and efficient, but the BenszAPI workspace/bensz-collect-bugs convention blocks and rhetorical flourishes ('经得起财务与学术双重审视', '财务散文') add tokens not strictly needed for the budget task and could be tightened. Not level 3 because some boilerplate does not earn its place; not level 1 because it does not explain concepts Claude already knows.	2 / 3
Actionability	Provides concrete, copy-paste-ready commands invoking real existing scripts ('init_budget_run.py', 'render_budget_project.py' with full flags) and a precise budget_spec.json field schema. Not level 2 because the code/commands are fully executable, not pseudocode.	3 / 3
Workflow Clarity	Five clearly sequenced steps with an explicit validate→fix→retry feedback loop ('若校验失败，先修 budget_spec.json 再重新运行脚本，直到通过') and a delivery-time review checklist. Not level 2 because validation checkpoints and error-recovery loops are explicit.	3 / 3
Progressive Disclosure	SKILL.md is an overview that signals one-level-deep references to real, present files (info_form.md, budget-writing-rules.md) at the points they are needed, plus a '关键文件' index. Not level 2 because references are clearly signaled and content is appropriately split rather than inline.	3 / 3
	Total	11 / 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.

A strong, specific description that clearly states what the skill produces, when to invoke it via natural user triggers, and when not to. It is distinctive and uses third-person voice throughout. No significant improvements needed.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — '输出一份可提交的预算说明书 LaTeX 项目并渲染 budget.pdf' and the pause-to-request-workdir behavior — rather than vague language. Not level 2 because it names several specific deliverable actions, not just a domain plus 'some actions'.	3 / 3
Completeness	Explicitly answers both WHEN ('当用户明确要求…时使用') and WHAT (output a submittable budget LaTeX project and render budget.pdf) with explicit triggers and exclusions. Not level 2 because the 'when' is explicit, not merely implied.	3 / 3
Trigger Term Quality	Quotes natural utterances users would actually say ('写/生成 NSFC 预算说明书', '生成 budget.tex / budget.pdf', '写国自然预算 justification') plus explicit non-applicable cases, giving strong coverage of natural terms.	3 / 3
Distinctiveness Conflict Risk	Targets a narrow niche (NSFC budget justification) with distinct triggers and an explicit '⚠️ 不适用' exclusion list, making conflict with other skills unlikely.	3 / 3
	Total	12 / 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-budget/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.