CtrlK
BlogDocsLog inGet started
Tessl Logo

nsfc-qc

当用户明确要求"标书QC/质量控制/润色前质检/引用真伪核查/篇幅与结构检查"时使用。对 NSFC 标书进行只读质量控制:并行多线程独立检查文风生硬、引用假引/错引风险、篇幅与章节分布、逻辑清晰度等,最终输出标准化 QC 报告;中间文件默认归档到 `project_root/.bensz-api/task-{yyyymmdd-hhmm}-{简短描述}/nsfc-qc/{yyyy-mm-dd-hh-mm}/`,并兼容 legacy `.nsfc-qc/` 读取/清理。

71

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

82%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.

A well-structured, actionable body with executable commands, a clear multi-phase workflow, and explicit read-only constraints. The main weaknesses are mild verbosity from duplicated input sections and policy boilerplate, an implicitly stated validation checkpoint, and an unreferenced checklist file in the bundle.

Suggestions

Link references/qc_checklist.md from the 多线程独立 QC section (e.g., "每个 thread 按 [qc_checklist.md](references/qc_checklist.md) 执行") so the existing reference is signaled and discoverable.

Tighten the validation step: replace "完成后执行…静态检查、脚本验证或人工复核" with an explicit checkpoint naming the script and pass criteria (e.g., run validate_final_outputs.py and only proceed on exit 0).

De-duplicate the two "### 输入" sections (lines 13–24 and 33–35) into a single input section to remove redundancy and trim tokens.

DimensionReasoningScore

Conciseness

Mostly lean bullet-form directives with executable commands and minimal concept re-explanation, but the duplicated "### 输入" section and the verbatim "公共硬约束" policy block add some padding that could be trimmed.

4 / 5

Actionability

Provides copy-paste-ready bash commands with real flags (nsfc_qc_run.py, nsfc_qc_precheck.py, run_parallel_qc.py, materialize_final_outputs.py) and concrete output-file paths covering the common cases.

5 / 5

Workflow Clarity

Clear sequenced phases (预检 → 多线程 QC → 汇总聚合 → 标准化报告 → 校验 → 失败与恢复) with a dedicated validation section and a fallback feedback loop, but the validation step is stated somewhat implicitly ("执行…或人工复核") rather than as an explicit pass/fail checkpoint.

4 / 5

Progressive Disclosure

Well-sectioned overview pointing to scripts via commands (verified real files), but references/qc_checklist.md exists as a bundle reference yet is never linked or signaled from SKILL.md, leaving a minor navigation gap.

4 / 5

Total

17

/

20

Passed

Description

92%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.

A strong, explicit description that clearly states what the skill does and when to use it, with concrete trigger phrases and a well-defined NSFC-QC niche. The only minor gap is trigger-term breadth (no format/extension terms), keeping trigger_term_quality at 4 rather than 5.

DimensionReasoningScore

Specificity

Lists multiple concrete check actions — "文风生硬、引用假引/错引风险、篇幅与章节分布、逻辑清晰度等" plus "输出标准化 QC 报告" — giving comprehensive, specific coverage rather than vague language.

5 / 5

Completeness

Explicitly answers both: "当用户明确要求…时使用" (when) and "对 NSFC 标书进行只读质量控制…输出标准化 QC 报告" (what), with concrete trigger phrases.

5 / 5

Trigger Term Quality

Includes natural user-facing phrases ("标书QC/质量控制/润色前质检/引用真伪核查/篇幅与结构检查") with synonyms, but stops short of comprehensive coverage (no file-extension or format triggers).

4 / 5

Distinctiveness Conflict Risk

Scoped to a clear niche (NSFC proposal read-only QC) with distinct triggers, so overlap with other skills is minimal.

5 / 5

Total

19

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository
huangwb8/ChineseResearchLaTeX
Reviewed

Table of Contents

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.