CtrlK
BlogDocsLog inGet started
Tessl Logo

nsfc-justification-writer

当用户明确要求"写/改 NSFC 立项依据""立项依据写作/重构"时使用。基于最小信息表输出价值与必要性、现状不足、科学问题/假说与项目切入点,并保持模板结构不被破坏。适用于 NSFC 及各类科研基金申请书的立项依据写作场景。

68

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

85%

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 skill body with an explicit sequenced workflow, validation checkpoints, and clean progressive disclosure to verified reference files. The main weakness is non-core framework-policy sections that consume token budget without advancing the writing task.

Suggestions

Move the 'BenszAPI 任务工作区' and '与 bensz-collect-bugs 的协作约定' framework-policy sections into a shared reference file so the SKILL.md body stays focused on the justification-writing task and saves context tokens.

DimensionReasoningScore

Conciseness

The core sections (输出契约, 硬规则, 推荐工作流) are lean bullets with no concept re-explanation, but the 'BenszAPI 任务工作区' and '与 bensz-collect-bugs 的协作约定' sections spend tokens on framework policy (temp-file paths, bug-reporting rules) that is non-core to the writing task, matching 'mostly efficient but includes some unnecessary explanation'; not 3 because of that non-core overhead, not 1 because nothing is verbose or padded.

2 / 3

Actionability

Provides concrete, runnable commands ('scripts/run.py coach --stage auto', 'scripts/run.py init', 'diagnose', 'review', 'apply-section', 'diff', 'rollback'), exact file contracts ('extraTex/1.1.立项依据.tex', 'main.tex', 'extraTex/@config.tex'), and a named config switch ('config.yaml:style.mode' → theoretical/mixed/engineering), meeting the 'fully executable commands; copy-paste ready' anchor; absence of inline code is acceptable for this instruction-only skill since the guidance is actionable.

3 / 3

Workflow Clarity

The 推荐工作流 is an explicit 8-step sequence with validation checkpoints (stage detection via 'coach --stage auto', 可核验性与引用守护, 术语/缩写/指标一致性检查) and recovery affordances (自动备份, rollback), matching the 'clear sequence with explicit validation steps; feedback loops' anchor; not capped at 2 because the LaTeX-editing destructive operation is covered by diagnose/backup/rollback.

3 / 3

Progressive Disclosure

The body is a well-signaled overview pointing one level deep to real reference files ('references/info_form.md', 'references/scientific_question_guidelines.md', etc., all verified present) and scripts, with substantive writing guidance split out rather than inlined, matching the 'clear overview with well-signaled one-level-deep references' anchor; the nested references/docs/workflows/ is organizational, not the chained-reference anti-pattern.

3 / 3

Total

11

/

12

Passed

Description

85%

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 explicitly pairs capability with an explicit use-when trigger and a distinct niche. The only weakness is trigger-term breadth, which leans heavily on the '立项依据' family and omits other natural phrasings from the description itself.

Suggestions

Broaden the trigger terms inside the description to include natural variants like '研究意义', '为什么要做', '国内外现状', '现有不足', '切入点' rather than relying on the frontmatter triggers list for that coverage.

DimensionReasoningScore

Specificity

Names multiple concrete outputs/actions — '输出价值与必要性、现状不足、科学问题/假说与项目切入点' and '保持模板结构不被破坏' — matching the 'lists multiple specific concrete actions' anchor; it is above 2 because the actions are enumerated and specific rather than a single vague domain mention.

3 / 3

Completeness

Explicitly answers both 'what' ('基于最小信息表输出…') and 'when' ('当用户明确要求…时使用'), with an explicit Use-when trigger clause, so it is not capped at 2 per the guideline and clearly meets the 'answers both what AND when' anchor.

3 / 3

Trigger Term Quality

Triggers center on the '立项依据' term family ('写/改 NSFC 立项依据', '立项依据写作/重构') which are natural, but common variations a user might say (研究意义, 为什么要做, 国内外现状) appear only in the frontmatter triggers list, not the description, so coverage is partial rather than comprehensive; not 3 because of the missing common variations, not 1 because the stated terms are genuinely natural.

2 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (NSFC / 科研基金申请书 立项依据 writing) with domain-specific triggers unlikely to fire for unrelated skills, matching the 'clear niche with distinct triggers' anchor; it is above 2 because the scope is narrowly scoped to grant-justification writing rather than a generic document skill.

3 / 3

Total

11

/

12

Passed

Validation

75%

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

Validation12 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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

referenced_paths_exist

Referenced path issues: 1 deeper-than-1-level

Warning

Total

12

/

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.