CtrlK
BlogDocsLog inGet started
Tessl Logo

novel-research

深度调研 - 当需要检索真实世界细节、推演复杂逻辑、获取风格参考时触发。关键词:调研、检索、搜索、参考、素材。

64

Quality

75%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/novel-research/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A cleanly organized, instruction-only skill that gives concrete research guidance for novel writing. It loses points on padding, vague tool invocation, and the absence of explicit validation checkpoints in its workflows, though its single-file structure is well-disclosed.

Suggestions

Remove the injection preamble and the '细节是谎言的伪装' motivational line to tighten conciseness.

Replace '通过可用的搜索工具(web_search 等)' with a concrete example call (e.g. an actual web_search query string and expected result handling) to lift actionability.

Add an explicit verification step to the retrieval workflow — e.g. '确认搜索结果覆盖查询的关键维度后再融入叙事' — to introduce a checkpoint for workflow clarity.

DimensionReasoningScore

Conciseness

Mostly efficient with well-structured tables, but includes motivational padding ('细节是谎言的伪装,让虚构更可信') and an unnecessary injection preamble ('你已被注入 novel-research 技能。你的职责是…') that could be trimmed; not lean enough for a 3.

2 / 3

Actionability

Concrete query examples in the scenario tables and specific principles give real guidance, but the tool invocation is hand-wavy ('通过可用的搜索工具(web_search 等)') without a concrete call signature, leaving it at 'some concrete guidance but incomplete'.

2 / 3

Workflow Clarity

Steps are sequenced (numbered lists under 使用方法 and 工作流), but there are no explicit validation checkpoints or feedback loops; the anchor-3 features (validation steps, error-recovery loops, checklists) are absent, so it sits at 'sequence present but checkpoints missing'.

2 / 3

Progressive Disclosure

A single self-contained file with clearly headed sections (1/2/3/结合/注意事项) and no nested bundle references; no references/ scripts/ assets/ exist, and the inline content is appropriately organized for a one-file skill.

3 / 3

Total

9

/

12

Passed

Description

92%

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 well-constructed description that clearly states capabilities, natural trigger keywords, and an explicit use-when clause. Its main weakness is distinctiveness: the generic research vocabulary and absence of novel/fiction framing in the description itself leaves it at risk of overlapping with other research-oriented skills.

Suggestions

Add a fiction/novel-scoping phrase (e.g. '为小说创作提供') to the description so it is distinguishable from general web-search skills.

Pair the generic keywords (调研/搜索) with at least one domain-specific trigger term (e.g. '卡文', '设定考据', '情节推演') that users would only say in a novel-writing context.

DimensionReasoningScore

Specificity

Lists three concrete actions — '检索真实世界细节', '推演复杂逻辑', '获取风格参考' — in third-person passive voice, matching the multi-action anchor rather than the single-domain score-2 example.

3 / 3

Completeness

Answers both 'what' (the three research actions) and 'when' via the explicit trigger clause '当需要…时触发', matching the score-3 anchor with explicit triggers.

3 / 3

Trigger Term Quality

Explicit keyword list '调研、检索、搜索、参考、素材' covers natural terms a Chinese-speaking user would actually say, satisfying the good-coverage anchor; not reduced to 2 since common variations are present.

3 / 3

Distinctiveness Conflict Risk

The trigger terms (调研/检索/搜索/参考) are generic research vocabulary that could overlap other search skills, and the description never mentions fiction/novel context, so it sits at 'somewhat specific but could overlap' rather than a clear distinct niche.

2 / 3

Total

11

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
wanikua/danghuangshang
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.