research

对目标话题进行初步调研，生成调研outline。用于学术调研、benchmark调研、技术选型等场景。

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/research-zh/research/SKILL.md

Quality

Content

77%Weight 40%Scale 1-3

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

The skill body is highly actionable, with a copy-paste-ready agent prompt and a clearly sequenced, checkpoint-gated workflow. Its main weaknesses are a redundant one-shot example that hurts conciseness and no use of file-based progressive disclosure for the lengthy template material.

Suggestions

Move the one-shot example into a separate references file (e.g., references/prompt-example.md) and link to it, reducing inline duplication and improving progressive disclosure.

Tighten or condense the one-shot example so it does not restate the full prompt template verbatim.

Add a brief validation step in Step 4/5 that checks outline.yaml and fields.yaml are well-formed before finalizing, strengthening the workflow's feedback loop.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and avoids explaining concepts Claude already knows, but the one-shot example (lines 69-108) largely restates the prompt template structure, adding redundant length that could be tightened.	2 / 3
Actionability	The web-search-agent prompt is given as a complete copy-paste-ready f-string template with explicit variables and a hard constraint ("必须严格复述"), plus a fully worked one-shot example, matching 'fully executable; copy-paste ready'.	3 / 3
Workflow Clarity	A clear five-step sequence with explicit AskUserQuestion confirmation gates at Steps 1, 2, 4, and 5 serves as validation checkpoints before proceeding, satisfying the 'clear sequence with explicit checkpoints' anchor.	3 / 3
Progressive Disclosure	The file is well-sectioned but exceeds 50 lines with a large inline prompt-template/one-shot block and no external reference files, matching 'some structure but content that could be separate is inline'.	2 / 3
	Total	10 / 12 Passed

Description

67%Weight 40%Scale 1-3

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 clearly states the skill's purpose and usage scenarios in third person, answering both what and when. It is somewhat held back by limited action specificity and trigger phrasing that is not in natural user terms.

Suggestions

Add a natural-language 'Use when...' trigger clause with common user phrasings (e.g., 'Use when starting a literature review, comparing benchmarks, or choosing a technology stack').

List more concrete actions the skill performs (e.g., 'searches the web, deduplicates items, writes outline.yaml and fields.yaml') to lift specificity.

Sharpen distinctiveness from sibling skills by emphasizing this is the initial outline-generation step before /research-deep.

Dimension	Reasoning	Score
Specificity	Names two concrete actions ("进行初步调研", "生成调研outline") but they are fewer and more abstract than the multi-action 3-anchor examples, so it sits at the 'names domain and some actions' level.	2 / 3
Completeness	It states both what ("进行初步调研，生成调研outline") and when ("用于学术调研、benchmark调研、技术选型等场景"), which is equivalent explicit trigger guidance, so it is not capped at 2 and reaches the 'answers both what AND when' anchor.	3 / 3
Trigger Term Quality	Relevant scenario keywords appear ("学术调研", "benchmark调研", "技术选型") but phrasing is not in natural user terms and lacks common variations, matching the 'some relevant keywords but missing common variations' anchor.	2 / 3
Distinctiveness Conflict Risk	The niche (preliminary research → outline generation) is reasonably specific but "调研" is broad and the body references sibling skills (/research-deep, /research-add-items), creating overlap risk, matching 'somewhat specific but could still overlap'.	2 / 3
	Total	9 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
relative_links	Relative link issues: 4 missing	Warning

	Total	14 / 16 Passed

Repository: Weizhena/Deep-Research-skills
Path: skills/research-zh/research/SKILL.md
Commit: e5479f8

Reviewed: 11 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.