CtrlK
BlogDocsLog inGet started
Tessl Logo

deep-research-agent

深度研究技能,用于系统性调研与分析。适用于研究、调研、竞品分析、市场分析或结构化信息收集等需求。

56

Quality

63%

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 ./app/skills/deep-research-agent/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

62%

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

The content delivers a well-sequenced, validated research workflow with checklists, but it is weakened by placeholder-laden code examples, redundant cleanup instructions, and a core templates dependency that is neither bundled nor clearly disclosed.

Suggestions

Consolidate the repeated placeholder-cleanup guidance into a single authoritative step instead of restating it in 5.1–5.4.

Provide at least one fully executable file_write/file_update example with real values, or clearly label the blocks as templates to be filled.

Either bundle the templates/ directory and list the available template files, or remove the dependency so the skill is self-contained.

DimensionReasoningScore

Conciseness

The body is mostly actionable instruction with executable commands, but the placeholder-cleanup rule is restated across sections 4, 5.1, 5.2, 5.3, and 5.4, adding redundant repetition that could be tightened; not score 3 because of this redundancy.

2 / 3

Actionability

Script invocations (init_research.py, md_to_html.py) are concrete and executable, but the file_write/file_update code blocks are filled with placeholders ([标题]、[要点1]、{研究背景说明}) rather than being copy-paste ready, matching 'some concrete guidance but incomplete'.

2 / 3

Workflow Clarity

A clear six-step sequence with explicit gating ('获得用户确认后再继续', '3+ 可靠来源即可撰写', '检查通过后生成'), a feedback-oriented quality-check section, and a final checklist — matching 'clear sequence with explicit validation steps and checklists'.

3 / 3

Progressive Disclosure

Scripts are referenced by path and exist in the bundle, but the core templates/ directory is referenced only vaguely ('无需在此列出具体模板名称') and is not bundled, and most guidance is inline in SKILL.md, fitting 'some structure but could be better organized'.

2 / 3

Total

9

/

12

Passed

Description

65%

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 provides explicit trigger guidance and natural keywords, but the capability statement is generic ('systematic research and analysis') without concrete actions, and the broad research niche risks overlap with similar skills.

Suggestions

Replace the vague '系统性调研与分析' with concrete actions the skill performs (e.g., '构建大纲、增量采集来源、按章节撰写报告、生成结构化 JSON 与 HTML').

Tighten distinctiveness by scoping triggers to multi-source, structured research deliverables rather than generic '研究/调研'.

DimensionReasoningScore

Specificity

Names the research/analysis domain and several application contexts (竞品分析、市场分析、结构化信息收集) but describes only generic actions ('系统性调研与分析') rather than multiple concrete operations, matching the 'names domain and some actions, but not comprehensive' anchor.

2 / 3

Completeness

It has an explicit 'when' trigger ('适用于…需求') but the 'what' is vague ('系统性调研与分析') without concrete actions, so it does not reach the 'clearly answers both what AND when' bar of anchor 3; not score 1 because both elements are present.

2 / 3

Trigger Term Quality

Lists natural terms a user would say — '研究、调研、竞品分析、市场分析、结构化信息收集' — giving good coverage of common variations, fitting the 'good coverage of natural terms' anchor; not score 2 because it goes beyond a single keyword.

3 / 3

Distinctiveness Conflict Risk

'深度研究' gives a partial niche but the broad research/analysis framing and triggers could overlap with other research-oriented skills, matching 'somewhat specific but could still overlap'.

2 / 3

Total

9

/

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
ZHangZHengEric/Sage
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.