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。

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

Quality

Content

81%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.

The content is a well-sequenced, actionable research workflow with strong validation checkpoints and a real supporting script bundle. Main improvements would be consolidating repeated placeholder-cleanup guidance and clarifying the exact tool/API names used in the code examples.

Suggestions

Consolidate the repeated placeholder-cleanup rules (sections 4, 5.1, 5.3) into one canonical checklist to reduce redundancy.

Replace illustrative tool calls (file_write/file_update) with the actual executable tool/API names or note them as placeholders explicitly.

DimensionReasoningScore

Conciseness

The body is efficient and assumes competence, though the placeholder-cleanup guidance is repeated across sections 4, 5.1, 5.3, and the checklist, which could be consolidated.

4 / 5

Actionability

Provides concrete commands (init_research.py, md_to_html.py) and code patterns for file_write/file_update, but uses illustrative tool names rather than a verified executable API, leaving minor gaps.

4 / 5

Workflow Clarity

Presents a clear 6-step sequence with an explicit user-confirmation checkpoint, a dedicated quality-check section (step 5), and a final checklist providing strong validation and feedback-loop structure.

5 / 5

Progressive Disclosure

Well-structured overview that references real bundle files (scripts/init_research.py, scripts/md_to_html.py) at one level deep, with only minor gaps where template specifics are deferred.

4 / 5

Total

17

/

20

Passed

Description

70%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.

The description is mostly clear and specific, with both a stated purpose and explicit applicable scenarios in third person. It could be strengthened by listing more concrete actions and using a more directive 'Use when...' trigger clause.

Suggestions

Add a more directive trigger clause such as '当用户需要研究、调研、竞品分析、市场分析或结构化信息收集时使用'.

Expand concrete actions beyond '系统性调研与分析' to mention deliverables like outline, incremental report building, and HTML/JSON output.

DimensionReasoningScore

Specificity

Names the research domain and a few concrete applications (竞品分析, 市场分析, 结构化信息收集), but the core actions are abstract ('系统性调研与分析') rather than a comprehensive list of concrete operations.

3 / 5

Completeness

Has a clear 'what' (深度研究技能用于系统性调研与分析) and an explicit 'when' (适用于研究、调研、竞品分析...), though the trigger phrasing could be more directive like 'Use when...'.

4 / 5

Trigger Term Quality

Includes natural user terms like 研究, 调研, 竞品分析, and 市场分析 with useful synonyms, though a few common variations are absent.

4 / 5

Distinctiveness Conflict Risk

Targets a clear research/investigation niche with distinct triggers, with only minor overlap risk against generic analysis skills.

4 / 5

Total

15

/

20

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.