CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

research-deep

读取调研outline,为每个item启动独立agent进行深度调研。禁用task output。

Quality

74%

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/research-zh/research-deep/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

82%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 body is highly actionable with a concrete, copy-paste-ready prompt template and validation step embedded in a clearly sequenced batch workflow. It is concise and well-structured, with only minor redundancy and a non-explicit error-recovery loop.

DimensionReasoningScore

Conciseness

Lean body with no concept over-explanation; the only redundancy is the one-shot example largely restating the prompt template; not a 5 because that example could be trimmed.

4 / 5

Actionability

Provides a copy-paste-ready f-string prompt template, exact parameter definitions, a full validation command with absolute path, and slugify rules; covers the common case completely.

5 / 5

Workflow Clarity

Steps 1–5 are clearly sequenced with a validation checkpoint (validate_json.py, '验证通过后才算完成任务'), user-gate between batches, and resume support; not a 5 because the validate→fix→retry feedback loop is implied rather than explicit.

4 / 5

Progressive Disclosure

Well-organized into clear sections with a one-level prompt template and no nested references; external paths (validate_json.py, fields.yaml) are runtime dependencies rather than bundled skill files; not a 5 because the body is over 50 lines and the one-shot example is inlined.

4 / 5

Total

17

/

20

Passed

Description

55%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 states concrete actions but omits any explicit 'Use when' trigger guidance, which limits its completeness and trigger quality. It is reasonably specific to a deep-research workflow but risks overlap with generic research skills.

Suggestions

Add an explicit 'Use when…' clause naming natural trigger phrases (e.g. 'Use when the user asks for deep per-item research driven by an outline.yaml').

Include synonyms/file extensions as trigger terms (outline.yaml, 深度调研, 逐项调研) to improve distinctiveness and keyword coverage.

Tighten the action list into one comprehensive sentence rather than separating the ancillary '禁用task output' detail.

DimensionReasoningScore

Specificity

Names the research domain and several concrete actions ('读取调研outline', '为每个item启动独立agent', '深度调研', '禁用task output'); not a 5 because coverage of capabilities is narrow rather than comprehensive.

4 / 5

Completeness

Has a clear 'what' (read outline, launch per-item agents, disable task output) but no explicit 'when/Use when' guidance; per the rubric a missing trigger clause caps this at 3.

3 / 5

Trigger Term Quality

Includes the relevant natural term '调研'/'深度调研' but lacks a 'Use when…' clause and common synonyms or file extensions; not a 4 because keyword coverage is thin rather than just missing a few.

3 / 5

Distinctiveness Conflict Risk

The per-item deep-research niche is somewhat distinct, but the broad '调研' framing could overlap with other research skills; not distinct enough for a 4.

3 / 5

Total

13

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

Total

15

/

16

Passed

Repository

Weizhena/Deep-Research-skills

Path

skills/research-zh/research-deep/SKILL.md

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.