CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

research-add-items

向现有调研outline补充items(调研对象)。

Quality

54%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/research-zh/research-add-items/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

55%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 exceptionally concise and well-structured for a small skill, but the workflow offers only vague hints with no executable commands or validation checkpoints for its outline-writing operation.

Suggestions

Add concrete executable detail: specify the actual glob (e.g., `find . -name 'outline.yaml'`), the outline.yaml schema for items, and how duplicates are detected.

Insert an explicit validation checkpoint before saving (e.g., parse the updated outline.yaml to confirm it is valid YAML and show the diff for user confirmation).

Specify the exact merge/format step (how new items are appended, required fields) so the action is copy-paste ready rather than descriptive.

DimensionReasoningScore

Conciseness

The body is a lean ~20-line workflow with no concept over-explanation and every line earning its place, matching the score-5 anchor of efficient content that assumes Claude's competence.

5 / 5

Actionability

Steps are high-level hints ("自动定位Outline", "询问用户") with no executable commands, file-glob specifics, or code, fitting the score-2 anchor of minimal concrete guidance missing the specific steps to execute.

2 / 5

Workflow Clarity

A rough 3-step sequence exists but Step 3 modifies outline.yaml (a write/batch operation) with no validation or duplicate-check checkpoint, and the destructive-write cap plus absent validation place it at the score-2 anchor of rough sequence with many gaps and no validation.

2 / 5

Progressive Disclosure

For a short single-purpose skill with no bundle files present, the body is well-organized into clear sections (触发方式, 执行流程, 输出) with appropriately placed content, matching the score-4 anchor of good structure with minor gaps.

4 / 5

Total

13

/

20

Passed

Description

33%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 conveys a clear single action but lacks any 'when to use' trigger guidance and leans on internal jargon rather than natural user keywords. It is marginally distinct from sibling research skills.

Suggestions

Add an explicit 'Use when...' clause naming natural trigger phrases (e.g., 'Use when the user wants to add more research targets to an existing outline').

Replace internal jargon ('items/调研对象') with user-facing synonyms and phrasings a person would actually say when requesting this.

Clarify the niche versus related research skills to reduce overlap risk (e.g., specify it only augments an existing outline.yaml, not creates one).

DimensionReasoningScore

Specificity

"向现有调研outline补充items(调研对象)" names the domain (research outline) and one concrete action (appending items), matching the score-3 anchor of a domain plus 1-2 concrete actions but not comprehensive coverage.

3 / 5

Completeness

It states a clear "what" (add items to an outline) but has no "Use when..." clause or equivalent trigger guidance, so per the judging guideline a missing trigger clause caps completeness and the vagueness-only-what pattern matches the score-2 anchor.

2 / 5

Trigger Term Quality

The phrase relies on technical jargon ("outline", "items", "调研对象") with no natural user-facing trigger terms a person would spontaneously say; this sits between the score-1 (only jargon) and score-3 anchors, leaning toward minimal generic keywords.

2 / 5

Distinctiveness Conflict Risk

It is somewhat specific (research-outline item supplementation) but could overlap with general research or outline-management skills, fitting the score-3 anchor of distinct-but-still-overlapping.

3 / 5

Total

10

/

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-add-items/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.