research-add-items

向现有调研outline补充items（调研对象）。

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

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

Quality

Content

85%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 body is concise, well-structured, and presents a clearly sequenced workflow with a user-confirmation checkpoint before the in-place file modification. The only gap is actionability: the dedup method and the exact merge/append format for outline.yaml are not specified.

Suggestions

Specify how duplicates are detected and avoided (e.g., match on item name/slug before appending) so the '避免重复' step is executable.

Show the concrete append format/structure for outline.yaml (an example item block) so the merge step is copy-paste ready.

Clarify how the optional Web Search agent is invoked (e.g., the Task call and how its results are merged back into the candidate item list).

Dimension	Reasoning	Score
Conciseness	The body is lean — short bullets and clearly labeled steps with no padding or explanation of concepts Claude already knows, matching the anchor for lean, efficient content where every token earns its place. It is not a 2 because there is no unnecessary explanation to tighten.	3 / 3
Actionability	It gives concrete guidance (the `*/outline.yaml` glob and explicit per-step actions) but leaves key details unspecified — how to detect/avoid duplicates and how items are appended into outline.yaml. It is not a 1 because the steps are concrete rather than abstract, and not a 3 because the dedup method and merge format are missing rather than copy-paste ready.	2 / 3
Workflow Clarity	The Step 1–3 sequence is clearly ordered and includes an explicit user-confirmation gate ("展示给用户确认") plus a dedup check before the in-place save, matching the anchor for a clear sequence with explicit validation steps. It is not a 2 because the checkpoint is explicit rather than missing or implicit.	3 / 3
Progressive Disclosure	The skill is under 50 lines with well-organized sections (触发方式, 执行流程/Step 1-3, 输出) and no need for external references, so per the simple-skills guideline progressive disclosure scores 3 on organization alone. It is not a 2 because the structure is clean and not monolithic or poorly organized.	3 / 3
	Total	11 / 12 Passed

Description

50%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 is concise and names a clear, specific niche, but it states only a single action and omits any "Use when..." trigger guidance. Every dimension lands at the mid-level because the "what" is adequate while trigger terms and explicit when-to-use cues are thin.

Suggestions

Add an explicit 'Use when...' / 「当需要...时使用」 clause stating the situations that should trigger this skill, which would lift completeness and trigger_term_quality.

List multiple concrete actions (e.g., locate outline, ask user, optionally web-search, append, dedup, save) instead of the single verb '补充' to improve specificity.

Add natural trigger-term variations (e.g., '补充调研对象', 'add research items', '扩展outline') to strengthen distinctiveness and reduce overlap with sibling research skills.

Dimension	Reasoning	Score
Specificity	The description names the domain ("调研outline", "items（调研对象）") and one concrete action ("补充"), matching the anchor that names a domain and some actions but is not comprehensive. It is not a 1 because the action and domain are concrete rather than vague, and not a 3 because only a single action is listed rather than multiple specific actions.	2 / 3
Completeness	It clearly answers "what" (补充items to an existing research outline) but provides no "Use when..." clause or equivalent explicit trigger guidance, so per the guideline completeness is capped at 2. It is not a 1 because the "what" is specific rather than weak, and not a 3 because no explicit "when" trigger is present.	2 / 3
Trigger Term Quality	It includes some relevant keywords a user might say ("调研", "outline", "items", "调研对象") but they are limited and "items"/"outline" are generic, matching the anchor for some relevant keywords missing common variations. It is not a 3 because there is no broad coverage of natural trigger variations, and not a 1 because the terms are natural rather than pure technical jargon.	2 / 3
Distinctiveness Conflict Risk	The niche (adding items to a research outline) is somewhat specific but the brief description lacks explicit distinct trigger language and could overlap with sibling research skills. It is not a 1 because it targets a defined workflow rather than being broadly generic, and not a 3 because the distinct triggers are not clearly established.	2 / 3
	Total	8 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
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
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.