CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

web-form-fill

网络表单填报 — 收集字段与材料,使用xiaobei浏览器逐页填写、验证框架控件和草稿保存,最终提交由用户确认。

Quality

82%

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

SKILL.md
Quality
Evals
Security

Quality

Content

100%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 skill body is an exemplary compact instruction skill: terse and token-efficient, parameter-concrete for every control type, with an explicit validation-first workflow, feedback loops, and safe escalation to the user for submission and uncertain outcomes. Structure is clean with a single clearly signaled external reference and no content that should be split out.

DimensionReasoningScore

Conciseness

The body is lean, imperative, and assumes Claude's competence throughout — no concept explanations, no padding, and every line carries instruction (e.g., "先 snapshot 找到真实输入区域的 ref,点击聚焦"). The 14-line checklist example is a concrete template rather than filler, matching anchor 5's 'every token earns its place'.

5 / 5

Actionability

Guidance is parameter-level concrete across all control types: `act kind="type", replace=false`, `paths` with `inputRef`, `session="default"`, `headed=true`, `lease wait`/`renew`/`release`, plus a concrete artifact convention (`form-fields-<项目简称>.md`) with a worked example. As an instruction-only skill whose guidance is fully actionable and covers the common cases (text, rich text, cascading dropdowns, radio/checkbox, date, upload), it meets anchor 5.

5 / 5

Workflow Clarity

A clear 5-step sequence (collect fields → prepare content → fill and verify → save before page switches → pre-submission confirmation) with explicit validation checkpoints ("输入后核验", "核对关键字段", "逐页复核所有字段、单位和附件") and error-recovery feedback loops ("失败时重新聚焦,清空后重试一次;仍失败则记录为待人工填写"). Checklists and uncertain-outcome handling (OUTCOME_UNKNOWN) are present, matching anchor 5.

5 / 5

Progressive Disclosure

The body is ~46 substantive lines, well-organized into five numbered sections, with the only external pointer ("先读公共 **`browser-guide`**") clearly signaled at the top and one level deep. No bundle files exist and no inlined content clearly belongs in a separate file, so the compact well-organized skill merits anchor 5 per the under-50-line exception.

5 / 5

Total

20

/

20

Passed

Description

58%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 communicates a clear, specific capability with a concrete workflow and a named tool, but it omits any explicit 'when to use this' trigger guidance, which caps completeness and limits natural trigger-term coverage. Adding a 使用时机 clause with common synonyms (申报、登记、报名、在线填表) would lift it to the top tier.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to fill in, submit, or complete an online form / 申报表、登记表、报名表 on a website."

Include natural trigger synonyms users would actually say — 申报, 登记, 报名, 申请, 在线填表 — alongside 网络表单填报.

Briefly scope the skill (e.g., multi-step application/declaration forms) to sharpen distinctiveness against generic browser-automation skills.

DimensionReasoningScore

Specificity

The description lists several concrete actions — "收集字段与材料", "使用xiaobei浏览器逐页填写", "验证框架控件和草稿保存", "提交由用户确认" — naming both the tool and the workflow stages. It stops short of anchor 5 because coverage has minor gaps (e.g., no indication of which kinds of forms or sites are in scope), but exceeds anchor 3's '1-2 concrete actions' bar.

4 / 5

Completeness

The 'what' is clearly stated (collect fields, fill page by page with the xiaobei browser, verify controls and draft saving, user-confirmed submission), but there is no 'Use when...' / 使用时机 clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. It is not a 2 because the 'what' half is concrete and specific.

3 / 5

Trigger Term Quality

"网络表单填报" and "表单" are relevant, natural keywords, but the description misses common variations users would say such as 申报, 登记, 报名, 申请, or 填表. This matches anchor 3 ('some relevant keywords but missing common variations or synonyms') rather than anchor 4's 'good keyword coverage'.

3 / 5

Distinctiveness Conflict Risk

"网络表单填报" combined with the named "xiaobei浏览器" tool carves a mostly distinct niche with minimal conflict risk against document/PDF skills. It is not a 5 because a generic browser-automation skill could still plausibly trigger on overlapping form-filling requests.

4 / 5

Total

14

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository

TeamWiseFlow/xiaobei

Path

skills/web-form-fill/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.