ask-echo

使用火山引擎 Ask-Echo 融合信息搜索 API 进行 web 搜索、web 搜索总结版和图片搜索。

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.trae/openclaw-skills/ask-echo/SKILL.md

Quality

Content

90%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 an exemplary lean operational guide: executable commands, concrete examples, real parameter limits, and no fluff. The two real gaps are the missing authentication/credential setup step in the workflow and the dangling external API-doc path instead of a bundled reference file.

Suggestions

Add a setup step covering required credentials (e.g., which environment variables like the API key must be set, and the .env locations the script auto-loads) plus a note on handling auth errors.

Replace the /root/api-docs/ask-echo.md absolute path with a reference file inside the bundle (e.g., references/api.md) so the pointer resolves wherever the skill runs.

Optionally move the advanced parameter details into that reference file, keeping the quick-start command examples in SKILL.md.

Dimension	Reasoning	Score
Conciseness	The body is lean and operational throughout — sections cover usage, examples, parameters, and output format with zero concept explanation or padding. Every token earns its place; nothing explains what Claude already knows.	5 / 5
Actionability	Commands are copy-paste ready with concrete examples ("python scripts/ask_echo.py \"北京旅游攻略\" --type web") and the advanced parameter section includes real limits ("web 最多 50 条，image 最多 5 条") and value enums. The referenced script scripts/ask_echo.py exists in the bundle.	5 / 5
Workflow Clarity	For a simple single-action skill the three-step sequence (prepare query → run script → read output) is unambiguous, which would merit a 5. It drops to 4 because the workflow omits any authentication setup — the script silently depends on credentials loaded from .env files, and a missing API key would cause an undocumented failure with no guidance.	4 / 5
Progressive Disclosure	The short body is well organized into clearly signaled sections and correctly references the bundled script (verified to exist). It is not a 5 because the API documentation pointer is an external absolute path (/root/api-docs/ask-echo.md) that is inaccessible from the bundle rather than a one-level-deep relative reference, and the parameter reference is inlined instead of split out.	4 / 5
	Total	18 / 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 is concise and specific about what the skill does, naming the exact API and its three search modes, but it entirely lacks "when to use it" trigger guidance and misses common natural-language synonyms. Adding a "Use when..." clause would raise both completeness and trigger-term quality.

Suggestions

Append an explicit trigger clause, e.g. "当用户需要进行联网搜索、图片搜索或需要搜索结果摘要时使用" (Use when the user needs web search, image search, or summarized search results).

Add natural synonyms users would say, such as 联网搜索, 搜资料, 查图片, or "search the web", so the skill triggers on real phrasing.

Briefly state the outcome (e.g., returns site results, LLM summaries, or image results) to sharpen the "what" toward anchor 5 specificity.

Dimension	Reasoning	Score
Specificity	The description lists several concrete actions — "进行 web 搜索、web 搜索总结版和图片搜索" (web search, web search summary, image search) — which cover the API's capability set with only minor gaps. It falls short of anchor 5 because the actions are narrow variants of one operation and no output or handling detail is given.	4 / 5
Completeness	The description gives a clear "what" (search via the Volcano Engine Ask-Echo API in three modes) but contains no "Use when..." trigger clause, so per the completeness cap it cannot exceed 3. It is not a 2 because the "what" is explicit and multi-part, not vague.	3 / 5
Trigger Term Quality	Relevant natural keywords like "web 搜索" and "图片搜索" are present, but common variations and synonyms a user would actually say (e.g., 联网搜索, 搜资料, 查图片, English equivalents) are missing. It sits between anchor 3 and 4, but the coverage is thin enough to match anchor 3.	3 / 5
Distinctiveness Conflict Risk	Naming the specific vendor API ("火山引擎 Ask-Echo 融合信息搜索 API") makes it mostly distinct with only minor overlap risk against generic web-search skills. It is not a 5 because "web 搜索" and "图片搜索" are broad triggers that could collide with other search skills.	4 / 5
	Total	14 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: huangruiteng/CS-Notes
Path: .trae/openclaw-skills/ask-echo/SKILL.md
Commit: 77c775d

Reviewed: 1 day 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.