CtrlK
BlogDocsLog inGet started
Tessl Logo

common-fetcher

统一采集框架 - 支持 RSS/Web/API,207+ 采集源,AI 评分/分类/摘要

51

Quality

57%

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 ./.trae/openclaw-skills/common-fetcher/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body provides solid, executable CLI/API/config examples (strong actionability) but functions as a project README padded with marketing and project-metadata sections, lacks any validation/verification step for its batch fetching, and references files that are not bundled.

Suggestions

Trim README-style sections (architecture ASCII diagram, emoji feature list, 性能指标 table, 开发计划, 贡献指南, 许可证, 联系方式) that do not guide skill execution.

Add a brief validation/verification step for batch fetches, e.g. checking the output report for empty results or failed sources and retrying/reporting failures.

Either bundle the referenced config/ and src/parsers/ files (references/ or scripts/) with clearly signaled links, or remove the dangling references so the skill is self-contained.

DimensionReasoningScore

Conciseness

The actionable core (CLI/API/config examples) is concise, but the body is padded with README-style sections (ASCII architecture diagram, emoji feature bullets, industry source counts, performance marketing table, 开发计划/贡献指南/许可证/联系方式) that do not help Claude execute the skill. Not anchor 1 because it does not explain basic concepts Claude already knows, but the padding keeps it from 3.

2 / 3

Actionability

Provides copy-paste-ready CLI commands ("common-fetcher --industry coal --output daily.md"), a concrete Node.js API example with options, and an OpenClaw config snippet. Matches anchor 3 (fully executable commands/code, specific examples). The parser stub is incomplete but the primary usage paths are executable.

3 / 3

Workflow Clarity

Usage is shown as single commands with no sequenced workflow, and a batch operation (fetching/processing many articles across 207 sources) has no validation or verification step (e.g., checking output, handling parse failures), which per the guideline caps workflow clarity at 2. Matches anchor 2 (steps/usage present but checkpoints missing).

2 / 3

Progressive Disclosure

No bundle files exist (references/scripts/assets absent), yet the body references config/, src/parsers/, and *-sources.json that are not provided; everything is inline in one ~180-line file. README-like sections (architecture, performance, dev plan, contributing, license) are content that should be separate or removed. Matches anchor 2 (some structure, references not clearly signaled, content that should be separate is inline).

2 / 3

Total

9

/

12

Passed

Description

50%

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 concrete capabilities and uses third-person voice, but reads as a product tagline rather than a trigger-oriented skill description: it lacks a "Use when..." clause, leans on buzzword/over-claim phrasing, and omits common user-natural trigger terms.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user wants to collect, scrape, or aggregate news/data from RSS feeds, websites, or APIs, or needs AI-based scoring/classification/summaries of fetched articles."

Drop marketing-style over-claims ("207+ 采集源", "统一") in favor of concrete, verifiable capability wording.

Include common user-natural terms (抓取/采集/聚合数据, 抓新闻) so the skill surfaces for natural requests.

DimensionReasoningScore

Specificity

Names the domain and concrete capabilities ("支持 RSS/Web/API", "AI 评分/分类/摘要") but pads with a buzzword ("统一采集框架") and an over-claim ("207+ 采集源") and is not comprehensive about output/scheduling/CLI. Closer to anchor 2 than 3, and below 3 due to the buzzword/over-claim penalties.

2 / 3

Completeness

Answers "what" (a unified multi-source collection framework with AI processing) but provides no "Use when..." clause or equivalent trigger guidance, so per the guideline completeness is capped at 2. Matches anchor 2 (has what, when is missing/implied).

2 / 3

Trigger Term Quality

Contains relevant natural terms ("RSS", "Web", "API", "采集") but frames them as a product tagline rather than user-natural phrasing, and misses common variations like 抓取数据/信息采集/新闻聚合. Matches anchor 2 (some relevant keywords, missing common variations).

2 / 3

Distinctiveness Conflict Risk

The multi-source collection + AI scoring/summary niche is fairly specific, but "采集框架" with no explicit triggers could overlap with general scraping/data-gathering skills. Matches anchor 2 (somewhat specific but could overlap).

2 / 3

Total

8

/

12

Passed

Validation

81%

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

Validation13 / 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

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

13

/

16

Passed

Repository
huangruiteng/CS-Notes
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.