intel-gathering

定时监控特定信源（自媒体账号/网页），按预设标准提取商业情报，生成简报或报告。

Quality

68%

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 ./crews/main/skills/intel-gathering/SKILL.md

Quality

Content

77%

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

The content is highly actionable with executable scripts, a clearly sequenced workflow, dedup validation, and a thorough error-recovery table. It is slightly verbose in places and monolithic, with room to split detailed procedures into bundle files.

Suggestions

Move the per-source采集 procedures (自媒体账号 / 网页信源) into a referenced bundle file (e.g., references/collection-procedure.md) to improve progressive disclosure and shorten SKILL.md.

Tighten the prose in Step 2 by converting explanatory sentences into terse imperative steps to lift conciseness.

Add a brief 'verify before delivery' checkpoint in Step 3 (e.g., confirm query-today.sh returned expected records) to strengthen the final validation loop.

Dimension	Reasoning	Score
Conciseness	The body is largely action-oriented with minimal concept explanation, but instructional prose around steps and the notes section could be tightened further, fitting the score-2 'mostly efficient but could be tightened' anchor.	2 / 3
Actionability	Provides fully executable commands with complete argument signatures — 'check-content.sh --source <内容URL>', 'record-content.sh --source ... --content ...', 'fetch-rss.mjs <feed_url> --limit 10', 'query-today.sh' — matching the copy-paste-ready score-3 anchor.	3 / 3
Workflow Clarity	Steps are explicitly sequenced (Step 1/2/3) with a dedup validation checkpoint (check-content.sh → skip if exists) and an error-handling table with recovery loops, satisfying the clear-sequence-with-validation score-3 anchor; batch validation is present so the cap does not apply.	3 / 3
Progressive Disclosure	The skill is a single self-contained SKILL.md with well-organized sections and no nested references, but it is long enough that overview material and per-source procedures could be split out, matching the score-2 'some structure, content that should be separate is inline' anchor.	2 / 3
	Total	10 / 12 Passed

Description

60%

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 states concrete capabilities in third person but omits any explicit trigger/use-when guidance, which caps completeness and trigger quality. It is specific and reasonably distinct yet would benefit from a clear activation clause.

Suggestions

Add an explicit 'Use when...' clause stating when Claude should invoke this skill (e.g., '定时监控信源、采集商业情报、生成简报或报告时使用').

Expand trigger terms with common user phrasings such as '舆情监控', '竞品动态', '每日简报', '信源订阅' to improve natural-keyword coverage.

Sharpen distinctiveness by contrasting with one-shot search skills (e.g., '用于持续/定时监控，而非一次性搜索').

Dimension	Reasoning	Score
Specificity	Names a concrete domain (信源监控/商业情报) and lists multiple specific actions — '定时监控', '按预设标准提取商业情报', '生成简报或报告' — matching the score-3 anchor of multiple concrete actions.	3 / 3
Completeness	It answers 'what' (监控/提取/生成) clearly but provides no 'Use when...' or equivalent explicit 'when' guidance, so per the judging guidelines completeness is capped at 2.	2 / 3
Trigger Term Quality	Contains relevant natural keywords ('自媒体账号', '网页', '商业情报', '简报', '报告') but offers no explicit trigger phrasing and misses common variations, fitting the score-2 anchor of some keywords but missing variations.	2 / 3
Distinctiveness Conflict Risk	The scheduled source-monitoring niche is somewhat specific, but the phrasing could still overlap with general search/gathering skills and lacks distinct triggers, matching the score-2 'somewhat specific but could overlap' anchor.	2 / 3
	Total	9 / 12 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: TeamWiseFlow/xiaobei
Path: crews/main/skills/intel-gathering/SKILL.md
Commit: bcef823

Reviewed: 3 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.