info-record

当执行 BD（商务拓展）任务时维护 SQLite 情报采集数据库，记录已采集的信息内容，避免重复采集，支持按日查询已采集情报。

Quality

75%

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 ./crews/main/skills/info-record/SKILL.md

Quality

Content

72%

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

A well-structured, highly actionable skill body with concrete commands and a sensible workflow; main gaps are minor redundancy and missing error-recovery guidance for the database operations.

Suggestions

Remove the duplicated init-db.sh invocation (keep it in one place) and consolidate the database-path reference to tighten token use.

Add a short error-recovery note for record-content.sh failures (e.g. retry or surface the {"ok":false,"error":...} result) to give the batch/database workflow a proper feedback loop.

Dimension	Reasoning	Score
Conciseness	The body is lean and avoids explaining concepts Claude knows, but the init-db.sh command is duplicated (数据库位置 section and 脚本命令 section) and the DB path is repeated, so it could be tightened further.	2 / 3
Actionability	Provides fully executable bash commands with every flag and the expected JSON return shapes (e.g. record-content.sh with --source/--source-type/--title/--author/--publish-date/--content and {"ok":...}), copy-paste ready.	3 / 3
Workflow Clarity	The 使用规则 section gives a clear check→record→query sequence with a dedup checkpoint, but this is a database/batch operation with no error-recovery feedback loop (record-content failure handling is absent), capping it at 2.	2 / 3
Progressive Disclosure	Content is organized into clear sections and the four referenced scripts (init-db.sh, check-content.sh, record-content.sh, query-today.sh) are real one-level-deep bundle files under scripts/, all verified present.	3 / 3
	Total	10 / 12 Passed

Description

77%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A fairly strong description that concretely states several capabilities and an explicit when-trigger, with room to improve trigger-term breadth and distinctiveness so it fires reliably for the right need.

Suggestions

Broaden trigger terms to include natural variations a user might say, e.g. '情报采集', '采集信息', '记录已采集内容', rather than relying solely on the 'BD任务' framing.

Narrow the activation context so it is less likely to overlap with other BD-related skills, e.g. explicitly tie it to intel-gathering/模式三 dedup rather than BD tasks in general.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — '维护 SQLite 情报采集数据库', '记录已采集的信息内容', '避免重复采集', '支持按日查询已采集情报' — matching the anchor for several specific concrete actions rather than a single domain/action.	3 / 3
Completeness	Explicitly states both what (maintain/record/dedup/query) and when ('当执行 BD...任务时' is an explicit trigger clause), so it is not capped at 2 for a missing 'Use when' equivalent.	3 / 3
Trigger Term Quality	The trigger '当执行 BD（商务拓展）任务时' plus terms like '情报采集' and '按日查询' are relevant, but coverage of natural term variations is narrow; not the broad set of synonyms a user might say.	2 / 3
Distinctiveness Conflict Risk	The intel-collection SQLite niche is specific, but the '当执行 BD 任务时' trigger is broad and could overlap with other business-development skills, so it is not a clearly distinct, low-conflict trigger.	2 / 3
	Total	10 / 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/info-record/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.