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

71%

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

76%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 a concise, highly actionable script-driven skill with clean structure and correctly referenced bundle files. Its one real gap is the absence of an explicit validation/retry feedback loop for the database write step, which caps workflow clarity.

Suggestions

Add a validation feedback loop in '使用规则': after record-content.sh, check the JSON; on '{"ok": false}', surface the error and retry rather than proceeding.

Tell the user to ensure init-db.sh has run (or note record-content.sh auto-initializes) so the check step's 'DB missing → not exists' branch is not mistaken for 'not yet collected'.

De-duplicate the DB path: state it once and reference it, instead of repeating ./db/info_record.db in both the location block and the init line.

Dimension	Reasoning	Score
Conciseness	Lean, well-sectioned body with no padding or explanations of concepts Claude already knows; held at 4 because the DB path is repeated in both the '数据库位置' block and the init line, a minor trim opportunity.	4 / 5
Actionability	All four scripts are given as copy-paste-ready bash commands with full argument lists and documented JSON return shapes ('{"exists": true/false}', '{"ok": true, "id": <记录ID>}'), covering the common cases.	5 / 5
Workflow Clarity	A clear ordered 3-step sequence (check → record → query) is present, but it involves database/batch operations with no explicit validation feedback loop (e.g., handling '{"ok": false}' and retrying), which per the rubric caps workflow clarity at 3.	3 / 5
Progressive Disclosure	Well-organized sections with one-level-deep, clearly signaled script references that match the real bundle (init-db.sh, check-content.sh, record-content.sh, query-today.sh); short of 5 because the inline schema table is the only 'reference-like' material and there is no separate reference doc, though none is strictly needed.	4 / 5
	Total	16 / 20 Passed

Description

67%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 a strong, mostly concrete Chinese-language trigger description that states both what the skill does and when to use it, anchored on a distinct BD-intel niche. Its main weakness is trigger-term breadth and slightly generic action verbs.

Suggestions

Add synonyms/variation trigger terms (e.g., '商务拓展', '竞品情报', '采集去重', '已采集内容') so the description matches more natural user phrasings.

Split the single 'when' clause into per-action triggers (e.g., 'Use check-content before opening a post; use record-content after each collection; use query-today to summarize the day').

Name concrete source types in the description (xhs/dy/bilibili etc.) to sharpen specificity from 4 toward 5.

Dimension	Reasoning	Score
Specificity	Lists several 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') with a named technology (SQLite); short of 5 because the actions remain somewhat generic in verb form and omit content-type specifics.	4 / 5
Completeness	Explicit 'when' trigger ('当执行 BD 任务时') plus a clear multi-action 'what'; not 5 because the 'when' is a single general condition rather than concrete per-action trigger guidance for record vs query.	4 / 5
Trigger Term Quality	Includes natural trigger phrases ('当执行 BD（商务拓展）任务时', '情报采集', '按日查询') a user would say, but coverage lacks common synonyms or variations beyond the single BD/intel phrasing.	3 / 5
Distinctiveness Conflict Risk	The BD + intel-collection + SQLite-dedup niche is mostly distinct with low conflict risk; not 5 because it could marginally overlap with generic data-collection or note-taking skills.	4 / 5
	Total	15 / 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: TeamWiseFlow/xiaobei
Path: crews/main/skills/info-record/SKILL.md
Commit: fdc03d6

Reviewed: 21 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.