bd-record

当执行 BD（商务拓展）任务时维护 SQLite 追踪数据库，记录已探索的创作者（模式一）和已互动的帖子（模式二），避免重复追踪和重复互动。

Quality

72%

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/bd-record/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.

A tight, highly actionable skill body with executable commands and documented JSON contracts, hindered only by an implicit (not explicit) error-feedback loop after recording and an inline schema that could be a separate reference. Both are minor and easily improved.

Suggestions

Add an explicit feedback loop: after record-creator.sh / record-post.sh, instruct Claude to check the JSON 'ok' field and retry or surface the 'error' when ok is false.

Move the full table-schema definitions into a reference file (e.g. SCHEMA.md) and link to it from SKILL.md, keeping only field summaries inline, to improve progressive disclosure.

State explicitly that init-db.sh is idempotent and can be run before any command (the header says it but the workflow does not reinforce it).

Dimension	Reasoning	Score
Conciseness	The body is lean: table schemas and exact executable commands with no padding, no explanation of concepts Claude already knows (e.g. what SQLite is), and every token earns its place.	3 / 3
Actionability	Every command is fully executable with real paths and flags ('./skills/bd-record/scripts/init-db.sh', check-creator.sh with --platform/--creator-id), and JSON return shapes are documented, making it copy-paste ready.	3 / 3
Workflow Clarity	The '使用规则' section sequences check-then-skip-then-record steps for both modes, but the check-and-skip pattern itself is the validation checkpoint; however it never explicitly verifies the record-post.sh return value or handles error feedback ('{"ok": false}'), so the validation loop is implicit rather than explicit.	2 / 3
Progressive Disclosure	Content is well-organized into sections and all referenced scripts (init-db.sh, check-creator.sh, record-creator.sh, check-post.sh, record-post.sh) are real files in ./scripts/, but the full table-schema reference is inline in SKILL.md rather than offloaded to a separate file, and there are no one-level-deep reference links to a schema/detail doc.	2 / 3
	Total	10 / 12 Passed

Description

67%

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 specific and occupies a clear, non-conflicting niche, but it lacks an explicit 'when to use' trigger clause and richer natural trigger terms. Adding a 'Use when performing BD lead-hunting or comment engagement...' clause would raise completeness and trigger-term quality.

Suggestions

Add an explicit trigger clause, e.g. 'Use when performing BD (商务拓展) lead-hunting or comment-engagement tasks and needing to avoid re-contacting the same creators or posts.'

Include more natural user-facing keywords such as '商务拓展', '联系创作者', '回帖互动', '避免重复联系' so users would naturally say them.

Keep third person but name the two modes more plainly as triggers (lead-hunting vs comment engagement) to aid discovery.

Dimension	Reasoning	Score
Specificity	Lists concrete actions ('维护 SQLite 追踪数据库', '记录已探索的创作者', '记录已互动的帖子') plus the concrete purpose of avoiding '重复追踪和重复互动', matching the multiple-specific-actions anchor.	3 / 3
Completeness	It clearly states what the skill does, but there is no explicit 'Use when...' trigger clause telling when Claude should invoke it, which per the guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	Contains relevant domain terms ('BD', '商务拓展', '创作者', '帖子互动') but lacks common user-facing variations a user might naturally say (e.g. '商务拓展追踪', '避免重复联系创作者'), so coverage is partial.	2 / 3
Distinctiveness Conflict Risk	The niche is narrow and distinct (a BD SQLite tracking database for two specific modes), with little overlap risk against other generic skills.	3 / 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/bd-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.