bd-record

BD 线索与互动记录数据库（SQLite）：已探索创作者去重、已互动帖子去重。

Quality

64%

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/expert-bd/tools/bd-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 highly actionable with fully executable commands and clear JSON contracts, and it is lean without over-explanation. Its main gap is the absence of an error-recovery feedback loop for the database write operations, which caps workflow clarity.

Dimension	Reasoning	Score
Conciseness	The body is a lean reference (schema tables, commands, JSON returns, terse usage rules) with no padding over concepts Claude already knows; it stops at 4 because a few prose lines in 使用规则 could be marginally tightened.	4 / 5
Actionability	Every command is fully executable with all flags and a documented JSON return shape (e.g. 'bd-record record-creator --platform … --creator-id …' returning '{"ok": true, "id": …}'), covering the common check/record cases copy-paste ready.	5 / 5
Workflow Clarity	The 使用规则 section gives a clear check-before-act sequence (check-creator → skip if exists → record-creator; check-post → skip if done → record-post), but for database write operations there is no error-recovery feedback loop when record-creator/record-post return '{"ok": false}', so per the rubric workflow clarity is capped at 3.	3 / 5
Progressive Disclosure	Content is well-organized into clear sections (数据库位置, 表结构, 命令, 使用规则) and is self-contained; it does not reach 5 because the body is ~95 lines (not a simple <50-line skill) and the bundle scripts in ./scripts/ are invoked via a PATH wrapper rather than clearly signaled one-level-deep references.	4 / 5
	Total	16 / 20 Passed

Description

53%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 clearly states what the skill is but omits any 'when to use it' trigger guidance, leaving completeness capped at 3. Keywords are domain-relevant but jargon-heavy without natural user phrasing.

Suggestions

Add an explicit 'Use when…' clause, e.g. 'Use when exploring BD creators or engaging with posts and needing to avoid revisiting already-processed leads or posts.'

Broaden trigger terms with natural user phrasing and synonyms (e.g. 'BD 线索', '创作者去重', '已互动帖子', 'dedup leads', 'bd_record.db') so users' actual queries match the description.

Optionally mention the SQLite file path or the bd-record CLI wrapper as a concrete trigger cue to raise specificity and distinctiveness.

Dimension	Reasoning	Score
Specificity	Names the domain ('BD 线索与互动记录数据库（SQLite）') and two concrete actions ('已探索创作者去重', '已互动帖子去重'), matching the '1-2 concrete actions, not comprehensive' anchor; it does not reach 4 because no additional specific capabilities are listed.	3 / 5
Completeness	It gives a clear 'what' (a SQLite dedup database for BD leads and post interactions) but offers no 'when/Use when…' trigger guidance, so per the rubric completeness is capped at 3.	3 / 5
Trigger Term Quality	Relevant domain keywords are present ('线索', '互动记录', '去重', '帖子', 'SQLite') but they are jargon-heavy and lack natural user-facing variations, synonyms, or file extensions, fitting 'some relevant keywords but missing common variations'.	3 / 5
Distinctiveness Conflict Risk	The niche is specific and largely distinct (BD lead/interaction dedup via SQLite) with minor overlap risk; it stops short of 5 because no explicit distinct triggers are stated.	4 / 5
	Total	13 / 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/expert-bd/tools/bd-record/SKILL.md
Commit: 72fd07a

Reviewed: 5 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.