published-track

发布记录追踪。使用 SQLite 数据库记录所有平台发布内容及其互动数据，按平台分表管理。三大块：与发布技能结合（发布记录 1B；打分+预测 1A 由 content-calibrator 负责）、数据更新、查询与平台设置。

Quality

72%

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/published-track/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 concrete commands, clear sequencing, and validation checkpoints for database operations. Weaker spots are conciseness (some rationale/prose padding) and progressive disclosure (an existing reference file is not linked from the body and heavy detail stays inline).

Suggestions

Link references/platform-constraints.md explicitly from the body (e.g., a '发布前合规校验 → see references/platform-constraints.md' pointer) so the bundled reference is clearly signaled.

Move the long 'xhs 取数路线' implementation detail into a reference file and keep only the essential route + gotchas inline to tighten conciseness.

Trim or collapse the '设计依据' rationale blockquotes into one-line notes to reduce token overhead.

Dimension	Reasoning	Score
Conciseness	The body is mostly dense and actionable (tables, full commands), but passages like the '设计依据' rationale blocks and the long 'xhs 取数路线' prose add explanation that could be tightened, fitting the 'mostly efficient but includes some unnecessary explanation' anchor rather than the lean 3.	2 / 3
Actionability	Provides fully executable, copy-paste-ready commands with concrete arguments (record.sh, fetch-and-update-metrics.sh), field tables, and explicit JSON return formats, matching the 'fully executable code/commands; copy-paste ready' anchor.	3 / 3
Workflow Clarity	The 1A→发布→1B sequence is explicitly ordered with validation checkpoints (missing score.json/prediction.md '报错退出' with a rerun hint, upsert dedup semantics, exit codes), giving clear feedback loops for the database operations, matching the 'clear sequence with explicit validation steps' anchor.	3 / 3
Progressive Disclosure	The body is well sectioned and references real scripts inline, but the bundled references/platform-constraints.md is never signaled from the body and substantial detail (xhs取数路线, platform table) is inline rather than split out, fitting the 'some structure but could be better organized; references present but not clearly signaled' anchor.	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 clearly differentiated, with concrete named capabilities and a well-scoped niche. Its main weakness is the absence of an explicit 'Use when...' trigger clause and reliance on internal jargon, which limits trigger-term quality and completeness.

Suggestions

Add an explicit 'Use when...' clause naming the natural user triggers (e.g., 'Use when tracking published content across platforms, updating engagement metrics, or querying distribution status').

Replace or gloss internal shorthand like '1A/1B' and 'content-calibrator' with user-facing terms so the description reads as natural trigger language.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — '使用 SQLite 数据库记录所有平台发布内容及其互动数据，按平台分表管理', plus three named blocks (data update, query, platform settings), matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Clearly states what the skill does but provides no 'Use when...' trigger guidance, so per the judging guidelines the missing explicit when caps completeness at 2.	2 / 3
Trigger Term Quality	Contains some natural terms ('发布记录追踪', '互动数据', '查询') but mixes in internal jargon ('1A/1B', 'content-calibrator') and lacks common user-facing variations, fitting the 'some relevant keywords but missing common variations' anchor.	2 / 3
Distinctiveness Conflict Risk	The niche (per-platform SQLite publishing-record tracking with scoring integration) is distinct and unlikely to trigger for unrelated skills, matching the 'clear niche with distinct triggers' anchor.	3 / 3
	Total	10 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: TeamWiseFlow/xiaobei
Path: crews/main/skills/published-track/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.