social-push

使用 agent-browser 帮用户将内容发到社交媒体上。当用户需要发布内容、推送文章、上传文章、发帖到社交平台时使用此 skill。

Quality

73%

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 ./app/skills/social-push/SKILL.md

Quality

Content

57%

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 well-structured orchestration skill with good progressive disclosure (real, one-level reference files) and useful guardrails. It is held back by moderate verbosity and steps that are described in prose rather than given as fully executable, copy-paste-ready commands.

Suggestions

Tighten the Rules section: drop explanatory asides like '确保用户打开的浏览器支持远程调试' and '因为页面状态变化可能导致 ref 编号变化', keeping just the executable command and the rule.

Make step 1 of the Core Workflow concrete by showing the exact AskUserQuestion call (the option list for platform / content type / source / title / hashtags) instead of describing it in prose.

Add an explicit final verification step in the Core Workflow confirming the draft is staged (e.g., a snapshot check that the draft/save state is reached) before handing off to the user.

Dimension	Reasoning	Score
Conciseness	The body is reasonably lean for an orchestration skill, but some lines pad with explanation Claude doesn't need (e.g., '确保用户打开的浏览器支持远程调试', '因为页面状态变化可能导致 ref 编号变化') that could be trimmed.	2 / 3
Actionability	It provides concrete, executable commands (open -na, agent-browser --auto-connect, agent-browser snapshot -i) and explicit guardrails, but several steps are prose direction rather than copy-paste-ready commands (e.g., reading references, consulting 爆款指导) and step 1 relies on the AskUserQuestion tool without showing the exact call.	2 / 3
Workflow Clarity	The Core Workflow is a clear numbered sequence with a strong validation checkpoint (snapshot -i after each step) and a self-evolution fix/verify loop, but the main workflow lacks an explicit verify-after-publish-draft checkpoint, and step ordering of 'consult --help' mid-flow is loosely specified.	2 / 3
Progressive Disclosure	SKILL.md is a concise overview that points one level deep to per-platform workflow and 爆款指导 reference files, all of which exist in ./references/, with clear per-platform navigation in the References section and no nested references.	3 / 3
	Total	9 / 12 Passed

Description

90%

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 concise, uses third person, and clearly states both what the skill does and when to use it with natural trigger terms. Its main weakness is only moderate specificity of concrete capabilities.

Dimension	Reasoning	Score
Specificity	Names the tool (agent-browser) and the domain (social media posting) plus a few concrete actions (发布内容、推送文章、上传文章、发帖), but does not enumerate a comprehensive set of distinct concrete operations the way a level-3 example does.	2 / 3
Completeness	Explicitly answers 'what' (使用 agent-browser 帮用户将内容发到社交媒体上) and 'when' with an explicit trigger clause (当用户需要发布内容...时使用此 skill).	3 / 3
Trigger Term Quality	Covers natural user phrasings users would actually say — 发布内容、推送文章、上传文章、发帖到社交平台 — giving good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	Scopes to a clear niche — publishing to social platforms via agent-browser with named trigger terms — making it unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	15 / 16 Passed

Repository: ZHangZHengEric/Sage
Path: app/skills/social-push/SKILL.md
Commit: ce79d60

Reviewed: about 19 hours 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.