Tessl • The management layer for AI agent skills

A lean, highly actionable orchestration skill body: concrete commands, paths, thresholds, clear workflow routing, and explicit platform-behavior rules, with detail correctly delegated to per-tool docs and workflow definitions. The main improvements are structural — breaking up the dense delegation-boundary paragraph and making the resource-name vs. workspace-path navigation more intuitive.

Dimension	Reasoning	Score
Conciseness	The body is dense and table-driven with no explanation of concepts Claude already knows, and its platform facts are non-obvious operational knowledge; however the ~350-character 视频全案分工硬边界 run-on paragraph with nested parentheticals could be split and tightened, matching the 4 anchor (efficient, minor trims possible).	4 / 5
Actionability	Guidance is copy-paste-ready for an instruction-only skill: exact commands ("wx-channel-engagement fetch-all", "published-track record --platform wx_channel --title", "login/login-confirm/fill"), concrete paths ("wx_channel/dna/", "dna-meta.json", "evals/"), and specific numbers (≤300 字, ≥60% 真人出镜, 周 3-5 条, 前 2 秒抛冲突) covering the common cases.	5 / 5
Workflow Clarity	The scenario→workflow table provides clear routing with trigger conditions, a QC gate exists ("video-review 成片质检闸门"), and error handling on the shared session is specified ("读到「session 正忙」就等当前操作完成再重试"); but the detailed multi-step sequences live in the referenced workflows and some checkpoints remain implicit, matching the 4 anchor.	4 / 5
Progressive Disclosure	The ~66-line body is well-sectioned and appropriately pushes detail outward (per-tool docs; DNA dimension framework in "references/video-dna-framework.md", one level deep), but navigation between logical resource names and workspace paths is confusing enough to require a dedicated 资源命名约定 section, and the single referenced file lives in another tool's package with no local bundle files to verify.	4 / 5
	Total	17 / 20 Passed

Description

75%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.

A highly specific, well-bounded description that clearly enumerates the skill's operational scope and its division of labor with content-producer. Its main weakness is the complete absence of any 'when to use' trigger guidance, which both caps completeness and leaves trigger-term coverage one notch short.

Suggestions

Append an explicit trigger clause, e.g. "Use when the user mentions 视频号 / 微信视频号 account operations, 起号, 选题, 口播文案, publishing, or 数据复盘."

Add common user-side synonyms to the trigger clause (涨粉, 流量, 账号诊断, 对标) so the description matches the natural phrasings users actually say.

State when NOT to use this skill directly (full production → content-producer) in trigger form as well, so the existing boundary sentence also works as routing guidance.

Dimension	Reasoning	Score
Specificity	"承接定位起号、内容 DNA、选题与短标题/视频描述包装、已有素材轻加工、视频全案 Brief 与口播文案、发布与数据复盘" lists many individually concrete actions spanning the full account-operations loop, plus a delegation boundary ("全片制作委托content-producer") — comprehensive coverage per the 5 anchor.	5 / 5
Completeness	The "what" is clear and detailed, but there is no "Use when…" clause or equivalent explicit trigger guidance anywhere in the description; per the judging guidelines a missing 'when' caps completeness at 3.	3 / 5
Trigger Term Quality	Natural creator-facing terms are present ("视频号", "运营", "起号", "选题", "口播文案", "复盘", "发布"), but common variations users would say (e.g. "涨粉", "流量", "账号诊断") are missing, so it falls just short of the 5 anchor's comprehensive synonym coverage.	4 / 5
Distinctiveness Conflict Risk	The description is pinned to a single platform niche (微信视频号) and explicitly disclaims the one plausible overlap with a sibling skill ("全片制作委托content-producer"), giving a clear niche with distinct triggers and minimal conflict risk.	5 / 5
	Total	17 / 20 Passed

Validation

81%

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 — 13 / 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
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	13 / 16 Passed

Repository: TeamWiseFlow/xiaobei
Path: crews/main/skills/expert-wx-channel/SKILL.md
Revision: 47aea0b

Reviewed: 6 days ago

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.

expert-wx-channel

Table of Contents

Is this your skill?