ai-court

以明朝内阁制为蓝本的多 Agent 协作系统

Quality

71%

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 ./skills/ai-court-skill/SKILL.md

Quality

Content

92%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is an efficient, actionable, well-sequenced setup guide with a real validation checkpoint; its main weakness is progressive disclosure, where a cited Discord reference and the configs/ directory are missing from the bundle.

Suggestions

Add the missing references/discord-setup.md file (or remove/fix the citation) so every signaled reference resolves.

Fix the Discord platform step, which currently copies configs/ming-neige/* rather than a Discord-specific config.

Confirm the configs/ directory (ming-neige, tang-sansheng, modern-ceo, feishu) ships in the bundle, since the workflow depends on it.

Dimension	Reasoning	Score
Conciseness	The body is lean and command-driven — install, select, configure, verify, start steps with copy-paste blocks and a compact comparison table — and does not explain concepts Claude already knows, so every token earns its place.	3 / 3
Actionability	It provides fully executable, copy-paste-ready commands (clawdhub install, cp -r configs, bash doctor.sh, openclaw start) plus a concrete API-key JSON snippet, matching the 'fully executable; copy-paste ready' anchor.	3 / 3
Workflow Clarity	The numbered flow (安装 → 选择制度 → 选择 IM → 配置 Key → 验证安装 → 启动) includes an explicit validation checkpoint via doctor.sh before launch, satisfying the clear-sequence-with-validation anchor.	3 / 3
Progressive Disclosure	SKILL.md is a concise overview that externalizes detail to references/feishu-setup.md and scripts/doctor.sh (one level deep, well signaled), but references/discord-setup.md is cited yet absent from the bundle and the referenced configs/ directory is not present, weakening actual navigation.	2 / 3
	Total	11 / 12 Passed

Description

50%

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 identifies a specific, distinctive domain but is purely declarative — it names no concrete actions and provides no 'when to use' trigger, leaving all dimensions at the mid level.

Suggestions

Add concrete capability verbs, e.g. "以明朝内阁制为蓝本，编排、调度并运行多 Agent 协作流程".

Append an explicit trigger clause such as "Use when the user wants to set up or run a multi-agent court/cabinet-style collaboration system over Feishu or Discord."

Include natural keyword variations (多 Agent、多智能体、agent 协作、朝廷/内阁编排) to improve trigger coverage.

Dimension	Reasoning	Score
Specificity	The phrase "多 Agent 协作系统" names a concrete domain, but the description states only what the skill is ("以明朝内阁制为蓝本") and lists no concrete actions verbs, so it sits above pure vagueness yet below the multi-action anchor.	2 / 3
Completeness	It conveys what the skill is, but there is no 'Use when...' or equivalent trigger guidance, so per the judging guideline completeness is capped at 2.	2 / 3
Trigger Term Quality	"多 Agent 协作系统" is a recognizable keyword a user might say, but only that single phrase is offered with no common variations or synonyms, matching the 'some relevant keywords but missing variations' anchor.	2 / 3
Distinctiveness Conflict Risk	The Ming-cabinet framing is a fairly distinct niche, yet without explicit triggers it could still overlap with other multi-agent skills, matching the 'somewhat specific but could overlap' anchor.	2 / 3
	Total	8 / 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
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: wanikua/danghuangshang
Path: skills/ai-court-skill/SKILL.md
Commit: acea185

Reviewed: about 13 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.