ai

AI/LLM 能力索引。Agent 开发、LLM 安全、RAG 系统。当用户提到 AI、LLM、Agent、RAG、Prompt 时路由到此。

Quality

59%

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 ./templates/skills/domains/ai/SKILL.md

Quality

Content

57%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 concise and well-organized as an index, but its value collapses because every referenced sub-skill file is missing, leaving no executable guidance or reachable detail. The generic principles block adds little actionable content.

Suggestions

Provide the referenced bundle files (agent-dev.md, llm-security.md, rag-system.md, prompt-and-eval.md) so the routing matrix resolves to real content.

Replace or tighten the generic "AI 工程原则" platitudes with concrete, non-obvious guidance, or move them into the relevant sub-skill files.

Add a brief note on how routing resolves (e.g., 'read the matched sub-skill and follow its steps') so the workflow has a complete, verifiable endpoint.

Dimension	Reasoning	Score
Conciseness	The body is lean with no padding or over-explanation of concepts, but the "AI 工程原则" block states generic maxims Claude already knows (e.g., "人机协作，AI 增强而非替代"), so a few tokens could be trimmed, fitting the efficient-with-minor-over-explanation anchor.	4 / 5
Actionability	The capability matrix gives a concrete need→sub-skill mapping, but there are no commands or code and the linked sub-skill files do not exist, leaving the guidance incomplete.	3 / 5
Workflow Clarity	The single routing action is clear, but the routing targets (agent-dev.md, llm-security.md, rag-system.md, prompt-and-eval.md) are missing, so the workflow dead-ends rather than completing.	3 / 5
Progressive Disclosure	Structure is a clean, well-signaled one-level-deep table of references, but the referenced files are absent from the bundle, so navigation is broken and the disclosure structure is non-functional.	3 / 5
	Total	13 / 20 Passed

Description

61%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 cleanly states what it is and when to route to it, with explicit natural trigger terms. Weaknesses are generic action verbs and broad triggers that risk overlap with other AI-related skills.

Suggestions

Add concrete capabilities per sub-domain (e.g., 'orchestrates multi-agent workflows, hardens prompts against injection, builds vector retrieval') to lift specificity beyond a generic index verb.

Narrow or qualify the broad triggers (AI, LLM, Prompt) to reduce overlap risk with other AI skills.

Dimension	Reasoning	Score
Specificity	The description names its domains ("Agent 开发、LLM 安全、RAG 系统") but the only actions are the generic "索引" and "路由到此" with no concrete capabilities, matching the anchor that names a domain with minimal/generic actions.	2 / 5
Completeness	Both are present: "what" ("AI/LLM 能力索引" plus the three domains) and an explicit "when" ("当用户提到 AI、LLM、Agent、RAG、Prompt 时路由到此"); the "what" is terse enough that it does not fully reach the concrete-and-explicit 5.	4 / 5
Trigger Term Quality	It explicitly lists natural trigger terms users would say ("AI、LLM、Agent、RAG、Prompt") with good coverage, but lacks synonyms or file extensions, so it falls just short of the comprehensive 5.	4 / 5
Distinctiveness Conflict Risk	As a router it has a niche, but the broad triggers (AI, LLM, Prompt) overlap with many other AI skills, fitting the anchor for somewhat-specific-but-still-overlapping.	3 / 5
	Total	13 / 20 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
relative_links	Relative link issues: 4 missing	Warning

	Total	15 / 16 Passed

Repository: fengshao1227/ccg-workflow
Path: templates/skills/domains/ai/SKILL.md
Commit: fba314b

Reviewed: 2 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.