add-permission

为 FastGPT 新资源接入权限管理。当用户需要为新资源（如 AgentSkill、Plugin 等）添加权限支持时触发。

Quality

61%

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 ./.agents/skills/support/permission/add-permission/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.

A well-organized, token-efficient routing skill whose SKILL.md acts as a hub, but it is undermined by missing bundle files: the actual guidance lives in references that are not present, leaving the body low on executable actionability and with broken navigation.

Suggestions

Ship the referenced bundle files (guides/quick-start.md, guides/full-integration.md, checklist.md, reference/README.md) so progressive-disclosure links resolve.

Add a minimal inline '5-step minimal onboarding' snippet with the first concrete code edit (e.g., the PerResourceTypeEnum addition) so the body is actionable without the external guides.

Inline one validation checkpoint (e.g., 'run permission tests / verify auth.ts rejects unauthorized calls') before pointing to the checklist.

Dimension	Reasoning	Score
Conciseness	The body is extremely lean — a decision tree, a links table, and a code-location table — with zero concept explanation or padding; every token earns its place and Claude's competence is assumed.	5 / 5
Actionability	Concrete pointers appear (file paths like packages/global/support/permission/constant.ts with '添加 PerResourceTypeEnum'), but there is no executable code or commands and the actual steps are deferred to referenced files (quick-start.md, full-integration.md) that are not bundled, leaving only high-level hints.	2 / 5
Workflow Clarity	A clear branching decision tree routes by resource type, but the integration steps themselves are externalized to missing files and there is no inline validation/checkpoint — verification is only implied via the external checklist reference.	3 / 5
Progressive Disclosure	Structure and signaling are clean (one-level-deep markdown links, decision tree, quick-links table), but the referenced destinations (./guides/*.md, ./checklist.md, ./reference/README.md) do not exist in the bundle, so the navigation points to nothing and the disclosure is broken.	3 / 5
	Total	13 / 20 Passed

Description

66%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 concise, well-targeted description that clearly states what the skill does and when to invoke it, with a concrete trigger clause. It is held back from the top band by limited action specificity and modest trigger-term synonym coverage.

Suggestions

List 2-3 concrete actions the skill performs (e.g., '添加 PerResourceTypeEnum、定义 Permission 类、编写鉴权函数') to lift specificity.

Expand the trigger clause with natural user phrasings and synonyms (e.g., '当用户说接入新资源权限、为新 AgentSkill/Plugin 加权限时').

Dimension	Reasoning	Score
Specificity	Names the domain (FastGPT new-resource permission onboarding) and one concrete action ('接入权限管理') plus example resource types (AgentSkill, Plugin), but does not list multiple specific actions, so it stops at 'names domain and 1-2 concrete actions'.	3 / 5
Completeness	Both 'what' (为 FastGPT 新资源接入权限管理) and 'when' (当用户需要...添加权限支持时触发) are explicitly present with a concrete trigger phrase, but the 'what' is terse and the when could enumerate more specific user situations.	4 / 5
Trigger Term Quality	Includes an explicit trigger phrase ('当用户需要为新资源...添加权限支持时触发') and resource keywords, but lacks synonym/variation coverage and natural user phrasings beyond the single trigger clause.	3 / 5
Distinctiveness Conflict Risk	Targets a narrow, well-defined niche (FastGPT permission onboarding for new resource types) with distinct triggers, making conflict with other skills unlikely.	5 / 5
	Total	15 / 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: 7 missing	Warning

	Total	15 / 16 Passed

Repository: labring/FastGPT
Path: .agents/skills/support/permission/add-permission/SKILL.md
Commit: 59d1e07

Reviewed: ~15 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.