add-permission

Add a new permission end-to-end — server constant + endpoint gate, and (admin app) mirror it into the permissions catalog + route guard. Use when a new endpoint needs authorization. See modules/identity.md + frontend/admin.md.

Quality

91%

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

Quality

Content

90%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 tight, highly actionable multi-step skill with concrete code and file paths, a useful safety warning, and a closing checklist. The only weakness is that the build/test verification is stated as a checklist item rather than an explicit validate→fix→retry loop.

Suggestions

Make the build/test verification an explicit feedback loop: e.g. "Run build; if it fails, fix and rebuild. Run admin test:e2e; if it fails, fix and rerun until green."

Add a one-line validation checkpoint after Step 2 confirming no duplicate IRequiredPermissionMetadata exists before proceeding to the admin mirror steps.

Consider flagging the admin-only steps (3–5) as skippable in the Checklist when the change is server-only, so the workflow is clearly conditional rather than linear.

Dimension	Reasoning	Score
Conciseness	Lean throughout — it assumes Claude knows C#/.NET/TypeScript and never pads with explanations of what permissions, JWTs, or RouteGuard are; every line (including the dense Dashboard section) earns its place.	5 / 5
Actionability	Provides copy-paste-ready code templates (C# constants, .RequirePermission call, frozen TS permission tree, RouteGuard JSX, test seed) with concrete file paths for every step, covering the common cases comprehensively.	5 / 5
Workflow Clarity	Clear numbered Steps 1–5 plus a validation-bearing Checklist and a critical ⚠️ warning about duplicate IRequiredPermissionMetadata, but the build/test feedback loop (fail → fix → rerun) is implicit rather than an explicit validate-then-retry sequence.	4 / 5
Progressive Disclosure	Cleanly sectioned (Steps, Dashboard, Checklist) with one-level-deep, clearly signaled references to repo docs (modules/identity.md, frontend/admin.md); no bundle files are needed, though the body is slightly above the trivial-skill threshold.	4 / 5
	Total	18 / 20 Passed

Description

92%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 strong, specific description that conveys the full server-and-admin permission workflow and an explicit use-when trigger. The only minor gap is synonym coverage (auth/RBAC/access control) in the trigger terms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete sub-actions spanning the full lifecycle — "server constant + endpoint gate", "mirror it into the permissions catalog + route guard" — giving comprehensive coverage rather than a single generic action.	5 / 5
Completeness	Clearly answers both what (the end-to-end four-part permission process) and when ("Use when a new endpoint needs authorization") with a concrete trigger phrase.	5 / 5
Trigger Term Quality	"permission" and "authorization" ("Use when a new endpoint needs authorization") are the natural phrases a user would say, but common synonyms like auth, RBAC, or access control are absent.	4 / 5
Distinctiveness Conflict Risk	The cross-stack "add a permission end-to-end" niche is highly specific with distinct triggers and minimal overlap risk against other skills.	5 / 5
	Total	19 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: fullstackhero/dotnet-starter-kit
Path: .agents/skills/add-permission/SKILL.md
Commit: 3f2959e

Reviewed: 16 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.