auth

Activate when code touches token management, credential resolution, git auth flows, GITHUB_APM_PAT, ADO_APM_PAT, AuthResolver, HostInfo, AuthContext, or any remote host authentication -- even if 'auth' isn't mentioned explicitly.

Quality

72%

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/auth/SKILL.md

Quality

Content

87%Weight 40%Scale 1-3

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

A lean, highly actionable internal auth reference with well-organized sections and clearly signaled one-level-deep references; its only gap is the absence of explicit validation checkpoints in the auth-resolution workflow.

Dimension	Reasoning	Score
Conciseness	The body is a tight operational reference of auth resolution order, env vars, error strings, and remediations that Claude would not already know; it assumes competence and avoids explaining generic concepts, so every line earns its place.	3 / 3
Actionability	It gives concrete file paths, env var names, executable commands (e.g. 'az account get-access-token --resource 499b84ac-1321-427f-aa17-267ca6975798', 'az login --tenant <tenant>'), and exact error-message-to-remediation mappings that are copy-paste ready.	3 / 3
Workflow Clarity	The ADO auth resolution order and stale-PAT fallback are clearly sequenced, and diagnostic cases map errors to fixes, but there are no explicit validation checkpoints or validate-fix-retry gates, keeping it below the score-3 anchor.	2 / 3
Progressive Disclosure	The body is a well-sectioned overview (When to activate, Key rule, Canonical reference, ADO auth) with clearly signaled one-level-deep references to the persona file and the canonical authentication.md flowchart, and no nested reference chains.	3 / 3
	Total	11 / 12 Passed

Description

57%Weight 40%Scale 1-3

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 trigger-heavy description that is highly specific and distinctive for its codebase, but leans on internal jargon and only implies the skill's actual actions, leaving the "what" underspecified.

Suggestions

Add a short lead clause stating what the skill does (e.g. 'Resolves per-host auth tokens and routes all credential access through AuthResolver') before the 'Activate when' trigger list.

Soften internal-symbol jargon (AuthResolver, HostInfo, AuthContext) or pair each with a natural-language gloss so the description reads as something a user would naturally say.

Keep the explicit 'Activate when' trigger guidance but ensure the description opens with the action verbs so both 'what' and 'when' are explicit.

Dimension	Reasoning	Score
Specificity	Names a concrete domain ("token management, credential resolution, git auth flows") and specific identifiers (GITHUB_APM_PAT, ADO_APM_PAT, AuthResolver), but describes when to trigger rather than listing concrete actions the skill performs, so it does not reach the multiple-actions anchor.	2 / 3
Completeness	The explicit "Activate when ..." clause strongly answers "when", but "what" the skill does is only implied from the domain terms, so it does not clearly answer both what and when.	2 / 3
Trigger Term Quality	Includes some natural terms ("authentication", "credentials", "git auth") but is dominated by internal code symbols (AuthResolver, HostInfo, AuthContext, ADO_APM_PAT) that a user would not naturally say, missing common variations.	2 / 3
Distinctiveness Conflict Risk	The narrow, codebase-specific triggers (GITHUB_APM_PAT, ADO_APM_PAT, AuthResolver, HostInfo, AuthContext) carve out a clear niche that is unlikely to fire for the wrong skill.	3 / 3
	Total	9 / 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
relative_links	Relative link issues: 2 suspicious	Warning

	Total	15 / 16 Passed

Repository: microsoft/apm
Path: .agents/skills/auth/SKILL.md
Commit: 634f7b6

Reviewed: 8 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.