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

73%

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

82%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 a strong, actionable auth-resolution reference: concrete commands, verbatim diagnostic strings, and a clear resolution order with an error-recovery feedback loop. It is concise and well-structured, with only minor tightening and refactoring opportunities.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — no 'what is a token' filler — with every section carrying novel specifics (env vars, exact az commands, error strings); a few diagnostic-case entries could be tightened, keeping it just below a 5.	4 / 5
Actionability	Fully executable guidance: the exact az command with its resource GUID, exact env-var names, the constant's source location, verbatim error/diagnostic strings, and copy-paste remediation commands like 'az login --tenant <tenant>' cover the common cases.	5 / 5
Workflow Clarity	The ADO resolution is a clear numbered sequence with an explicit feedback loop (HTTP 401 -> retry az bearer -> emit diagnostic -> map error to fix); it stops short of a 5 because there is no explicit validation checkpoint or checklist, though this is reference-style rather than destructive/batch work.	4 / 5
Progressive Disclosure	Well-organized sections with clearly signaled one-level-deep references (the auth-expert persona file and the canonical authentication.md mermaid flowchart as 'single source of truth'); a fair amount of ADO detail is inlined that could live in a separate reference, keeping it at 4 rather than 5.	4 / 5
	Total	17 / 20 Passed

Description

65%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 excels at distinctiveness and trigger specificity for its narrow auth-resolution niche, but it is almost entirely an activation clause — the 'what does this skill do' half is left implicit, capping completeness.

Suggestions

Lead with a brief 'what' clause before the activation trigger, e.g. 'Resolves and routes authentication tokens for GitHub/ADO remotes. Activate when ...'

Add a couple of natural synonyms/extensions users might say (e.g. 'PAT', 'personal access token', 'service principal') to lift trigger coverage from 4 to 5.

State the skill's concrete actions (e.g. 'resolves per-org -> global -> credential-fill -> fallback tokens') so the capability is explicit, not inferred.

Dimension	Reasoning	Score
Specificity	Names a concrete domain ('token management, credential resolution, git auth flows') plus specific symbols/env vars (GITHUB_APM_PAT, AuthResolver, HostInfo), but these are activation triggers rather than concrete actions the skill performs, so it sits at the 'names domain and 1-2 concrete actions' level rather than comprehensive.	3 / 5
Completeness	The 'when' is explicit and strong ('Activate when code touches ...'), but the 'what' is only implied — the description never states what the skill does, only when to fire, so it does not clearly answer both halves.	3 / 5
Trigger Term Quality	Strong keyword coverage a developer would naturally reference ('token management', 'credential resolution', 'git auth', GITHUB_APM_PAT, ADO_APM_PAT, AuthResolver), with only minor synonyms missing; not quite the full synonym+extension breadth of a 5.	4 / 5
Distinctiveness Conflict Risk	A clear niche (per-host/per-org auth resolution in a specific codebase) with distinct, named triggers (GITHUB_APM_PAT, ADO_APM_PAT, AuthResolver, AuthContext) and minimal overlap risk with other skills.	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: 2 suspicious	Warning

	Total	15 / 16 Passed

Repository: microsoft/apm
Path: .agents/skills/auth/SKILL.md
Commit: 71a877c

Reviewed: ~2 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.