CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

73

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

100%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.

The body is a strong, token-efficient knowledge skill: concrete identifiers, exact commands and error strings, an ordered resolution flow with fallback, and well-organized sections. It adds only what Claude would not already know about this project's auth machinery.

DimensionReasoningScore

Conciseness

Lean and dense with project-specific operational detail (file paths, env vars, exact az commands, error strings); it assumes Claude's competence and avoids explaining what auth or git is.

3 / 3

Actionability

Fully concrete and executable — exact paths like src/apm_cli/core/auth.py, exact commands like 'az account get-access-token --resource 499b84ac-...', and exact diagnostic message strings a developer can match against.

3 / 3

Workflow Clarity

The ADO resolution is an explicit ordered sequence (1 env var, 2 az bearer, 3 error) with a described stale-PAT fallback as error recovery; no destructive/batch step requires a separate validation checkpoint.

3 / 3

Progressive Disclosure

A single ~50-line file organized into clearly labeled sections (When to activate, Key rule, Canonical reference, Bearer-token auth) with a one-level-deep, clearly signaled link to the canonical docs reference.

3 / 3

Total

12

/

12

Passed

Description

82%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 highly specific, well-triggered description that names concrete identifiers and natural terms. Its one gap is the absence of an explicit capability statement — it tells Claude when to activate but not what the skill does.

Suggestions

Add a short leading clause stating the skill's action, e.g. 'Resolves and manages authentication tokens for remote git/API hosts. Activate when...'

Lead with the capability verb ('Resolves', 'Manages') so the 'what' is explicit before the 'when' triggers.

DimensionReasoningScore

Specificity

Lists multiple concrete items — 'token management, credential resolution, git auth flows, GITHUB_APM_PAT, ADO_APM_PAT, AuthResolver, HostInfo, AuthContext' — rather than vague language.

3 / 3

Completeness

The 'when' is explicit and strong ('Activate when code touches...') but the 'what' is only implied — no verb states what the skill actually does, so it does not clearly answer both halves.

2 / 3

Trigger Term Quality

Natural terms a developer would say ('token', 'credential', 'git auth', 'remote host authentication') are covered alongside specific identifiers, and it notes triggering 'even if auth isn't mentioned explicitly.'

3 / 3

Distinctiveness Conflict Risk

Project-specific identifiers (GITHUB_APM_PAT, ADO_APM_PAT, AuthResolver, HostInfo, AuthContext) carve a clear niche unlikely to trigger the wrong skill.

3 / 3

Total

11

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 2 suspicious

Warning

Total

15

/

16

Passed

Repository
microsoft/apm
Reviewed

Table of Contents

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.