azure-devops

Manage Azure DevOps projects, work items, repos, PRs, pipelines, wikis, test plans, security alerts, variable groups, environments/approvals, branch policies, and attachments. Use when user asks to: manage sprints, create/update work items, list repos, create PRs, run pipelines, search code, manage wiki pages, check security alerts, manage variable groups, approve deployments, or configure branch policies. Covers 13 domains with 99 tools via REST API.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Risky

Do not use without reviewing

Quality

Content

65%

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

The body excels at actionability with dense, executable command examples across all domains, but presents a monolithic inline command catalog rather than progressively disclosing detail into reference files. Destructive and batch operations lack the validation checkpoints expected for clear workflows.

Suggestions

Split the per-domain command catalogs into one-level-deep reference files (e.g. references/work-items.md, references/pipelines.md) and keep SKILL.md as a concise overview with signaled links, improving both conciseness and progressive_disclosure.

Add validation/verification checkpoints for destructive and batch operations — e.g. confirm a work item exists before deleting, run list-prs to verify a PR state before complete-pr/abandon-pr, and check build status before cancel-build.

Tighten the First-Time Setup section into an explicit numbered sequence (authenticate -> verify with `auth.py status` -> run a first list command) so the entry workflow is unambiguous.

Dimension	Reasoning	Score
Conciseness	It avoids explaining concepts Claude already knows and is almost entirely runnable commands, but ~440 lines of inlined command reference is repetitive and high-volume for an overview; not every token earns its place versus deferring to per-domain reference files.	2 / 3
Actionability	Hundreds of concrete, copy-paste-ready commands with real flags and values (e.g. '--link-type "System.LinkTypes.Dependency-Forward"', '--variable ENV production'), matching the fully-executable score-3 anchor.	3 / 3
Workflow Clarity	Setup is sequenced and content is grouped by domain, but destructive/batch operations (delete, complete-pr, abandon-pr, cancel-build, remove) lack validation or verification checkpoints, capping clarity at 2 per the guideline.	2 / 3
Progressive Disclosure	14 real script bundle files exist and are referenced by path in commands, but the ~440-line command reference is inlined in SKILL.md rather than split into one-level-deep per-domain reference files, matching the score-2 anchor of inline API reference that could be separate.	2 / 3
	Total	9 / 12 Passed

Description

100%

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 description: third-person voice, concrete capabilities across all 13 domains, and an explicit 'Use when' trigger clause covering natural user phrasings. It is specific, complete, and clearly distinguishable from other skills.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions across 13 domains ('projects, work items, repos, PRs, pipelines, wikis, test plans, security alerts, variable groups, environments/approvals, branch policies, and attachments') plus 'create/update work items, list repos, create PRs, run pipelines'.	3 / 3
Completeness	Explicitly answers both what (manage 13 domains with 99 tools) and when via the 'Use when user asks to:' clause with concrete triggers, matching the score-3 anchor.	3 / 3
Trigger Term Quality	'manage sprints, create/update work items, list repos, create PRs, run pipelines, search code, manage wiki pages, check security alerts, manage variable groups, approve deployments, or configure branch policies' are natural phrases a user would actually say.	3 / 3
Distinctiveness Conflict Risk	Scoped specifically to Azure DevOps with distinct triggers unlikely to overlap with or fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: sanjay3290/ai-skills
Commit: 9731c77

Reviewed: 4 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.