CtrlK
BlogDocsLog inGet started
Tessl Logo

azure-pipelines

Use when validating Azure DevOps pipeline changes for the VS Code build. Covers queueing builds, checking build status, viewing logs, and iterating on pipeline YAML changes without waiting for full CI runs.

64

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./.github/skills/azure-pipelines/SKILL.md

The canonical home for this skill is azure-pipelines in microsoft/vscode

SKILL.md
Quality
Evals
Security

Quality

Content

75%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.

Highly actionable content with executable commands, comprehensive options tables, and well-signaled workflows. Its weakness is redundancy: the Common Workflows section and dual polling examples repeat earlier material, and the large parameter table could be split into a reference file.

Suggestions

Trim the 'Common Workflows' section to short scenario pointers instead of repeating the queue/status/cancel commands verbatim from earlier sections.

Drop the manual while-loop polling example in favor of the built-in --watch flag (or keep only one), and remove the note explaining that sleep works on all OSes.

Move the 20-row product-build parameter table into a reference file, keeping only the most-used parameters (e.g. VSCODE_BUILD_TYPE, VSCODE_PUBLISH, VSCODE_BUILD_WEB) inline.

DimensionReasoningScore

Conciseness

The body is mostly efficient commands and tables, but the 'Common Workflows' section repeats queue/status/cancel commands already shown in dedicated sections, the polling section duplicates the manual while-loop with the --watch alternative, and it explains known facts ("The sleep command works on all major operating systems"). This fits 'mostly efficient but includes some unnecessary explanation or could be tightened'.

3 / 5

Actionability

Every instruction is a copy-paste-ready executable command with real flags (e.g. --parameter "VSCODE_BUILD_TYPE=CI Build", --watch 60, --dry-run), plus a full parameter table with types, defaults, and allowed values — fully executable with common cases covered.

5 / 5

Workflow Clarity

Sequences are clear with checkpoints (queue → poll → check final result; cancel-before-queue when iterating; --dry-run verification; troubleshooting recovery). Not a 5 because the manual polling example greps '"status": "completed"' without verifying the script's actual JSON output, and failure investigation is scattered across sections rather than integrated as a feedback loop.

4 / 5

Progressive Disclosure

Well-organized headers and consistent one-level references to the azure-pipeline.ts script. Minor gaps: the 20-row parameter table is inline bulk that could live in a separate reference file, and there are no reference docs to offload detail to, so it does not reach the 'clear overview with well-signaled references' 5-anchor.

4 / 5

Total

16

/

20

Passed

Description

78%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 description with a clear 'Use when' trigger, third-person concrete actions, and a tightly scoped niche. The main improvements are adding missing capability verbs (cancel, download artifacts) and broadening trigger synonyms.

Suggestions

Mention cancelling builds and downloading logs/artifacts in the capability list so coverage is comprehensive.

Add trigger synonyms such as 'Azure Pipelines', 'pipeline YAML', or '.yml' to widen natural keyword matching.

DimensionReasoningScore

Specificity

Names four concrete actions ("queueing builds, checking build status, viewing logs, and iterating on pipeline YAML changes"), but coverage has minor gaps — cancelling builds and artifact download are not mentioned — so it matches 'several specific actions; minor gaps' rather than the comprehensive 5-anchor.

4 / 5

Completeness

Explicitly answers both: what ("Covers queueing builds, checking build status, viewing logs...") and when ("Use when validating Azure DevOps pipeline changes for the VS Code build"). It falls short of the 5-anchor because it offers a single trigger condition rather than multiple concrete trigger phrases.

4 / 5

Trigger Term Quality

Includes natural, likely-user phrases like "Azure DevOps pipeline", "build", "CI", "YAML", and "VS Code", but common variations such as "Azure Pipelines", "build agent", or ".yml" are missing, fitting 'good keyword coverage; a few natural terms missing'.

4 / 5

Distinctiveness Conflict Risk

Highly specific niche — Azure DevOps pipeline validation for the VS Code build — with distinct trigger terms, making conflict with other skills minimal.

5 / 5

Total

17

/

20

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 3 missing

Warning

Total

15

/

16

Passed

Repository
posit-dev/positron
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.