$ loading_
Write, review, and standardize Agent Skills to match agentskills.io requirements.
This appears to be an open-source, prompt/documentation-style skill authoring guide with no required secrets, no declared remote endpoints, and no stated local execution capability, so overall risk is low. While the README mentions optional scripts and npm validation commands, the available evidence suggests repository documentation rather than an inherent high-risk behavior, with no concrete red flags observed.
The material explicitly states that no keys or environment variables are required, and the README does not request API tokens, account credentials, or other sensitive secrets. No credential collection, storage, or abuse indicators are shown.
System checks and metadata indicate no remote endpoints, and the content is primarily guidance on skill authoring. The README only references documentation links such as the agentskills.io specification and does not indicate that user data is sent to third-party services.
This item is classified as prompt-only, and its core function is to provide writing/review guidance. Although the README mentions optional npm validation commands in a scripts directory, that appears to be repository workflow documentation rather than evidence that the skill itself can execute local code or spawn processes.
The material does not declare any need to read local files, write system paths, access databases, or call external resources; it focuses on structural guidance for SKILL.md and references. No data access beyond documentation guidance is evident.
The source is a Microsoft GitHub open-source repository with auditable code and some community adoption (222 stars), which are positive factors that reduce risk. The license and maintenance status are not explicit, leaving some transparency gaps, but no high-risk red flags such as closed-source distribution, suspicious delivery, or unclear dependency abuse are evident from the provided material.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "skill-authoring" skill from askskill: 1. Download https://raw.githubusercontent.com/microsoft/GitHub-Copilot-for-Azure/main/.github/skills/skill-authoring/SKILL.md 2. Save it as ~/.claude/skills/skill-authoring/SKILL.md 3. Reload skills and tell me it's ready
Based on the agentskills.io specification, draft a complete SKILL.md for a 'meeting notes organizer' skill, including frontmatter, instructions, examples, and best practices.
A well-structured skill document draft with compliant fields, ready for further editing.
Please review the following SKILL.md for compliance with the agentskills.io specification, identify missing items, formatting issues, and improvement areas, and suggest revisions.
A compliance review checklist with issue explanations and actionable revision suggestions.
I am preparing a skill-related PR. Please organize the change summary according to the skill specification, covering additions, structural updates, and compatibility impact.
A clear PR description that helps reviewers quickly understand the skill changes.
This skill provides guidance for writing Agent Skills that comply with the agentskills.io specification.
name: 1-64 chars, lowercase + hyphens, match directorydescription: 1-1024 chars, ≤60 words, explain WHAT and WHENWHEN: with quoted trigger phrases (preferred over USE FOR:)DO NOT USE FOR: unless the skill has trigger overlap with a broader skill (see frontmatter guidelines)>- folded scalars)SKILL.md (required) - Instructionsreferences/ (optional) - Detailed docsscripts/ (optional) - Executable codeFrontmatter: name (lowercase-hyphens), description (WHAT + WHEN)
Metadata (~100 tokens) loads at startup. SKILL.md (<5000 tokens) loads on activation. References load only when explicitly linked (not on activation). Keep SKILL.md lean.
References are JIT (just-in-time) loaded:
[text](references/file.md) load[Recipes](references/recipes/README.md) not [Recipes](references/recipes/)See REFERENCE-LOADING.md for details.
# Run from the scripts directory
cd scripts
npm run references # Validate all skill links
npm run tokens -- check # Check token limits
When reviewing or authoring skills, verify:
See Validation for detailed procedures.
Analyze and compress Markdown to reduce tokens and improve AI efficiency.
Discover Azure OpenAI capacity, quotas, and best regions for deployment.
Create, validate, and run eval.yaml suites for agent skill evaluation.
Query and analyze logs, telemetry, and time-series data in Azure Data Explorer.
Quickly deploy Azure OpenAI to the best available region automatically.
Assess AKS Automatic readiness and generate fixes for migration blockers.
Access and understand Agent Skills specifications and documentation quickly.
Create, refine, validate, and restructure AgentSkills and SKILL.md files.
Create, refine, and troubleshoot AI skills, specs, invocation, and compatibility.
Create a custom skill with structure, documentation, and optional bundled scripts.
Create reusable SKILL.md skills that package repeatable workflows for future use.
Create, revise, and validate AI skills before deployment.