CtrlK
BlogDocsLog inGet started
Tessl Logo

skill-authoring

Guidelines for writing Agent Skills that comply with the agentskills.io specification. WHEN: "create a skill", "new skill", "write a skill", "skill template", "skill structure", "review skill", "skill PR", "skill compliance", "SKILL.md format", "skill frontmatter", "skill best practices".

92

1.35x
Quality

88%

Does it follow best practices?

Impact

100%

1.35x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Discovery

89%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This description has strong trigger term coverage and completeness with an explicit WHEN clause containing numerous relevant keywords. The main weakness is the somewhat vague capability statement - it says 'guidelines for writing' but doesn't specify what concrete actions the skill enables (validation, generation, formatting, etc.). The distinctiveness is excellent due to the specific agentskills.io domain.

Suggestions

Expand the capability statement to list specific actions like 'validates frontmatter fields, generates compliant YAML headers, checks specification requirements' rather than just 'guidelines for writing'.

DimensionReasoningScore

Specificity

Names the domain (Agent Skills, agentskills.io specification) and implies actions like writing/reviewing skills, but doesn't list concrete specific actions like 'validate frontmatter fields', 'generate YAML headers', or 'check compliance rules'.

2 / 3

Completeness

Clearly answers both what ('Guidelines for writing Agent Skills that comply with the agentskills.io specification') and when (explicit 'WHEN:' clause with comprehensive trigger terms). The explicit trigger guidance is present and thorough.

3 / 3

Trigger Term Quality

Excellent coverage of natural trigger terms users would say: 'create a skill', 'new skill', 'write a skill', 'skill template', 'skill structure', 'review skill', 'skill PR', 'skill compliance', 'SKILL.md format', 'skill frontmatter', 'skill best practices' - these are highly relevant and varied.

3 / 3

Distinctiveness Conflict Risk

Very distinct niche focused specifically on 'agentskills.io specification' and 'SKILL.md format' - these are highly specific terms unlikely to conflict with general coding or documentation skills.

3 / 3

Total

11

/

12

Passed

Implementation

87%

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

This is a well-crafted skill that demonstrates excellent conciseness and progressive disclosure. It provides actionable guidance with specific constraints and executable commands. The main weakness is the lack of a clear sequential workflow for skill authoring, which would help guide users through the creation process step-by-step.

Suggestions

Add a numbered workflow section showing the skill authoring process (e.g., 1. Create directory structure, 2. Write frontmatter, 3. Write SKILL.md body, 4. Add references if needed, 5. Validate) with explicit checkpoints between steps.

DimensionReasoningScore

Conciseness

The content is lean and efficient, avoiding explanations of concepts Claude already knows. Every section provides specific, actionable information without padding or unnecessary context.

3 / 3

Actionability

Provides concrete constraints with specific values (token limits, character counts), executable validation commands, and clear structural requirements. The bash commands are copy-paste ready.

3 / 3

Workflow Clarity

The validation section provides clear commands, but the overall skill authoring workflow lacks explicit sequencing. The integrity checks are listed but not presented as a sequential workflow with validation checkpoints between steps.

2 / 3

Progressive Disclosure

Excellent structure with a concise overview and well-signaled one-level-deep references. The Reference Documentation section clearly links to detailed materials with descriptive labels, and content is appropriately split across files.

3 / 3

Total

11

/

12

Passed

Validation

100%

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

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
microsoft/github-copilot-for-azure
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.