CtrlK
BlogDocsLog inGet started
Tessl Logo

make-custom-agent

Create custom GitHub Copilot agents. Use when asked to create, scaffold, or configure a custom agent, declarative agent, or @-invokable chat participant for GitHub Copilot.

67

Quality

81%

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

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.

A well-structured, actionable skill body with clear sequencing and a validation checklist, efficiently written without padding. The main gap is the GitHub App step leaning on external docs and the absence of an explicit validate-fix-retry loop to elevate workflow clarity.

Suggestions

Turn Step 6 (GitHub App) into more actionable guidance with a minimal skeleton (webhook registration, SSE response stub) rather than primarily pointing to external docs.

Add an explicit validate-fix-retry feedback loop in the workflow (e.g., after authoring, run frontmatter/YAML validation and re-check until clean) to strengthen workflow clarity.

Consider splitting the large frontmatter-fields and handoff-field tables into a short reference snippet or linking them, to tighten the overview toward progressive disclosure 5.

DimensionReasoningScore

Conciseness

Efficient, assumes Claude's competence with no padding about what Copilot or agents are; dense tables and code earn their place, with only minor trimming opportunities, sitting above the 3 anchor but short of fully lean.

4 / 5

Actionability

Provides mostly executable guidance — concrete TypeScript/JSON/YAML snippets, a template, and field tables — with minor gaps such as the GitHub App step being largely a pointer to external docs rather than copy-paste code.

4 / 5

Workflow Clarity

Seven clearly sequenced steps plus a Step 7 validation checklist with explicit checkpoints; falls short of 5 because the checklist is verification-oriented without a full validate-fix-retry feedback loop for the creation process.

4 / 5

Progressive Disclosure

Well-organized overview sections with appropriately inlined essential content and a clean References list of one-level-deep external links; no bundle files exist, so minor organization gaps keep it just below the ideal 5.

4 / 5

Total

16

/

20

Passed

Description

87%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, well-scoped description that clearly states what the skill does and when to use it with concrete, natural trigger terms. Only minor improvements in keyword synonym coverage would push specificity and trigger quality to the top anchor.

DimensionReasoningScore

Specificity

Names the domain and lists several concrete actions ("create, scaffold, or configure") across multiple agent types ("custom agent, declarative agent, or @-invokable chat participant"), with only minor coverage gaps relative to the comprehensive 5 anchor.

4 / 5

Completeness

Explicitly answers both what ("Create custom GitHub Copilot agents") and when ("Use when asked to create, scaffold, or configure...") with concrete trigger phrases, matching the 5 anchor exactly.

5 / 5

Trigger Term Quality

Includes natural user phrases like "create, scaffold, or configure" and "custom agent, declarative agent, @-invokable chat participant"; good keyword coverage though a few natural synonyms are missing, sitting between the 3 and 5 anchors.

4 / 5

Distinctiveness Conflict Risk

Scoped narrowly to GitHub Copilot custom agents with distinct triggers and explicitly differentiated from Agent Skills, giving a clear niche with minimal conflict risk.

5 / 5

Total

18

/

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 2 suspicious

Warning

Total

15

/

16

Passed

Repository
dotnet/efcore
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.