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.

79

Quality

100%

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

100%

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

The content is a well-structured, actionable guide: a sequenced 7-step workflow with explicit validation, executable templates and code blocks, and clean one-level navigation through external references, with minimal wasted tokens.

DimensionReasoningScore

Conciseness

The body is lean: it leads with a useful agents-vs-skills distinction and otherwise relies on templates, field tables, and code blocks where every token earns its place, avoiding explanations of concepts Claude already knows; it is not level 2 because there is no notable padding to trim.

3 / 3

Actionability

It provides concrete file locations (`.github/agents/<name>.md`), a full frontmatter field table, and copy-paste-ready YAML/JSON/TypeScript blocks for participant declaration and request handlers, meeting the level-3 fully-executable bar rather than mere description.

3 / 3

Workflow Clarity

The seven steps are clearly sequenced and capped by an explicit "Validate" step with a checklist of verification items, providing explicit validation checkpoints for risky authoring operations rather than an implicit or missing sequence.

3 / 3

Progressive Disclosure

With no bundle files, the single SKILL.md is well-organized into clearly signaled sections and points outward via a one-level-deep References list of external docs and sibling skills, giving easy navigation without nested reference chains.

3 / 3

Total

12

/

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.

The description is concise, third-person, and strong across all dimensions: it names concrete actions, provides natural trigger phrases, answers both what and when explicitly, and occupies a distinct niche unlikely to conflict with other skills.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — "Create", "scaffold", or "configure" — applied to a concrete object (custom GitHub Copilot agents), matching the level-3 anchor of several specific concrete actions; it is not level 2 because the verbs are enumerated rather than a single domain-and-action.

3 / 3

Completeness

It explicitly answers both what ("Create custom GitHub Copilot agents") and when via an explicit "Use when asked to create, scaffold, or configure..." clause, satisfying the level-3 anchor for clear what-and-when with explicit triggers.

3 / 3

Trigger Term Quality

"create, scaffold, or configure a custom agent, declarative agent, or @-invokable chat participant" are natural phrases a user would say when needing this skill, giving good coverage of common variations rather than only some relevant keywords.

3 / 3

Distinctiveness Conflict Risk

The niche (GitHub Copilot custom agents/chat participants) is specific with distinct triggers unlikely to fire for unrelated skills, and the body's "When Not to Use" section reinforces separation from sibling skills.

3 / 3

Total

12

/

12

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.