generate-agent

Generates Custom Agent files (.github/agents/*.agent.md) with persona-based configurations, specialized tool sets, and role-specific cognitive architectures. Use when the user requests a specialized role or perspective (Security Auditor, Documentation Writer, Release Engineer, etc.). Creates agents with defined identity, constrained tools, and thinking processes aligned to their role. Not for general capabilities—use generate-agent-skills for those.

1.15x

Quality

92%

Does it follow best practices?

Impact

90%

1.15x

Average score across 3 eval scenarios

Securityby

Medium

Suggest reviewing before use

Quality

Content

85%Weight 40%Scale 1-3

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, and progressively disclosed workflow with strong validation checkpoints; the main weakness is redundant repetition of example agents across multiple sections that inflates token cost without adding new information.

Suggestions

Consolidate the example agents: show each persona (Security Auditor, Documentation Writer, etc.) once in Step 2 or the Examples section rather than re-listing them in Overview, Steps 3-4, and the trailing 'Examples of Common Agents' block.

Trim the 'Examples of Common Agents' section or fold it into the Role Analysis step to remove overlap with examples already given inline.

Remove the standalone Overview example bullets (lines 19-24) since they are reprised verbatim later in the workflow steps.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and actionable, but the same example agents (Security Auditor, Documentation Writer, Release Engineer) are repeated across Overview, Steps 2-4, and a standalone 'Examples of Common Agents' section, padding the body with redundant material.	2 / 3
Actionability	Provides concrete, executable commands (`cat references/...`, `python3 .../validate_skill.py`, `grep -E ...`), a populated decision tree, a tool-selection table, and copy-paste-ready output templates.	3 / 3
Workflow Clarity	A clear 7-step sequence with an upfront decision tree (STOP + redirect branches) and explicit validation/checklist checkpoints in Step 6, including a validate-fix-retry feedback loop.	3 / 3
Progressive Disclosure	SKILL.md is an overview with well-signaled, one-level-deep references to real bundle files (references/role_analysis_checklist.md, tool_selection_guide.md, cognitive_architecture_patterns.md, assets/agent_template.md), all of which exist and are summarized in a Resources section.	3 / 3
	Total	11 / 12 Passed

Description

100%Weight 40%Scale 1-3

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, third-person description that names concrete capabilities, gives natural trigger terms, and explicitly states both when to use and when not to use the skill.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions: 'Generates Custom Agent files', 'persona-based configurations, specialized tool sets, and role-specific cognitive architectures', 'defined identity, constrained tools, and thinking processes aligned to their role'.	3 / 3
Completeness	Explicitly answers both what ('Generates Custom Agent files ... with persona-based configurations') and when ('Use when the user requests a specialized role or perspective'), with an explicit 'Not for general capabilities' disambiguation.	3 / 3
Trigger Term Quality	'Use when the user requests a specialized role or perspective (Security Auditor, Documentation Writer, Release Engineer, etc.)' gives natural terms users would actually say when requesting a persona-based agent.	3 / 3
Distinctiveness Conflict Risk	Clear niche (Custom Agents = 'Who') explicitly contrasted against generate-agent-skills, generate-path-instructions, and generate-repo-instructions, making misfires unlikely.	3 / 3
	Total	12 / 12 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: canonical/copilot-collections
Path: .github/skills/generate-agent/SKILL.md
Commit: 0fe9990

Reviewed: 7 days ago

Table of Contents

Discovery Implementation Validation

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.