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

77%

Does it follow best practices?

Impact

90%

1.15x

Average score across 3 eval scenarios

Securityby

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./.github/skills/generate-agent/SKILL.md

Quality

Content

67%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 thorough, well-organized generative skill with concrete commands, examples, and a clear seven-step workflow supported by real bundle files. Its main weakness is verbosity from repeating dual-agent examples and restating content across later sections, plus a missing error-recovery loop in the validation step.

Suggestions

Collapse the repeated Security Auditor / Documentation Writer dual examples in Steps 2–4 into a single worked example and reference the others once, to reduce token cost without losing actionability.

Remove or merge the 'Examples of Common Agents' and 'Anti-Patterns' sections, which largely restate guidance already given in the workflow steps.

Add an explicit validation feedback loop in Step 6 (e.g., 'If validate_skill.py reports errors, fix the frontmatter/XML and re-run until clean') and either bundle the validator script or document its source.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and well-structured, but it repeats dual worked examples (Security Auditor AND Documentation Writer) across Steps 2–4 and restates the same agents again in 'Examples of Common Agents' and 'Anti-Patterns', which could be tightened without losing clarity.	3 / 5
Actionability	Provides mostly executable guidance — concrete `cat references/...` loads, a copy-paste XML thinking_process, a tool decision table, and a final output template — but Step 6's validator (`python3 .github/skills/generate-agent-skills/scripts/validate_skill.py`) depends on a sibling skill's unbundled script, a minor gap.	4 / 5
Workflow Clarity	Seven steps are clearly sequenced with a routing decision tree in Step 1 and a validation checklist in Step 6, but there is no explicit error-recovery feedback loop (validate → if fail, fix → re-validate) for the validation step.	4 / 5
Progressive Disclosure	Good one-level-deep structure: the body signals each bundle file via `cat references/...` / `cat assets/...` at the point of need, all referenced files exist, and a Resources section indexes them with descriptions; minor gap is the long inline worked examples that could be trimmed.	4 / 5
	Total	15 / 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, third-person description that clearly states what the skill does and when to use it, with concrete role-name triggers and explicit boundary guidance against sibling skills. Minor room to tighten the slightly repetitive second sentence and add trigger synonyms.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions/attributes ('Generates Custom Agent files (.github/agents/*.agent.md)', 'persona-based configurations, specialized tool sets, and role-specific cognitive architectures', 'defined identity, constrained tools'), though some lean conceptual ('cognitive architectures') and the second sentence partly restates the first rather than adding new concrete operations.	4 / 5
Completeness	Explicitly answers both what ('Generates Custom Agent files... with persona-based configurations, specialized tool sets, and role-specific cognitive architectures') and when ('Use when the user requests a specialized role or perspective') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Provides good natural trigger coverage via 'Use when the user requests a specialized role or perspective (Security Auditor, Documentation Writer, Release Engineer, etc.)' with concrete role names users would actually say, but lacks synonyms/variations beyond the listed examples.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (role/persona agents) and explicitly boundaries against siblings ('Not for general capabilities—use generate-agent-skills for those'), minimizing wrong-skill triggering.	5 / 5
	Total	18 / 20 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: e75d6ec

Reviewed: 19 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.