generate-agent-skills

Architects, generates, and validates Agent Skills. Enforces specification and best practices. Used any time an agent skill must be created or updated.

1.25x

Quality

85%

Does it follow best practices?

Impact

100%

1.25x

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 workflow with strong validation checkpoints and clean one-level-deep reference navigation. Its chief weakness is verbosity from repeated emphatic compliance warnings that pad the token budget.

Suggestions

Consolidate the repeated "MUST run scaffolding / manual creation PROHIBITED" warnings and 🚨/STOP banners into a single concise compliance block to cut redundant tokens.

Move the Script-vs-Checklist decision flow and the Common Iteration Patterns into a reference file, leaving SKILL.md as a leaner overview that points to them.

Dimension	Reasoning	Score
Conciseness	The body is operational and actionable, but it is padded with redundant emphatic warnings — the "MUST run scaffolding / manual creation PROHIBITED" message and 🚨/STOP banners recur four or more times — and could be tightened considerably without losing meaning.	2 / 3
Actionability	It gives copy-paste-ready commands (e.g. "python3 scripts/scaffold_skill.py --name <skill-name>", "python3 scripts/validate_skill.py --path <path>") plus concrete regex, expected outputs, and checklists.	3 / 3
Workflow Clarity	A clear 6-step sequence with explicit validation checkpoints, STOP conditions, feedback loops ("If validation fails: read error, fix, re-run"), and post-validation checklists matches the explicit-validation anchor.	3 / 3
Progressive Disclosure	References are well-signaled and one level deep (BEST_PRACTICES.md, SPECIFICATION.md, TEMPLATES.md, workflows.md, output-patterns.md — all verified present), with a "Knowledge Retrieval" map routing question types to specific files and content appropriately split out of SKILL.md.	3 / 3
	Total	11 / 12 Passed

Description

85%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 solid third-person description that answers both what and when with concrete verbs and a distinct niche. Its main weakness is trigger-term coverage, which captures the core create/update intent but lacks natural phrasing variations.

Suggestions

Broaden trigger terms to natural user phrasings, e.g. "Use when the user asks to build, make, scaffold, or update an agent skill."

Drop or sharpen the abstract "Enforces specification and best practices" clause in favor of a more concrete capability to avoid mild over-claim wording.

Dimension	Reasoning	Score
Specificity	"Architects, generates, and validates Agent Skills" lists three distinct concrete verbs on a named object, matching the multiple-specific-actions anchor; the abstract "enforces specification and best practices" clause is secondary.	3 / 3
Completeness	It states WHAT ("Architects, generates, and validates Agent Skills") and an explicit WHEN clause ("Used any time an agent skill must be created or updated"), satisfying both halves.	3 / 3
Trigger Term Quality	"Used any time an agent skill must be created or updated" covers create/update triggers but omits common natural variations a user would say such as "build", "make", "new skill", or "scaffold".	2 / 3
Distinctiveness Conflict Risk	Agent-skill authoring is a distinct meta-niche with a specific trigger, making it unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 7 missing	Warning

	Total	15 / 16 Passed

Repository: canonical/copilot-collections
Path: .github/skills/generate-agent-skills/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.