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

72%

Does it follow best practices?

Impact

100%

1.25x

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-skills/SKILL.md

Quality

Content

77%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.

The body delivers a well-sequenced, validated workflow with strong progressive disclosure and executable commands, but is held back by redundant emphatic warnings and duplicated compliance checklists that inflate token cost.

Suggestions

Collapse the repeated "MANDATORY / PROHIBITED" mandates into a single concise compliance block; remove the duplicate restatements in Step 3 stop conditions and the post-validation checklist.

Trim decorative emoji/bold warning headers (e.g. "🚨 CRITICAL WORKFLOW REQUIREMENTS 🚨") to plain emphasized headers that convey the same constraint in fewer tokens.

Move the Step 2 resource-type taxonomy and the Step 6 iteration-pattern catalog into a reference file, keeping SKILL.md as a lean overview with a pointer.

Dimension	Reasoning	Score
Conciseness	The body is directive and substantive but noticeably padded: "Manual file creation is PROHIBITED" and the "You MUST run scaffold" mandates are restated across the critical-requirements block, Step 3, stop conditions, and the post-validation checklist, and emoji-heavy warnings add length without information.	3 / 5
Actionability	It provides concrete, executable commands ("python3 scripts/scaffold_skill.py --name <skill-name>", "python3 scripts/validate_skill.py --path <path-to-skill-root>", "ls -la .github/skills/<skill-name>/") plus explicit reference paths, with only minor gaps in the content-generation step.	4 / 5
Workflow Clarity	A clearly sequenced 6-step process with explicit validation checkpoints (Step 3 verification, Step 5 validation), feedback loops ("If validation fails: fix and re-validate"), stop conditions, and a post-validation checklist covering error recovery.	5 / 5
Progressive Disclosure	The body acts as an overview pointing to real one-level-deep references (BEST_PRACTICES.md, SPECIFICATION.md, TEMPLATES.md, workflows.md, output-patterns.md, all verified present), and the "Knowledge Retrieval" section maps question types to files for easy navigation.	5 / 5
	Total	17 / 20 Passed

Description

67%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.

The description cleanly states what the skill does and when to use it with third-person voice and a distinct niche, but its trigger vocabulary is thin on synonyms and the when-clause is somewhat abstract.

Suggestions

Add concrete user-facing trigger phrases and synonyms, e.g. "Use when the user asks to build, scaffold, create, update, or validate an agent skill."

Broaden capability wording with more specific verbs (e.g. "scaffolds directories, generates templates, validates spec compliance") to lift specificity from 4 to 5.

Include file/extension or naming hints (e.g. "SKILL.md", ".github/skills/") to sharpen distinctiveness and trigger matching.

Dimension	Reasoning	Score
Specificity	Names the domain ("Agent Skills") and several concrete actions ("Architects, generates, and validates" plus "Enforces specification and best practices"), though the verbs are slightly abstract and a few capability gaps remain.	4 / 5
Completeness	It answers both what ("Architects, generates, and validates Agent Skills") and when ("Used any time an agent skill must be created or updated"), but the when could be more explicit with concrete user phrasings rather than a single abstract clause.	4 / 5
Trigger Term Quality	"agent skill" and "created or updated" are relevant, natural-ish terms, but common synonyms and variations (build, scaffold, modify, skill template) are missing, so coverage is incomplete.	3 / 5
Distinctiveness Conflict Risk	"Agent Skills" creation/validation is a clear niche with distinct triggers and only minor overlap risk against generic code-generation or scaffolding skills.	4 / 5
	Total	15 / 20 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: 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.