generate-prompt

Generates reusable Prompt Template files (.github/prompts/*.prompt.md) with variable substitution for ad-hoc, high-frequency tasks. Use when the user needs quick, repeatable prompts for common operations (explain code, fix bug, add tests, refactor, document). Creates templates with handlebars variables, optimized context structure, and strict output constraints. Not for complex workflows (use skills) or persistent roles (use agents).

2.10x

Quality

92%

Does it follow best practices?

Impact

97%

2.10x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

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.

The content is a well-structured, actionable 7-step workflow with real one-level-deep reference files and clear validation checkpoints. Its main weakness is conciseness: repeated example sets and explanations of basic concepts pad the body and overlap with the reference files.

Suggestions

Consolidate the recurring Explain Code / Fix Bug / Add Tests example sets that repeat across Steps 2, 3, and 5 into a single worked example, delegating the rest to the reference files.

Remove or condense explanations of concepts Claude already knows — the "Common constraint types" catalog in Step 5 and the "Needle in a Haystack" rationale — keeping only the skill-specific application.

Move the inline variable-type and constraint-type catalogs out of Steps 3 and 5 into the existing reference files to reduce redundancy with variable_identification_guide.md and context_optimization_patterns.md.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and actionable but padded: the Explain Code/Fix Bug/Add Tests example sets recur across Steps 2, 3, and 5, and it teaches concepts Claude already knows (the "Common constraint types" catalog in Step 5 and the "Needle in a Haystack" rationale), so it is not the lean score-3 case.	2 / 3
Actionability	It provides executable commands (cat references/..., head -10, grep -o), concrete file-naming (.github/prompts/{{task-name}}.prompt.md), explicit YAML frontmatter fields, and a copy-paste-ready output template and validation checklist, matching the fully-executable score-3 anchor.	3 / 3
Workflow Clarity	A clearly sequenced 7-step workflow with an intent-validation decision tree (STOP/redirect) and a final validation step plus checklist provides explicit checkpoints and error-recovery guidance, satisfying the score-3 anchor.	3 / 3
Progressive Disclosure	All four referenced bundle files exist and are loaded at the appropriate step via signaled cat commands one level deep, with a Resources section for navigation; the SKILL.md acts as an overview pointing to detailed materials, matching the well-signaled score-3 anchor.	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.

The description is specific, uses natural trigger terms, answers both what and when, and explicitly disambiguates itself from skills and agents. It is written in third person with no over-claims, making it a strong, low-conflict skill description.

Dimension	Reasoning	Score
Specificity	"Generates reusable Prompt Template files (.github/prompts/*.prompt.md) with variable substitution" and "Creates templates with handlebars variables, optimized context structure, and strict output constraints" list multiple specific concrete actions, matching the score-3 anchor rather than the partial score-2 anchor.	3 / 3
Completeness	It explicitly states what it does (generates prompt template files with variable substitution) and when to use it ("Use when the user needs quick, repeatable prompts..."), plus negative scoping, satisfying both halves required for the score-3 anchor.	3 / 3
Trigger Term Quality	"Use when the user needs quick, repeatable prompts for common operations (explain code, fix bug, add tests, refactor, document)" surfaces natural terms a user would actually say, giving good coverage rather than the sparse score-2 case.	3 / 3
Distinctiveness Conflict Risk	"Not for complex workflows (use skills) or persistent roles (use agents)" carves out a clear niche with distinct triggers and explicit disambiguation from sibling skills, unlikely to fire for the wrong skill.	3 / 3
	Total	12 / 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: 1 missing	Warning

	Total	15 / 16 Passed

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