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

—

Does it follow best practices?

Impact

97%

2.10x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

85%

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 skill body with clear sequencing, validation checkpoints, and properly signaled one-level-deep references that all resolve to real files. The main weakness is conciseness: repeated per-task example blocks and a derivable template catalog add padding.

Suggestions

Collapse the repeated per-task example tables in Steps 2, 3, and 5 into a single consolidated example or move them into a reference file, keeping each step focused on its method.

Trim or remove the 'Common Prompt Templates' catalog (12 entries) since Claude can generate these on demand from the workflow; reference it only if users frequently ask for inspiration.

Move the full 'Good structure'/'Bad structure' markdown examples in Step 4 into context_optimization_patterns.md and summarize the principle inline.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and actionable, but repeats per-task example tables across Steps 2, 3, and 5 ('Explain Code'/'Fix Bug'/'Add Tests' each re-listed) and pads a 12-entry 'Common Prompt Templates' catalog that Claude could derive — fitting the 'mostly efficient but could be tightened' anchor rather than the lean score-3 anchor.	2 / 3
Actionability	Provides copy-paste-ready, concrete guidance: `cat references/...md` load commands, a concrete prompt structure template, file-naming conventions, and a validation block (`head -10`, `grep -o`) with a final checklist, matching the fully-executable score-3 anchor.	3 / 3
Workflow Clarity	Seven clearly sequenced steps culminate in Step 7's explicit validation (verify YAML, grep for unclosed variables, test with sample data) plus a final checklist, satisfying the clear-sequence-with-validation score-3 anchor; the task is generative so the destructive/batch cap does not apply.	3 / 3
Progressive Disclosure	The body is an overview signaling four real, one-level-deep bundle files via `cat` commands and a Resources section — all referenced paths (task_analysis_checklist.md, variable_identification_guide.md, context_optimization_patterns.md, prompt_template.md) resolve to existing files — matching the well-signaled-references score-3 anchor.	3 / 3
	Total	11 / 12 Passed

Description

100%

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 covers both what and when while distinguishing itself from related skills. No first/second-person voice penalty applies.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — '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' — matching the multi-action anchor rather than the partial score-2 anchor.	3 / 3
Completeness	Explicitly answers both 'what' ('Generates reusable Prompt Template files... with variable substitution') and 'when' via an explicit 'Use when...' clause, satisfying the score-3 anchor rather than the implied-when score-2 anchor.	3 / 3
Trigger Term Quality	Natural user-facing phrasing — 'Use when the user needs quick, repeatable prompts for common operations (explain code, fix bug, add tests, refactor, document)' — gives good coverage of terms users would actually say, exceeding the partial-coverage score-2 anchor.	3 / 3
Distinctiveness Conflict Risk	The clause 'Not for complex workflows (use skills) or persistent roles (use agents)' carves out a clear niche and explicitly differentiates from sibling skills, matching the distinct-triggers score-3 anchor.	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
Commit: d1b6440

Reviewed: 4 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.