create-prompt

Create a reusable prompt file (.prompt.md) for a common task.

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./extensions/copilot/assets/prompts/skills/create-prompt/SKILL.md

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is concise and well-sequenced for a simple instructional skill, scoring well on conciseness and workflow clarity. Its main weakness is actionability and progressive disclosure: the actual prompt template is deferred to a prompts.md file that is not present in the bundle, leaving a dangling reference and incomplete deliverable guidance.

Suggestions

Add the referenced prompts.md to a references/ bundle (or inline the template) so 'Load and follow prompts.md' resolves to a real file.

Specify where the .prompt.md should be saved (e.g., workspace .claude/prompts/ vs. personal) and what a minimal .prompt.md looks like, so the deliverable is actionable without the missing file.

Make the references to prompts.md and the agent-customization skill clearer links (e.g., a relative path) and confirm they exist in the bundle.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — short bullets and a three-phase outline with no padding or explanation of concepts Claude already knows. Every section earns its place; not level 2 because there is no unnecessary explanation to trim.	3 / 3
Actionability	The process bullets ('Extract: the core task...', 'Draft the prompt and save it') give concrete guidance, but the actual deliverable format/template is deferred to 'prompts.md', which is not present in the bundle, and where/how to save the .prompt.md is unspecified. Above level 1 because steps are concrete; below level 3 because key details are missing and the referenced template is absent.	2 / 3
Workflow Clarity	A clear Extract → Clarify → Iterate sequence with a numbered iteration list; this is a non-destructive instructional skill so validation checkpoints are not required, and per the simple-skills note the clear sequence qualifies. Not level 2 because the ordering and steps are explicit, not implicit.	3 / 3
Progressive Disclosure	Sections are well organized, but the body instructs the reader to 'Load and follow prompts.md for template and principles' and references the 'agent-customization' skill, yet no bundle files exist (references/ is absent), so prompts.md is a dangling reference. Above level 1 because structure is present, but below level 3 because a key referenced file is missing and navigation is therefore broken.	2 / 3
	Total	10 / 12 Passed

Description

50%

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 concise and states a concrete capability, but it omits any 'when to use' trigger guidance and lists only a single action, leaving it at the mid-level across all dimensions. Adding a 'Use when...' clause with natural trigger terms would lift completeness and trigger quality.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user wants to save a reusable prompt for a task they repeat, or asks to create a .prompt.md.'

List the concrete actions involved (e.g., extract a repeatable pattern from the conversation, draft, and save a .prompt.md) to broaden specificity.

Include natural trigger variations users would actually say, such as 'reusable prompt', 'prompt template', or 'save a prompt'.

Dimension	Reasoning	Score
Specificity	Quotes 'Create a reusable prompt file (.prompt.md)' — it names the domain (.prompt.md) and a single concrete action, but is not comprehensive (only 'Create' is listed, no associated actions like editing or invoking). It is above level 1 because it is concrete, but below level 3 because it does not list multiple specific actions.	2 / 3
Completeness	It states what the skill does ('Create a reusable prompt file (.prompt.md) for a common task') but provides no 'Use when...' clause or equivalent explicit trigger guidance, which per the guidelines caps completeness at 2. Not level 1 because 'what' is clearly stated; not level 3 because 'when' is entirely missing.	2 / 3
Trigger Term Quality	Terms 'prompt file' and 'prompt' are natural things a user might say, but coverage is limited with no common variations (e.g., 'reusable prompt', 'prompt template', 'save a prompt'). It exceeds level 1 because the keywords are natural, but falls short of level 3's broad coverage.	2 / 3
Distinctiveness Conflict Risk	The .prompt.md niche is fairly specific, but the skill explicitly defers to the related 'agent-customization' skill, creating overlap risk, and 'for a common task' is generic. More specific than level 1 but not the clear, conflict-free niche of level 3.	2 / 3
	Total	8 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: posit-dev/positron
Path: extensions/copilot/assets/prompts/skills/create-prompt/SKILL.md
Commit: b87c504

Reviewed: 2 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.