create-prompt

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

Quality

58%

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

63%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 is a concise, well-sequenced interactive workflow with a genuine feedback loop, but its actionability depends on a dangling prompts.md reference and it never shows a concrete template or example .prompt.md. Clarifying the reference path and inlining a minimal template would lift the two weakest dimensions.

Suggestions

Resolve or clarify the prompts.md reference — either include it in a references/ directory with a markdown link (e.g., [prompts.md](references/prompts.md)) or explicitly state it belongs to the agent-customization skill's location.

Inline a minimal .prompt.md template or one short example so the skill is executable even if the referenced file is unavailable.

Drop the duplicate closing reminder ("Remember to follow the `agent-customization` guidelines") since the same pointer already appears in the opening line, tightening conciseness.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence with no concept over-explanation, but contains minor redundancy: "Related skill: `agent-customization`" is repeated as "Remember to follow the `agent-customization` guidelines" at the end, and "Guide the user to create a `.prompt.md`." restates the frontmatter description. That leaves it just below the every-token-earns-its-place anchor of 5.	4 / 5
Actionability	The "Extract" bullets (core task, implicit inputs, desired output format) and the iterate loop are concrete instructions, but no .prompt.md template, example, or command is provided inline — the actual template is delegated to "prompts.md", whose location is not resolvable from the bundle. Missing key executable details matches the score-3 anchor rather than the mostly-executable score-4 anchor.	3 / 5
Workflow Clarity	There is a clear three-phase sequence ("Extract from Conversation" → "Clarify if Needed" → "Iterate") with a built-in feedback loop ("Identify the most ambiguous or weak parts and ask about those"). This is a non-destructive interactive skill, so the validation cap does not apply, but the checkpoints are implicit rather than explicit validation steps, keeping it below 5.	4 / 5
Progressive Disclosure	The body is well-sectioned for a sub-50-line skill, but its key reference is not clearly signaled or resolvable: "Load and follow prompts.md" points to a file that does not exist in any references/ directory in the bundle, and it is ambiguous whether it lives in the `agent-customization` skill. That matches the anchor for references present but not clearly signaled.	3 / 5
	Total	14 / 20 Passed

Description

53%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 is concise and third-person with a clear "what" and a concrete file format, but it has no "Use when..." trigger clause and thin keyword coverage. Its distinctiveness is decent thanks to the .prompt.md specificity.

Suggestions

Add an explicit trigger clause, e.g., "Use when the user asks to save a reusable prompt, create a .prompt.md file, or turn a repeated task pattern into a prompt."

Include natural user phrasings and synonyms such as "custom prompt", "slash command", or "save this as a prompt" to broaden trigger-term coverage.

Optionally name 1-2 concrete sub-actions (e.g., extract the task pattern from the conversation, scaffold the .prompt.md template) to raise specificity.

Dimension	Reasoning	Score
Specificity	The description names a concrete artifact ("a reusable prompt file (.prompt.md)") with one clear action ("Create"), matching the anchor for 1-2 concrete actions that are not comprehensive. It does not list several specific actions, so it falls below the score-4 anchor.	3 / 5
Completeness	It has a clear "what" ("Create a reusable prompt file (.prompt.md) for a common task") but entirely lacks a "Use when..." clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	"reusable prompt file (.prompt.md)" and "common task" provide some relevant, natural keywords including a concrete file extension, but common variations users would actually say (e.g., "save a prompt", "make a custom prompt", "turn this into a reusable prompt") are missing. It is more specific than the generic score-2 anchor but lacks synonym coverage for a 4.	3 / 5
Distinctiveness Conflict Risk	Creating .prompt.md files is a mostly distinct niche anchored by a specific file extension, with only minor overlap risk against general prompt-writing or agent-customization guidance. It is not fully clear-cut since "prompt" overlaps broadly with prompt-engineering skills, so it does not reach 5.	4 / 5
	Total	13 / 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
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: b0258bc

Reviewed: 5 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.