create-skill

Create a reusable skill (SKILL.md) that packages a workflow.

Quality

64%

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-skill/SKILL.md

Quality

Content

75%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 an exemplar of conciseness with a clear three-phase workflow and a built-in iteration checkpoint. Its main weaknesses are the dangling references to skills.md/agent-customization that are not part of this bundle, which both reduces actionability and slightly muddies navigation.

Suggestions

Bundle the template and principles currently delegated to 'skills.md' into a references/ file (or inline the essential template) so the skill is self-contained and the guidance is executable.

Make the external reference explicit and navigable, e.g., 'See [references/template.md](references/template.md)' instead of the unanchored 'follow skills.md'.

Add an explicit completion check before the finalize step (e.g., verify the SKILL.md has a description with what/when triggers) to close the workflow's feedback loop.

Dimension	Reasoning	Score
Conciseness	The body is lean (under 30 lines), has no padding, and explains nothing Claude already knows; it even delegates template details to 'skills.md'. Every line directs behavior, matching the 'lean and efficient; every token earns its place' anchor.	5 / 5
Actionability	The guidance gives concrete questions ('Workspace-scoped or personal?', 'Quick checklist or full multi-step workflow?') and a draft-iterate loop, but the substantive template and principles are delegated to 'skills.md' and the 'agent-customization' guidelines, neither of which exists in this skill's bundle. This leaves key executable detail missing, matching the 'some concrete guidance but incomplete' anchor rather than the mostly-executable anchor at 4.	3 / 5
Workflow Clarity	The three-phase sequence (Extract from Conversation -> Clarify if Needed -> Iterate) is clearly ordered, and 'Identify the most ambiguous or weak parts and ask about those' provides a feedback checkpoint. No destructive or batch operations apply, so the validation cap does not. It is not a 5 because the error-recovery path is implicit and there are no explicit completion checks for the drafted skill.	4 / 5
Progressive Disclosure	The skill is under 50 lines with well-organized sections, so per the simple-skill note a 5 is possible on structure alone. However, it points to 'skills.md' for the template and to the 'agent-customization' skill, and neither is present in the bundle (no references/, scripts/, or assets/ directories exist), leaving a dangling, poorly-located reference — matching 'good structure; minor organization gaps' rather than fully clear one-level-deep navigation.	4 / 5
	Total	16 / 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 names a concrete artifact, giving a clear 'what', but it omits any 'use when' trigger guidance and only lists a single action. It is serviceable for a user-invoked command skill but would benefit from explicit trigger phrases and a fuller action inventory.

Suggestions

Add a 'Use when...' clause (e.g., 'Use when the user wants to turn a repeated workflow into a reusable skill or command') to lift completeness.

List the concrete actions the skill performs (extract steps from the conversation, draft the SKILL.md, iterate on weak parts) to improve specificity.

Include natural user phrasings and variations such as 'make a skill', 'create a command', or 'package this workflow' to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description names the artifact ('Create a reusable skill (SKILL.md)') and one action ('that packages a workflow'), matching the anchor for naming a domain plus 1-2 concrete actions. It is not a 4 because it does not list the several specific actions the skill actually performs (extract a workflow, draft, iterate, suggest prompts).	3 / 5
Completeness	It answers 'what' clearly (creates a reusable SKILL.md packaging a workflow) but contains no 'Use when...' clause or equivalent trigger guidance, which per the judging guidelines caps completeness at 3. It is not a 2 because the 'what' is specific and concrete, and not a 4 because the 'when' is entirely absent rather than merely weakly implied.	3 / 5
Trigger Term Quality	It includes relevant keywords ('skill', 'SKILL.md', 'workflow') a user might say, but misses common natural variations and synonyms such as 'make a skill', 'package a process', or 'command'. This matches the 'some relevant keywords but missing common variations' anchor rather than the good-coverage anchor at 4.	3 / 5
Distinctiveness Conflict Risk	Skill creation is a distinct niche with little overlap risk against typical skills (document/code/data skills). It falls at 'mostly distinct; minor overlap risk' rather than 5 because the wording lacks concrete trigger phrases that would fully disambiguate it from adjacent authoring/customization skills.	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-skill/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.