create-skill

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

Quality

68%

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

82%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 tight, well-structured instruction skill that appropriately delegates the template to referenced materials and gives a clear staged workflow. Its main gap is the absence of an explicit validation/quality checkpoint confirming the produced skill meets the stated quality criteria before finalizing.

Suggestions

Add an explicit validation step in the Iterate loop — e.g., 'Before finalizing, verify the skill satisfies the quality criteria extracted earlier; if not, revise and re-check.'

Surface one or two concrete elements from `skills.md` inline (such as the minimal SKILL.md frontmatter shape) so Claude can act without first loading the external file.

Make the `skills.md` and `agent-customization` references into explicit markdown links with a one-line note on what each provides, improving navigation signaling.

Dimension	Reasoning	Score
Conciseness	The body is lean (~25 lines), assumes Claude's competence, avoids explaining concepts Claude already knows, and defers the template and principles to `skills.md` and `agent-customization` rather than inlining them, matching the 'lean and efficient; every token earns its place' anchor.	5 / 5
Actionability	It gives concrete staged guidance (extract specific items from conversation, ask specific clarifying questions, iterate via draft→identify weak parts→summarize), but the actual authoring template is deferred to `skills.md` rather than provided inline, leaving minor gaps that fit the 'mostly executable guidance with minor gaps' anchor.	4 / 5
Workflow Clarity	The Extract → Clarify → Iterate sequence is clearly laid out with a clarifying checkpoint ('Identify the most ambiguous or weak parts and ask about those'), but there is no explicit validation/quality-gate step before declaring the skill final, fitting the 'clear sequence with most checkpoints present; minor validation gaps' anchor rather than the checkpoint-rich 5.	4 / 5
Progressive Disclosure	Content is well-organized into clear sections and defers detail to one-level-deep, clearly signaled references (`skills.md`, `agent-customization`), with no bundle files present to misorganize; it falls short of 5 only because it lacks a polished quick-start/advanced reference-file split.	4 / 5
	Total	17 / 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 purpose, but it omits any 'Use when…' trigger guidance and names only a single concrete action, leaving both completeness and specificity at the midpoint. Adding explicit trigger phrases and one or two more concrete capabilities would meaningfully raise the score.

Suggestions

Append a 'Use when…' clause naming concrete triggers (e.g., 'Use when the user wants to turn a repeated workflow or methodology into a reusable skill').

List one or two additional concrete actions beyond 'create/package', such as extracting a process from conversation history or refining an existing skill.

Add natural synonyms users might say ('build a skill', 'make a custom skill', 'skill template') to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (skill authoring) and one concrete action — 'Create a reusable skill (SKILL.md) that packages a workflow' — but offers only a single action with no breadth of capabilities, matching the anchor listing 1-2 concrete actions without comprehensive coverage.	3 / 5
Completeness	The 'what' is clear (create a reusable skill that packages a workflow) but the 'when' is entirely absent with no 'Use when...' clause or equivalent trigger guidance, so completeness is capped at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Includes relevant natural terms ('skill', 'SKILL.md', 'workflow') a user might say, but lacks common synonyms or variations and has no explicit trigger phrasing, matching the 'some relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	It targets a clear niche (SKILL.md authoring) with minimal conflict risk, though the body's reference to the adjacent `agent-customization` skill introduces minor overlap, fitting the 'mostly distinct; minor overlap with closely related skills' anchor rather than the fully-distinct 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-skill/SKILL.md
Commit: 9bb0f27

Reviewed: about 23 hours 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.