create-agent

Create a custom agent (.agent.md) for a specific job.

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-agent/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 lean and well-sequenced with a built-in feedback loop, but its actionability and navigation suffer because the referenced template file (agents.md) is absent from the bundle. It reads as an overview that points to detail that is not actually shipped with the skill.

Suggestions

Inline a minimal .agent.md template (frontmatter fields + a one-section body example) so the skill is actionable even before agents.md is loaded.

Resolve the dangling reference: either ship agents.md under references/ or specify its exact path/location so navigation is not broken.

Add an explicit validation step in 'Iterate' (e.g., review the saved .agent.md against a template checklist) before declaring the agent finalized.

Dimension	Reasoning	Score
Conciseness	The body is efficient and assumes Claude's competence, giving task steps without explaining concepts Claude already knows (e.g., what an agent is). It is not a 5 because the closing 'Remember to follow the agent-customization guidelines...' partially repeats the opening reference and could be trimmed.	4 / 5
Actionability	The sections list concrete steps (extract role/tool/scope, clarify, draft, ask, summarize) but the core actionable detail — the .agent.md template and format — is deferred to 'agents.md', which is not present in the bundle. This matches 'some concrete guidance but incomplete; missing key details' rather than the mostly-executable bar of a 4.	3 / 5
Workflow Clarity	A clear sequence (Extract -> Clarify -> Iterate) is given with a feedback checkpoint ('Identify the most ambiguous or weak parts and ask about those'). It is not a 5 because there is no explicit validation step confirming the drafted agent meets a template before finalizing.	4 / 5
Progressive Disclosure	Sections are well-organized and the reference to 'agents.md' is clearly signaled, but no bundle directory (references/) exists, so the referenced file is dangling and navigation breaks. This fits 'references present but not clearly signaled / content that should be separate is inline' more than the 'minor organization gaps' of a 4 because the primary reference target is missing.	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 states a clear purpose but omits any explicit trigger ('Use when...') guidance, which caps its completeness. It is distinct enough to avoid most conflicts yet lacks the keyword breadth and action coverage of top-tier descriptions.

Suggestions

Add a 'Use when...' clause stating when Claude should create a custom agent (e.g., 'Use when the user wants to define a reusable, specialized agent or persona').

Expand the action list beyond a single verb (e.g., 'Draft, refine, and save a custom agent (.agent.md)') to lift specificity toward 4-5.

Include natural synonyms such as 'agent template' or 'define an agent' to broaden trigger term coverage.

Dimension	Reasoning	Score
Specificity	The phrase 'Create a custom agent (.agent.md) for a specific job' names the domain (custom agent) plus one concrete action (create), matching the anchor for 1-2 concrete actions without comprehensive coverage. It is above a 2 because 'create' is a concrete action rather than a generic verb, but below a 4 since only a single action is listed.	3 / 5
Completeness	It clearly states what the skill does ('Create a custom agent (.agent.md) for a specific job') but provides no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. It is not a 4 because 'when' is entirely absent rather than weakly implied.	3 / 5
Trigger Term Quality	Terms like 'custom agent' and '.agent.md' are relevant keywords a user might say, but common variations ('make an agent', 'define an agent', 'agent template') are missing. This matches 'some relevant keywords but missing common variations or synonyms' rather than the broader coverage of a 4.	3 / 5
Distinctiveness Conflict Risk	Creating a custom .agent.md is a fairly distinct niche with specific triggers, giving minor overlap risk only with closely related agent-customization skills. It is not a 5 because the generic word 'agent' still allows some overlap with broader agent-related 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-agent/SKILL.md
Commit: 9bb0f27

Reviewed: about 22 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.