init

Generate or update chat customization files for AI coding agents

Quality

53%

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/init/SKILL.md

Quality

Content

57%

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

The content is a well-structured, lean instruction skill with good progressive disclosure and a clear workflow, but several exploration steps are abstract rather than actionable and the workflow lacks explicit validation checkpoints for modifying existing files.

Suggestions

Tighten soft/redundant framing lines (e.g. the repeated 'immediately productive' phrasing) so every line guides behavior.

Make the 'Explore the codebase' step more actionable by specifying concrete signals or commands to look for rather than 'Find essential knowledge'.

Add an explicit verification checkpoint before finalizing (e.g. confirm existing instruction files were preserved and deduped) to lift workflow clarity.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with short prose and a numbered workflow, but contains some soft/redundant lines (e.g. repeated framing about agents being 'immediately productive') that could be tightened.	2 / 3
Actionability	It includes concrete elements (a literal search glob, a file-preference rule, named targets) but several steps remain abstract directives ('Explore the codebase', 'Find essential knowledge') rather than fully actionable instructions.	2 / 3
Workflow Clarity	There is a clear 4-step Discover/Explore/Generate/Iterate sequence with a feedback step, but no explicit verify/validate checkpoint for modifying existing user instruction files, only a soft 'preserve valuable content' guard.	2 / 3
Progressive Disclosure	The body is well-organized into a concise overview and a numbered workflow, and cleanly delegates detail to the one-level-deep 'agent-customization' and 'chronicle' skills without any nested reference chain.	3 / 3
	Total	9 / 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 clear about its domain and two core actions but is generic and lacks any explicit trigger guidance for when to use it. It does not list a comprehensive set of concrete actions or natural user phrasings.

Suggestions

Add an explicit 'Use when...' trigger clause, e.g. 'Use when setting up or refreshing AI coding agent instructions such as AGENTS.md or .github/copilot-instructions.md'.

List more concrete actions and natural terms (e.g. 'create or update AGENTS.md, copilot-instructions.md, skills, and custom agents') to lift specificity and trigger coverage.

Reference the specific target file names users would naturally say (AGENTS.md, copilot instructions) to improve distinctiveness and trigger term quality.

Dimension	Reasoning	Score
Specificity	The description names a domain ('chat customization files for AI coding agents') and two actions ('Generate or update'), but does not enumerate multiple concrete actions like the score-3 anchor; it stays somewhat abstract.	2 / 3
Completeness	It clearly states what the command does, but there is no 'Use when...' clause or equivalent explicit trigger guidance for when to invoke it, which caps completeness at 2.	2 / 3
Trigger Term Quality	Terms like 'chat customization files' and 'AI coding agents' are relevant but lean technical; common natural phrasings a user would say ('AGENTS.md', 'copilot instructions', 'agent setup') are missing.	2 / 3
Distinctiveness Conflict Risk	The 'chat customization files for AI coding agents' niche is reasonably specific, but the broad verbs and lack of distinct trigger language mean it could still overlap with adjacent tooling skills.	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/init/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.