init

Generate or update chat customization files for AI coding agents

Quality

66%

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

78%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 well-structured, actionable command spec: a concrete discovery glob, explicit merge principles, a feedback-oriented iteration step, and a defined output format. Its main gap is the absence of an explicit validation step when merging into existing customization files.

Suggestions

Add an explicit validation checkpoint in the 'Generate or merge' step, e.g. 'After merging, re-read the diff against the original to confirm no valuable content was lost or duplicated.'

Tighten the opening ('The purpose of this command is to create or update chat customization files' duplicates the description) to save tokens.

State concretely what the final table columns should be (file path, created/updated, why useful) so the output format is unambiguous.

Dimension	Reasoning	Score
Conciseness	The body is efficient and behavior-directed — the discovery glob, merge rules, and output requirements each earn their place with no explanation of concepts Claude already knows. A few phrasings could be tightened ('The purpose of this command is to...', explanatory clauses in the intro), keeping it just below the 'lean and efficient; every token earns its place' anchor.	4 / 5
Actionability	Concrete, executable guidance throughout: an exact search glob for discovery, explicit merge rules ('Link, don't embed', 'Minimal by default', 'Preserve valuable content'), a defined output artifact (a table of added/modified files), and named follow-up commands. As an instruction-only skill, absence of code is not penalized; minor gaps remain from delegating file-choice detail to the external 'agent-customization' skill, so it fits 'Mostly executable guidance; concrete code or commands with minor gaps' rather than the fully copy-paste-ready anchor.	4 / 5
Workflow Clarity	A clear four-step sequence (Discover existing conventions → Explore codebase → Generate or merge → Iterate) with a genuine feedback loop ('Ask for feedback on unclear or incomplete sections'). It falls short of 5 because there is no explicit validation checkpoint for the merge/overwrite step — 'Preserve valuable content, update outdated sections' states intent but includes no step to verify nothing valuable was lost. It is not a destructive/batch operation that would trigger the cap of 3.	4 / 5
Progressive Disclosure	The body is under 50 lines with no need for external reference files (none exist in the bundle), and it is organized into clear sections with external material (the 'agent-customization' and 'chronicle' skills) explicitly signaled exactly one level deep. Per the guideline for short skills with no need for external references, well-organized sections merit the top score.	5 / 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 states a clear, moderately specific purpose but is a single clause with no trigger guidance. Its 'what' is serviceable; its complete lack of a 'when' component and missing natural trigger terms (file names like AGENTS.md) keep it mid-range.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user wants to create or update agent instructions like AGENTS.md, .github/copilot-instructions.md, or CLAUDE.md, or set up agent skills.'

Name the concrete artifacts handled (AGENTS.md, .github/copilot-instructions.md, custom skills/agents) to raise specificity and give users natural trigger terms.

Mention key synonyms users would actually say ('agent instructions', 'coding agent setup') to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('chat customization files for AI coding agents') and one concrete action pair ('Generate or update'), but does not enumerate the concrete artifacts it works with (AGENTS.md, .github/copilot-instructions.md, skills, agents). This matches the anchor 'Names domain and 1-2 concrete actions, but not comprehensive' — not 4 because it does not list several specific actions, and not 2 because the actions are not purely generic.	3 / 5
Completeness	Has a clear 'what' ('Generate or update chat customization files for AI coding agents') but no 'when' clause at all — no 'Use when...' or equivalent trigger guidance — which caps completeness at 3 per the judging guidelines. Not 4 because the 'when' is entirely absent rather than merely implicit.	3 / 5
Trigger Term Quality	Contains relevant keywords ('customization files', 'AI coding agents') but misses the natural terms users would actually say, such as AGENTS.md, copilot-instructions, CLAUDE.md, or 'agent instructions'. Fits 'Some relevant keywords but missing common variations or synonyms' rather than 4, which requires good natural-term coverage.	3 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (chat customization files specifically for AI coding agents) that is unlikely to trigger for unrelated skills, with only minor overlap risk against generic documentation or config skills. Fits 'Mostly distinct; minor overlap risk with closely related skills' — not 5 since it lacks the fully distinct concrete triggers of the top anchor.	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/init/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.