sessions

Agents window architecture — covers the agents-first app, layering, folder structure, chat widget, menus, contributions, entry points, and development guidelines. Use when implementing features or fixing issues in the Agents window.

Quality

87%

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

Quality

Content

100%

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

A lean, highly actionable skill body: concrete commands, a clear pre-change and validation workflow, and a well-structured table of one-level-deep spec references.

Dimension	Reasoning	Score
Conciseness	The body is dense and project-specific with no padding or explanations of concepts Claude already knows; every section and pitfall earns its place even where entries run long.	3 / 3
Actionability	It gives concrete executable commands ("npm run compile-check-ts-native", "npm run valid-layers-check", "scripts/test.sh --grep"), exact spec file paths, and explicit do/don't rules that are copy-paste ready.	3 / 3
Workflow Clarity	A clear pre-change reading sequence is followed by a numbered validation checklist with explicit checkpoints and a "fix the imports before proceeding" feedback loop.	3 / 3
Progressive Disclosure	The overview body points to one-level-deep spec documents via a well-signaled table listing path and "When to read" for each, making navigation easy with no nested-reference chaining.	3 / 3
	Total	12 / 12 Passed

Description

75%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A clear, distinctive description with an explicit Use-when trigger, but it enumerates covered topics rather than concrete capabilities and offers a thin set of natural trigger terms.

Suggestions

Lead with concrete actions (e.g. "Add, refactor, or debug Agents window features") instead of the passive "covers" topic list to lift specificity.

Broaden trigger terms with natural user phrasings such as "Agents window bug", "sessions sidebar", or "chat widget" so it matches how users actually ask.

Dimension	Reasoning	Score
Specificity	The description enumerates topic areas ("covers the agents-first app, layering, folder structure, chat widget, menus, contributions, entry points, and development guidelines") rather than concrete actions; the only action verbs are the generic "implementing features or fixing issues".	2 / 3
Completeness	It explicitly answers both what (the covered architecture areas) and when ("Use when implementing features or fixing issues in the Agents window").	3 / 3
Trigger Term Quality	"Agents window" combined with "implementing features or fixing issues" gives a relevant but narrow set of natural terms, lacking common variations a user might actually say.	2 / 3
Distinctiveness Conflict Risk	"Agents window" is a clear, distinctive niche with a specific trigger, making it unlikely to fire for unrelated skills.	3 / 3
	Total	10 / 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
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: posit-dev/positron
Path: .github/skills/sessions/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.