Tessl • The management layer for AI agent skills

An exemplary workflow-router skill: concrete paths, commands, contracts, and a well-signaled one-level-deep reference table make it highly actionable with excellent progressive disclosure. The only improvements are removing the small duplication between the principles and contract sections and adding a brief fix-and-retry loop to the validation step.

Dimension	Reasoning	Score
Conciseness	The body is dense with project-specific rules and explains nothing Claude already knows, but section 4 duplicates section 1 principles — 'Contributions load through the appropriate sessions.*.main.ts entry point' and 'Sessions menus use the shared Menus registry' restate earlier bullets almost verbatim. It is above anchor 3 (only minor trimming needed) but short of anchor 5's every-token-earns-its-place bar.	4 / 5
Actionability	For an instruction-only skill the guidance is fully executable: exact file paths (browser/menus.ts, src/vs/sessions/README.md), a 13-row routing table mapping areas to specific specifications, a copy-paste command (npm run valid-layers-check), named service contracts (ISessionsManagementService, ISessionsService), and a concrete three-item edit-gate checklist covering the common cases.	5 / 5
Workflow Clarity	The seven numbered sections give a clear, ordered workflow with a dedicated validation section (§5) and an explicit specification-edit gate (§4) acting as checkpoints. It misses anchor 5 because there is no error-recovery feedback loop — nothing about what to do when valid-layers-check or unit tests fail — though the anchors and sequence are otherwise explicit.	4 / 5
Progressive Disclosure	This is a model router: the body stays lean (principles plus a routing table) and pushes all detail to one-level-deep specifications, each row labeled with the area it owns, plus search-then-read guidance for the learning inbox. There are no bundle files to structure, and nothing that belongs in a separate file is inlined.	5 / 5
	Total	18 / 20 Passed

Description

73%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.

A tightly scoped, third-person description with an explicit path-based trigger clause and minimal conflict risk. Its main weakness is that 'Core principles and workflow router' names the artifact type rather than the concrete actions the skill performs, leaving both specificity and completeness just below the top anchors.

Suggestions

Replace the abstract role phrase with 1-2 concrete action verbs, e.g. 'Applies core Agents Window principles and routes changes to the owning specification under src/vs/sessions', to lift specificity from 3 to 4-5.

Add the most common natural synonyms users would say — 'Sessions', 'session/chat UI', 'automations' — to broaden trigger coverage toward the anchor-5 level.

Consider an explicit 'Use when changing code under src/vs/sessions/**' phrasing to make the when-clause unambiguous rather than embedded in a prepositional phrase.

Dimension	Reasoning	Score
Specificity	The description names its domain precisely ('changes to the Agents Window under src/vs/sessions') and its role ('Core principles and workflow router'), but lists no concrete actions such as applying principles, routing to specifications, or validating changes. It matches anchor 3 (domain plus a functional description, not comprehensive) rather than 4, which requires several specific enumerated actions.	3 / 5
Completeness	It answers both parts: what ('Core principles and workflow router') and an explicit when ('for changes to the Agents Window under src/vs/sessions'). It falls short of 5 because the 'what' is an abstract noun phrase describing the artifact rather than concrete action verbs, unlike the anchor-5 example's explicit capability list.	4 / 5
Trigger Term Quality	'Agents Window' and 'src/vs/sessions' are exactly the phrases a developer would naturally say when needing this skill, giving good keyword coverage. It stays at 4 rather than 5 because natural variations users might say — Sessions, automations, mobile layout, providers — are absent.	4 / 5
Distinctiveness Conflict Risk	The description is scoped to one directory in one codebase ('Agents Window under src/vs/sessions'), a clear niche with distinct triggers and minimal risk of firing for unrelated skills.	5 / 5
	Total	16 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: posit-dev/positron
Path: .github/skills/sessions/SKILL.md
Revision: 5d355d4

Reviewed: 22 days ago

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.

sessions

Table of Contents

Is this your skill?