CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

sessions

Core principles and workflow router for changes to the Agents Window under src/vs/sessions.

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.github/skills/sessions/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

86%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 an exemplar router skill: concrete, path-exact guidance organized into a clear seven-step workflow that defers all detail to one-level-deep specifications. Its only weaknesses are mild repetition in the specification-edit-gate and skill-maintenance sections and the absence of an explicit validation-failure recovery loop.

DimensionReasoningScore

Conciseness

The body is dense and prescriptive with zero concept re-teaching — every bullet is a repo-specific rule, and it actively budgets itself ("Keep the core-principles section at no more than ten bullets"). Minor trimming is possible: the specification edit gate and sections 6-7 each restate the where-knowledge-belongs philosophy, keeping it just short of the every-token-earns-its-place anchor.

4 / 5

Actionability

For an instruction-only skill the guidance is fully executable: an exact command (`pnpm run valid-layers-check`), exact paths (`browser/menus.ts`, `sessions.*.main.ts`), named contracts (`ISessionsManagementService`, `ISession`/`IChat`), and a 13-row routing table of exact specification paths covering every subsystem. This matches the anchor for concrete, copy-paste-ready guidance covering the common cases.

5 / 5

Workflow Clarity

Sections 1-7 form a coherent sequence (principles → identify area → inspect → implement → validate → record feedback → maintain) with an explicit proportional-validation section and the three-question edit-gate checklist ("If any answer is missing, leave the specification unchanged"). It sits at anchor 4 rather than 5 only because there is no explicit error-recovery loop, e.g. what to do when valid-layers-check fails.

4 / 5

Progressive Disclosure

The skill is a pure router: a well-signaled table maps each area to its specification one level deep, reinforced by "read only the specifications relevant to the change" and heading-scoped searching of the learning inbox. No bundle files exist to fragment content, and the body stays a lean overview — a clear match for the well-signaled one-level-deep-references anchor.

5 / 5

Total

18

/

20

Passed

Description

61%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 highly distinct and correctly scoped to a specific code area, but it tells Claude what the skill contains rather than what it does. Adding one or two concrete actions and richer trigger phrasing would lift the weaker specificity and trigger-term dimensions.

Suggestions

Name 1-2 concrete capabilities in the description, e.g. "Applies layering and provider-neutrality principles and routes changes to the owning specification" instead of the generic "Core principles and workflow router".

Add an explicit "Use when..." trigger clause with natural variations, e.g. "Use when implementing, reviewing, or designing Agents Window work — sessions model, layout, automations, session list, mobile, or Copilot Chat providers".

Include subsystem synonyms from the routing table (sessions sidebar, layout, automations, providers) so the description triggers on the natural phrases users actually say.

DimensionReasoningScore

Specificity

The description names a precise domain ("changes to the Agents Window under src/vs/sessions") but lists no concrete actions — "Core principles and workflow router" describes what the skill contains, not what it does. It matches the anchor for naming the domain with minimal or generic actions, and cannot reach 3 because no concrete action is stated.

2 / 5

Completeness

The "when" is explicit and path-scoped ("for changes to the Agents Window under src/vs/sessions"), and a "what" is present ("Core principles and workflow router"), so both halves are answered. It falls short of anchor 5 because the "what" is generic rather than concrete capabilities, while the explicit "when" rules out anchor 3.

4 / 5

Trigger Term Quality

"Agents Window" and "src/vs/sessions" are natural terms a developer would say, but coverage stops there — no subsystem variations the body actually routes to (sessions list, layout, mobile, Copilot Chat, automations). This is some relevant keywords with common variations missing, short of anchor 4's good keyword coverage.

3 / 5

Distinctiveness Conflict Risk

Scoping triggers to a named feature and a specific source path ("Agents Window under src/vs/sessions") gives the skill a clear niche with minimal overlap risk against other skills. This squarely matches the clear-niche anchor.

5 / 5

Total

14

/

20

Passed

Validation

100%

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

microsoft/vscode

Path

.github/skills/sessions/SKILL.md

Reviewed

Table of Contents

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.