multi-session

Use when you need to orchestrate multiple parallel terminal sessions via wsh server mode. Examples: "run builds in parallel across several projects", "tail logs in one session while working in another", "fan out tests across multiple sessions and gather results".

Quality

68%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/multi-session/SKILL.md

Quality

Discovery

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.

The description has a clear 'Use when' clause with good examples and occupies a distinct niche, which are its main strengths. However, it could be more specific about the concrete actions the skill performs (beyond user-facing examples) and could include more natural trigger terms that users would actually say instead of relying on the technical term 'wsh server mode'.

Suggestions

Add concrete capability verbs describing what the skill does, e.g., 'Spawns and manages multiple parallel terminal sessions, collects output, and coordinates concurrent commands using wsh server mode.'

Include more natural trigger terms users might say, such as 'concurrent commands', 'run simultaneously', 'multiple terminals', 'background tasks', or 'parallel processes'.

Dimension	Reasoning	Score
Specificity	The description names the domain (parallel terminal sessions via wsh server mode) and gives examples of actions (run builds in parallel, tail logs, fan out tests), but doesn't list concrete specific capabilities of the skill itself—it relies on user-facing examples rather than stating what the skill actually does (e.g., 'spawns terminal sessions', 'collects output', 'manages session lifecycle').	2 / 3
Completeness	Clearly answers both 'what' (orchestrate multiple parallel terminal sessions via wsh server mode) and 'when' (explicit 'Use when' clause with multiple example triggers covering builds, logs, and tests).	3 / 3
Trigger Term Quality	Includes some natural terms like 'parallel', 'builds', 'logs', 'tests', 'sessions', but the primary trigger 'wsh server mode' is technical jargon most users wouldn't naturally say. Missing common variations like 'concurrent commands', 'background tasks', 'multiple terminals', 'run simultaneously'.	2 / 3
Distinctiveness Conflict Risk	The focus on 'wsh server mode' and 'multiple parallel terminal sessions' is a very specific niche that is unlikely to conflict with other skills. The combination of parallel execution and terminal session orchestration creates a distinct identity.	3 / 3
	Total	10 / 12 Passed

Implementation

62%

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

This is a well-structured guide to multi-session orchestration patterns with clear workflow sequences and good organizational patterns (fan-out, watcher, pipeline). However, it operates at an abstract/pseudocode level rather than providing executable commands, and it includes some verbose sections explaining concepts Claude would already understand (when to use parallelism, process isolation basics). The content would benefit from being more concrete in its examples and trimming explanatory material.

Suggestions

Make examples more actionable by providing at least one fully executable example — either a concrete wsh_* tool call sequence or a complete curl-based workflow — rather than only pseudocode-style descriptions.

Trim the 'When to Use Multiple Sessions' section significantly — Claude understands when parallelism is appropriate vs sequential execution; a single sentence would suffice.

Consider splitting the federation section and detailed pitfalls into a separate reference file to keep the main SKILL.md focused on core patterns and reduce its length.

Dimension	Reasoning	Score
Conciseness	The content is generally well-written but includes some unnecessary verbosity — the 'When to Use Multiple Sessions' section explains obvious heuristics Claude would know, the 'Context Isolation Cuts Both Ways' section explains basic process isolation concepts, and the federation section adds significant length for what could be a brief pointer. The execution context preamble is also quite long.	2 / 3
Actionability	The skill provides patterns and pseudocode-like instructions (e.g., 'create session "build"', 'send input to "build": exit\n') but these are not executable — they're abstract descriptions of operations rather than concrete tool calls, curl commands, or real code. The preamble acknowledges this by saying 'this skill describes what to do' but that inherently limits actionability.	2 / 3
Workflow Clarity	The multi-step workflows are clearly sequenced with explicit patterns (fan-out, watcher, pipeline). The fan-out pattern includes polling/waiting strategies, the pipeline pattern includes conditional progression, and session cleanup discipline is emphasized throughout. The wait-for-idle with tag filtering provides an efficient coordination mechanism.	3 / 3
Progressive Disclosure	The content is a single monolithic file with no bundle files to reference. It references 'wsh:cluster-orchestration' skill and 'skills/core/ SKILL.md' for API details, which is good, but the document itself is quite long (~200+ lines) and could benefit from splitting pitfalls or patterns into separate reference files. The federation section in particular could be a separate document.	2 / 3
	Total	9 / 12 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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: deepgram/wsh
Commit: 4863aaf

Reviewed: 10 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.