trellis-channel

Use Trellis channel for live multi-agent collaboration, spawned workers, cross-agent review, progress inspection, forum channels, and channel log debugging.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

100%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 exemplary index skill: lean, actionable, with a clear intent-routing workflow and well-structured one-level-deep progressive disclosure into verified reference files.

Dimension	Reasoning	Score
Conciseness	The body is dense and operator-oriented with no concept preamble; every line earns its place (routing table, core rules, reference pointers, 'Not For'), and it assumes Claude's competence throughout.	5 / 5
Actionability	It provides copy-paste-ready entry commands ('trellis channel list --scope global --all', 'trellis channel forum <board> --scope global'), a concrete intent→reference routing table, and specific flag guidance (--type forum, --stdin, --raw, --kind done) covering the common cases.	5 / 5
Workflow Clarity	As an index/routing skill it sequences clearly (First Commands → inspect → Route By User Intent → Core Rules → Reference Files) and includes an explicit error-avoidance checkpoint in the dispatcher wait pattern rule; the simple-skill exception applies since no destructive/batch workflow is present.	5 / 5
Progressive Disclosure	It explicitly declares itself an index, maps each user signal to a specific one-level-deep references/*.md via the routing table, and lists each file with a one-line purpose; all five referenced files (workflows, forum, workers, progress-debugging, command-reference) exist and are well-signaled.	5 / 5
	Total	20 / 20 Passed

Description

67%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 specific and clearly niche-scoped to the Trellis channel runtime, but it lacks an explicit 'Use when…' trigger clause and the natural-language phrasing users would actually say, capping completeness and trigger quality.

Suggestions

Add an explicit 'Use when…' clause with concrete user triggers (e.g., 'Use when the user wants to brainstorm with another agent, spawn an implement/check worker, inspect a stalled channel, or open a forum board').

Surface natural user phrasing — phrases like 'brainstorm with an agent', 'spawn a worker', 'channel is stuck / no output' — into the description rather than only in the body.

Optionally include product/CLI synonyms ('trellis channel', 'channel run') to broaden keyword coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain (Trellis channel) and lists six concrete capabilities — 'live multi-agent collaboration, spawned workers, cross-agent review, progress inspection, forum channels, and channel log debugging' — for comprehensive coverage with no gaps.	5 / 5
Completeness	There is a clear 'what' (the capability list), but 'when' is only weakly implied by 'Use Trellis channel for…' with no explicit 'Use when…' trigger clause, which the guideline caps at 3.	3 / 5
Trigger Term Quality	It includes relevant domain keywords ('spawned workers', 'forum channels') but the natural user phrasing ('brainstorm with an agent', 'channel is stuck', 'spawn a worker') lives in the body rather than the description, so common variations are missing.	3 / 5
Distinctiveness Conflict Risk	It is scoped to a specific named runtime (Trellis channel) with distinctive features (forum channels, spawned workers, event-log debugging), giving it a clear niche with minimal conflict risk.	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: mindfold-ai/Trellis
Path: .agents/skills/trellis-channel/SKILL.md
Commit: 88f4834

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.