Name: trellis-meta
Rating: 64.8 (1 reviews)
Author: mindfold-ai

trellis-meta

Understand and customize the local Trellis architecture inside a user project. Use when modifying .trellis plus platform hooks, settings, agents, skills, commands, prompts, workflows, the channel runtime (trellis channel), bundled runtime agents under .trellis/agents/, selectable workflow templates, registry-backed spec refresh, cross-session memory (trellis mem) generated by trellis init, or AI-facing bundled skills (trellis-channel, trellis-session-insight, trellis-spec-bootstrap) and bundled-skill auto-dispatch flow.

Quality

77%

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

Fix and improve this skill with Tessl

tessl review fix ./.opencode/skills/trellis-meta/SKILL.md

The canonical home for this skill is trellis-meta in mindfold-ai/Trellis

Quality

Content

71%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.

A well-structured, highly actionable meta-skill whose SKILL.md correctly serves as an overview pointing to a verified, one-level-deep reference bundle. The main drag on token efficiency is cross-section restatement of the same paths and a long platform-directory enumeration.

Suggestions

De-duplicate paths/facts that recur across the intro, Current Rules, and Do Not (e.g., the channel events.jsonl path and bundled-agent behavior) by stating each once and cross-referencing.

Promote the existing validation cues ('check .trellis/.template-hashes.json', 'cross-check trellis --help') into explicit numbered checkpoints in the 'How To Use' workflow so post-edit verification is part of the sequence rather than only in 'Do Not'.

Dimension	Reasoning	Score
Conciseness	The body is information-dense and avoids explaining concepts Claude already knows, but the same paths and facts (channel event log, bundled agents) recur across the intro, Current Rules, and Do Not, and the platform-directory enumeration is long enough that it could be tightened.	3 / 5
Actionability	It supplies concrete, copy-paste-ready CLI commands ('trellis channel spawn --agent <name>', 'task.py create --parent <slug>', 'trellis workflow --template <id>') and specific config keys throughout, with only minor gaps since full code blocks are absent (acceptable for an instruction skill).	4 / 5
Workflow Clarity	The 'How To Use' section gives a clear 5-step sequence and validation cues exist ('treat local content as authoritative', cross-check 'trellis --help', check '.trellis/.template-hashes.json'), but the validation is distributed across 'Do Not' rather than appearing as explicit post-edit checkpoints in the workflow.	4 / 5
Progressive Disclosure	SKILL.md is a clean overview with a References section listing 23 real, one-level-deep files organized into three labeled groups, each with a one-line description, giving easy navigation.	5 / 5
	Total	16 / 20 Passed

Description

83%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 strong, third-person description with an explicit 'Use when' clause and comprehensive, tool-specific trigger surfaces. Its main weakness is verb variety ('understand and customize') and the sheer jargon density that could obscure the most natural user phrasings.

Suggestions

Vary the action verbs beyond 'Understand and customize' (e.g., 'Inspect, modify, and extend') to push specificity toward comprehensive distinct actions.

Lead with the most common natural phrasing (e.g., 'Use when modifying the .trellis setup or platform integration files in a project') before the long surface list, so the primary trigger is not buried in jargon.

Dimension	Reasoning	Score
Specificity	The description enumerates many specific customization surfaces (.trellis, platform hooks, agents, channel runtime, trellis mem, bundled skills), but the verbs are limited to 'Understand and customize', so it lists several specific targets with minor gaps in action variety rather than fully comprehensive distinct actions.	4 / 5
Completeness	It explicitly answers both 'what' ('Understand and customize the local Trellis architecture inside a user project') and 'when' via a concrete 'Use when modifying...' clause with multiple trigger surfaces.	5 / 5
Trigger Term Quality	Strong keyword coverage including natural CLI synonyms ('channel runtime (trellis channel)', 'cross-session memory (trellis mem)') and tool invocations users would say ('trellis init'), though the density of jargon buries a few common phrasings.	4 / 5
Distinctiveness Conflict Risk	It carves a clear Trellis-architecture-customization niche with highly specific triggers, with only minor overlap risk against the sibling bundled skills (trellis-channel, trellis-spec-bootstrap, trellis-session-insight) it names.	4 / 5
	Total	17 / 20 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: 27 deeper-than-1-level	Warning

	Total	15 / 16 Passed

Repository: mindfold-ai/Trellis
Path: .opencode/skills/trellis-meta/SKILL.md
Commit: e77ae89

Reviewed: 3 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.