Name: trellis-meta
Rating: 75.2 (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

94%

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

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

Quality

Content

92%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.

An excellent meta-skill body: concrete commands, paths, and config keys throughout, a well-sequenced conditional workflow with explicit pre-edit validation and destructive-overwrite guards, and clean one-level-deep progressive disclosure verified against the actual bundle. The only weakness is mild verbosity where overview paragraphs duplicate detail already covered in reference files.

Suggestions

Compress the 'Trellis v0.6 adds three architectural surfaces' paragraph to a one-line summary per surface and defer the detail to references/local-architecture/multi-agent-channel.md, workspace-memory.md, and bundled-skills.md.

Move the per-platform detail (Pi's trellis_subagent dispatch modes, Reasonix's runAs frontmatter, Kimi Code's shared skill layer) out of the platform-directory bullet and into references/platform-files/platform-map.md, keeping only the directory list inline.

Dimension	Reasoning	Score
Conciseness	Every line is Trellis-specific with no explanations of concepts Claude already knows, but the ~170-word 'Trellis v0.6 adds three architectural surfaces' paragraph and the platform-directory bullet's per-platform detail (Pi trellis_subagent modes, Reasonix frontmatter, Kimi Code layout) partially duplicate dedicated reference files and could be tightened.	4 / 5
Actionability	Concrete, executable guidance throughout: exact commands ('trellis workflow --template <id>', 'task.py create --parent <slug>', 'trellis channel spawn --agent <name>'), exact config keys ('codex.dispatch_mode: inline \| sub-agent', 'channel.worker_guard.idle_timeout'), exact paths, and specific Do/Don't rules — fully actionable for an instruction-only skill.	5 / 5
Workflow Clarity	The 'How To Use' section gives a clear 5-step conditional read sequence with an explicit pre-edit validation checkpoint ('read the actual files in the user project and treat local content as authoritative'), a destructive-overwrite guard ('check `.trellis/.template-hashes.json` first and prefer `.new` sidecar files'), and a fact-check guard (cross-check `trellis --help` before claiming a knob exists).	5 / 5
Progressive Disclosure	A genuine overview body pointing to 22 one-level-deep reference files, all verified to exist on disk, each with a clear one-line description organized into three grouped sections; navigation is easy and content is appropriately split.	5 / 5
	Total	19 / 20 Passed

Description

95%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 description with an explicit 'Use when...' clause, comprehensive natural trigger terms, and a clearly distinct Trellis-specific niche. The only minor weakness is the generic headline verbs ('Understand and customize') backed by an enumerated scope rather than multiple distinct concrete actions.

Dimension	Reasoning	Score
Specificity	'Use when modifying .trellis plus platform hooks, settings, agents, skills, commands, prompts, workflows, the channel runtime (trellis channel), bundled runtime agents..., registry-backed spec refresh, cross-session memory (trellis mem)...' lists several concrete action targets with near-comprehensive coverage, but the headline verbs 'Understand and customize' are generic rather than the multiple distinct concrete actions of the top anchor.	4 / 5
Completeness	Explicitly answers both: what ('Understand and customize the local Trellis architecture inside a user project') and when ('Use when modifying .trellis plus platform hooks, settings, agents, skills, commands, prompts, workflows...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural trigger coverage within the niche: '.trellis', 'hooks', 'settings', 'agents', 'skills', 'commands', 'prompts', 'workflows', 'trellis channel', 'trellis mem', 'trellis init', workflow templates, spec refresh, and named bundled skills — exactly what a user customizing Trellis would say.	5 / 5
Distinctiveness Conflict Risk	A clear niche with Trellis-specific identifiers (trellis channel, trellis mem, .trellis, bundled skill names) that no other skill would match; minimal conflict risk.	5 / 5
	Total	19 / 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: f089cb3

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.