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

100%

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

Quality

Content

100%

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 architecture overview: dense and jargon-appropriate, packed with executable commands and exact config keys, sequenced with a pre-edit checkpoint, and backed by well-organized one-level-deep reference files. It rewards rather than penalizes Claude's competence throughout.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's competence — it never explains what hooks, JSONL, or workflow phases are, and every line is Trellis-specific architectural detail that earns its place, matching the 'lean and efficient; every token earns its place' anchor rather than the 2 anchor with unnecessary explanation.	3 / 3
Actionability	Provides concrete, copy-ready commands and identifiers (`task.py create --parent <slug>`, `trellis channel spawn --agent <name>`, `trellis workflow --template <id>`, `trellis mem search\|extract\|context`) plus exact config keys (`hooks.after_create`, `channel.worker_guard.idle_timeout`, `codex.dispatch_mode`) and file paths, matching the 'fully executable code/commands' anchor.	3 / 3
Workflow Clarity	The 'How To Use' section gives a clear 5-step reading sequence with an explicit pre-edit checkpoint ('Before editing, read the actual files in the user project and treat local content as authoritative'), and the 'Do Not' section supplies guardrails for destructive overwrites (check `.trellis/.template-hashes.json`, prefer `.new` sidecars), matching the 'clear sequence with explicit validation steps' anchor.	3 / 3
Progressive Disclosure	SKILL.md is a concise overview pointing to one-level-deep references organized into three labeled groups (Local Architecture, Platform Files, Local Customization) with per-file descriptions; all referenced paths verified to exist, matching the 'clear overview with well-signaled one-level-deep references' anchor.	3 / 3
	Total	12 / 12 Passed

Description

100%

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 specific, explicitly triggers on concrete Trellis customization surfaces, and answers both what and when with natural in-domain terminology. Its only weakness is verbosity — a single very long sentence that could be tightened without losing the distinct niche.

Suggestions

Tighten the description into a shorter sentence or two; the enumerated surface list is comprehensive but padded, and the rubric penalizes verbosity even when accurate.

Consider trimming the redundant bundled-skills enumeration (the skill names and the 'bundled-skill auto-dispatch flow' overlap) to reduce token cost.

Dimension	Reasoning	Score
Specificity	Enumerates many concrete customization surfaces (`.trellis`, platform hooks/settings/agents/skills/commands/prompts/workflows, `trellis channel` runtime, `.trellis/agents/`, workflow templates, registry-backed spec refresh, `trellis mem`, bundled skills, auto-dispatch), matching the 'lists multiple specific concrete actions' anchor rather than the single-domain anchor at 2.	3 / 3
Completeness	Explicitly states what ('Understand and customize the local Trellis architecture inside a user project') and when ('Use when modifying .trellis plus platform hooks...'), satisfying the 'clearly answers both what AND when' anchor; it is not the 2 anchor which lacks an explicit trigger.	3 / 3
Trigger Term Quality	Uses in-domain natural terms a Trellis user would actually say ('modifying .trellis', 'hooks, settings, agents, skills, commands, workflows', 'trellis channel', 'trellis mem', 'trellis init', bundled-skill names), giving good coverage rather than the partial-variation anchor at 2.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear, Trellis-specific niche with distinct triggers (`trellis channel`, `trellis mem`, `.trellis/agents/`, named bundled skills) that are unlikely to fire for unrelated skills, matching the 'clear niche with distinct triggers' anchor.	3 / 3
	Total	12 / 12 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: .agents/skills/trellis-meta/SKILL.md
Commit: 12e279a

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.