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

90%

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

87%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 lean, dense, and highly actionable, with concrete commands, paths, and config keys throughout and an excellent one-level-deep reference structure. Its one weak spot is workflow_clarity: the customization workflow has good guardrails but no explicit validation/re-run feedback loop for destructive edits.

Suggestions

Add an explicit validate→fix→retry checkpoint to the 'How To Use' workflow, e.g. after editing run `trellis --help` / inspect `.trellis/config.yaml` to confirm a knob exists, and re-check `.trellis/.template-hashes.json` before any overwrite.

Make the destructive-edit guardrail in 'Do Not' (check `.trellis/.template-hashes.json` first, prefer `.new` sidecars) a numbered step in the workflow rather than only a negative rule, so the validation loop is part of the sequence.

Cross-reference the bundled `trellis-session-insight` skill from the `mem`/workspace-memory guidance so the 'when to reach for mem' validation path is reachable from the main workflow.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's competence — it never explains what a hook, task, or channel is, and packs concrete paths, config keys, and CLI subcommands into every line, matching the lean score-5 anchor.	5 / 5
Actionability	Fully executable guidance throughout: concrete commands ('task.py create --parent <slug>', 'trellis channel spawn --agent <name>', 'trellis mem search\|extract\|context', 'trellis workflow --template <id>'), exact file paths, and named config keys ('channel.worker_guard.idle_timeout', 'codex.dispatch_mode') cover the common customization cases.	5 / 5
Workflow Clarity	The 'How To Use' section is a clear 5-step numbered sequence with an authority checkpoint ('read the actual files in the user project and treat local content as authoritative') and a 'Do Not' guardrail list, but it lacks an explicit validate→fix→retry feedback loop for the destructive/batch local edits this skill governs, which the rubric caps at 3.	3 / 5
Progressive Disclosure	A clear overview body points to well-labeled one-level-deep references grouped under Local Architecture, Platform Files, and Local Customization; every referenced path was verified to exist as a real bundle file, so navigation is clean and easy.	5 / 5
	Total	18 / 20 Passed

Description

92%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, complete, and distinctive, explicitly pairing a concrete 'what' with a detailed 'Use when' clause and naming many real customization surfaces and bundled skills. Trigger-term coverage is strong with only minor synonym gaps.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete customization surfaces — '.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)' — comprehensive coverage of the skill's capabilities, matching the score-5 anchor.	5 / 5
Completeness	Explicitly answers both 'what' ('Understand and customize the local Trellis architecture inside a user project') and 'when' ('Use when modifying .trellis plus...') with concrete trigger phrases, matching the score-5 anchor.	5 / 5
Trigger Term Quality	Good keyword coverage with natural terms a user would say ('modifying .trellis', 'platform hooks', 'trellis channel', 'workflow templates', 'trellis mem', 'trellis init'), plus named bundled skills; a few common synonyms/variations are missing so it sits just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	A clear niche — local Trellis architecture customization — anchored by highly specific named triggers (.trellis, trellis channel, trellis mem, bundled skill names) that minimize overlap with unrelated skills.	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: .agents/skills/trellis-meta/SKILL.md
Commit: 64e6636

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.