Content
86%Weight 40%Scale 1-5Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A well-structured, actionable meta-skill with a clear sequenced workflow, concrete commands and paths, and excellent progressive disclosure through verified reference files. Minor tightening of redundant intro material and an explicit feedback loop would lift it further.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Dense, information-rich body that assumes Claude's competence (no explaining what hooks/skills/agents are) and earns most of its tokens; minor redundancy between the v0.6 intro paragraph and the Current Rules section keeps it just below the lean anchor 5. | 4 / 5 |
Actionability | Highly actionable for an instruction-only skill: concrete CLI commands ('trellis channel spawn --agent <name>', 'trellis mem list | search | context | extract | projects', 'task.py create --parent <slug>', 'trellis workflow --template <id>'), exact file paths, and specific config keys (hooks.after_create, channel.worker_guard.idle_timeout, codex.dispatch_mode) cover the common cases. | 5 / 5 |
Workflow Clarity | The 'How To Use' section gives a clear 5-step sequenced navigation procedure with a verification checkpoint ('read the actual files... treat local content as authoritative'), and the Do Not section adds validation (check .template-hashes.json, cross-check trellis --help); no explicit validate->fix->retry feedback loop, so it sits at 4 rather than 5. | 4 / 5 |
Progressive Disclosure | SKILL.md is a clear overview pointing to well-signaled, one-level-deep references organized into three labeled categories (Local Architecture, Platform Files, Local Customization), each file described and verified present; navigation is easy and content is appropriately split. | 5 / 5 |
Total | 18 / 20 Passed |