onboard

Interactive three-part onboarding for new team members to the Trellis AI-assisted workflow system. Covers core philosophy (AI memory, project-specific knowledge, context drift), system structure and command deep-dives, real-world workflow examples, and guideline customization. Use when a new developer joins the project, someone needs to understand the Trellis workflow, or project guidelines need initial setup.

Quality

88%

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

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

Actionable and clearly sequenced with concrete commands and validation checkpoints, but token-heavy: it re-explains AI concepts Claude already knows and keeps all content inline rather than splitting detail into reference files.

Suggestions

Trim the 'Core Philosophy' section to project-specific essentials — Claude already knows that AI lacks persistent memory and has a limited context window; state only how Trellis addresses these.

Move the five real-world workflow examples and the spec-file listing into a separate reference file (e.g. EXAMPLES.md) with a one-line pointer from SKILL.md to apply progressive disclosure.

Collapse the repetitive 'WHY IT EXISTS / WHAT IT ACTUALLY DOES / WHY THIS MATTERS' scaffolding per skill into a single concise description to reduce token overhead.

Dimension	Reasoning	Score
Conciseness	The 'Core Philosophy' section explains general AI concepts Claude already knows (no memory, generic vs project-specific knowledge, limited context window) and repeated 'WHY THIS MATTERS' prose pads the token budget, though the bulk of the project-specific guidance earns its place.	2 / 3
Actionability	Provides concrete copy-paste commands ('python3 ./.trellis/scripts/task.py create "Fix bug" --slug fix-bug', 'grep -l "To be filled by the team" .trellis/spec/backend/*.md'), exact file paths, and specific step sequences.	3 / 3
Workflow Clarity	Numbered step sequences in all five real-world examples, an explicit validation checkpoint (grep template-status check before branching to Situation A/B), and a mandatory three-part completion checklist give a clear sequenced workflow.	3 / 3
Progressive Disclosure	Section headers organize the content well, but all ~360 lines are inline in one monolithic file with no reference files — the detailed examples, spec file listing, and skill deep dives would be better split into one-level-deep references.	2 / 3
	Total	10 / 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.

A strong description: third-person voice, specific enumerated capabilities, and an explicit multi-trigger 'Use when' clause. It clearly conveys both what the skill does and when to invoke it without over-claiming.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete capabilities with parenthetical detail — 'core philosophy (AI memory, project-specific knowledge, context drift), system structure and command deep-dives, real-world workflow examples, and guideline customization' — rather than vague language.	3 / 3
Completeness	Explicitly answers both what ('Interactive three-part onboarding... Covers core philosophy...') and when (explicit 'Use when...' clause with multiple triggers).	3 / 3
Trigger Term Quality	The 'Use when a new developer joins the project, someone needs to understand the Trellis workflow, or project guidelines need initial setup' clause covers natural phrasings a user would actually say.	3 / 3
Distinctiveness Conflict Risk	The 'Trellis AI-assisted workflow system' onboarding niche with triggers tied to new-developer onboarding and guideline setup is distinct and unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: zhukunpenglinyutong/desktop-cc-gui
Path: .agents/skills/onboard/SKILL.md
Commit: 786846c

Reviewed: about 12 hours 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.