CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

trellis-bootstrap

Initialize Trellis AI workflow system in a project. Use when user mentions "Trellis", "初始化 Trellis", "setup Trellis", "install Trellis", or wants to add AI-assisted development workflow to their project. This is a one-time setup skill.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

82%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.

A tight, actionable bootstrap skill: fully executable commands, an explicit step sequence, verification, and success criteria. It loses points only on minor redundancy, absent error-recovery guidance for install/init failures, and a couple of sections that could be consolidated.

Suggestions

Remove the redundant trailing 'Note' at the end, which repeats the 'After successful setup, this skill is no longer needed. The user should use /start' statement from the Success Criteria section.

Add brief error-recovery guidance for the two most likely failure points: 'trellis --version' failing after npm install (e.g., PATH/restart terminal) and 'trellis init' errors (e.g., not in project root, rerun in the correct directory).

Consider merging the 'What is Trellis?' bullets into the opening paragraph to tighten the overview without losing the structure/memory/automation context.

DimensionReasoningScore

Conciseness

The body is efficient — executable commands, a compact directory tree, and a command table with almost no filler — but includes minor redundancy: the closing note 'Once Trellis is initialized, use the built-in /start command instead of this skill' repeats the 'After successful setup, this skill is no longer needed. The user should use /start' line above it, and the 'What is Trellis?' bullets could be trimmed.

4 / 5

Actionability

Every step is copy-paste ready: 'node --version', 'npm install -g @mindfoldhq/trellis@latest', 'trellis --version', 'trellis init -u <developer-name>', and verification 'ls -la .trellis/' commands, plus a concrete example question for the developer-name step. Commands are executable as written and cover the common path end to end.

5 / 5

Workflow Clarity

Clear sequence (prerequisites → install → get name → init → verify) with a verification step and a Success Criteria checklist, plus one error path ('If Node.js is not installed, ask the user to install it first'). Not 5 because there are no feedback loops for other failure modes (e.g., 'trellis --version' failing after install, or 'trellis init' erroring), and not 3 because checkpoints are explicit and the operation is non-destructive.

4 / 5

Progressive Disclosure

No bundle files exist and none are needed at this size; content is organized into well-labeled sections with headers, a table, and a checklist. It sits just above the <50-line threshold where clean sections alone earn a 5, and the ~113-line body includes borderline-inline detail (the Quick Reference command table and directory tree), so 'good structure with minor organization gaps' is the best fit.

4 / 5

Total

17

/

20

Passed

Description

86%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: explicit what and when, comprehensive natural triggers (including bilingual variants), third-person voice, and a distinct proper-noun niche. Its only weaknesses are that it names a single action rather than enumerating the setup steps, and one broad intent clause that slightly raises conflict risk.

DimensionReasoningScore

Specificity

The description names the domain and exactly one concrete action — 'Initialize Trellis AI workflow system in a project' — without listing what setup involves (installing the CLI, running init, verifying). This matches 'names domain and 1-2 concrete actions, but not comprehensive'; it is not 4 because no additional specific actions are enumerated, and not 2 because 'initialize ... in a project' is a concrete, non-generic action.

3 / 5

Completeness

It explicitly answers 'what' ('Initialize Trellis AI workflow system in a project') and 'when' with concrete trigger phrases ('Use when user mentions "Trellis", "初始化 Trellis", "setup Trellis", "install Trellis"...'), and adds the useful scope note 'This is a one-time setup skill' — matching the anchor for clearly and explicitly answering both. Voice is third person ('Initialize', 'Use when').

5 / 5

Trigger Term Quality

Trigger coverage is comprehensive for this domain: 'Trellis', '初始化 Trellis', 'setup Trellis', 'install Trellis', plus the intent-based paraphrase 'wants to add AI-assisted development workflow to their project'. It includes the product name, bilingual variants, and the natural setup/install/initialize verb forms a user would actually say, matching the 'comprehensive coverage of natural terms including synonyms' anchor.

5 / 5

Distinctiveness Conflict Risk

The 'Trellis' proper-noun triggers give it a clear, distinct niche, but the broader clause 'wants to add AI-assisted development workflow to their project' could fire for generic AI-workflow setup requests unrelated to Trellis — minor overlap risk with closely related skills, which is the anchor-4 fit rather than 5's 'minimal conflict risk'.

4 / 5

Total

17

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

Total

15

/

16

Passed

Repository

mindfold-ai/Trellis

Path

.trellis/tasks/archive/2026-01/01-19-readme-redesign-taosu/bootstrap-skill/SKILL.md

Reviewed

Table of Contents

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.