trellis-start

Initializes an AI development session by reading workflow guides, developer identity, git status, active tasks, and project guidelines from .trellis/. Classifies incoming tasks and routes to brainstorm, direct edit, or task workflow. Use when beginning a new coding session, resuming work, starting a new task, or re-establishing project context.

Quality

95%

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%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 an exemplary instruction-only skill: a lean, well-sequenced session-initialization workflow with executable commands, explicit status-based decision routing, and clearly signaled on-demand references. No concept over-explanation, no padding, and no risky operations lacking validation.

Dimension	Reasoning	Score
Conciseness	The ~60-line body is lean and every sentence carries operational weight (e.g., 'This platform has no session-start hook, so manually load the equivalent compact context' explains why the manual steps exist). No explanation of concepts Claude already knows; matches the 5 anchor — every token earns its place.	5 / 5
Actionability	Fully executable, copy-paste-ready commands at every step: 'python3 ./.trellis/scripts/get_context.py' with three modes, and the exact step-detail invocation 'get_context.py --mode phase --step 2.1 --platform codex'. Concrete conditional routing in Step 4 covers the common cases.	5 / 5
Workflow Clarity	A clear 4-step sequence where Step 4 is an explicit condition→action checklist keyed off task status ('planning' + no prd.md → load trellis-brainstorm, etc.), plus an explicit output check in Step 1 ('If this output includes a line beginning Trellis update available:'). Operations are read-only, so no destructive/batch validation cap applies; matches the 5 anchor.	5 / 5
Progressive Disclosure	Single-file bundle with clearly signaled, one-level-deep, on-demand references: 'Full guide in .trellis/workflow.md (read on demand)', index files that 'list the specific guideline docs to read when you actually start coding', and 'Full rules + anti-rationalization table in .trellis/workflow.md'. Sections are well organized with an inline quick-reference routing table — matches the 5 anchor.	5 / 5
	Total	20 / 20 Passed

Description

88%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 in third-person voice that clearly states what the skill does (reads Trellis context artifacts, classifies tasks, routes to workflows) and when to use it, with concrete trigger phrases. The only weakness is trigger coverage that misses common user phrasings and slightly generic session-start triggers that create minor conflict risk.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions with comprehensive coverage: 'reading workflow guides, developer identity, git status, active tasks, and project guidelines from .trellis/', plus 'Classifies incoming tasks and routes to brainstorm, direct edit, or task workflow.' Not 4 because coverage of the skill's actual behavior (read, classify, route) has no gaps.	5 / 5
Completeness	Explicitly answers both what ('Initializes an AI development session by reading... Classifies incoming tasks and routes...') and when ('Use when beginning a new coding session, resuming work, starting a new task, or re-establishing project context') with concrete trigger phrases — a direct match for the 5 anchor.	5 / 5
Trigger Term Quality	Good natural trigger phrases — 'beginning a new coding session, resuming work, starting a new task, or re-establishing project context' — but misses common variations like 'onboarding', 'pick up where I left off', or 'get up to speed'. Matches the 4 anchor (good coverage, a few natural terms missing) rather than 5's synonym-level breadth.	4 / 5
Distinctiveness Conflict Risk	The .trellis/ niche is clear and the 'what' is highly specific, but broad triggers like 'beginning a new coding session' and 'starting a new task' could overlap with other session-start or task-management skills. Best fit is the 4 anchor (mostly distinct; minor overlap risk); the generic trigger phrasing rules out 5's 'minimal conflict risk'.	4 / 5
	Total	18 / 20 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: mindfold-ai/Trellis
Path: .agents/skills/trellis-start/SKILL.md
Commit: f089cb3

Reviewed: 3 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.