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

92%

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%

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

A tight, actionable session-start procedure with a clear sequenced workflow and well-signaled deferred detail. It respects token budget while giving concrete commands and an unambiguous decision tree.

Dimension	Reasoning	Score
Conciseness	Lean, command-driven body where each step is a one-line purpose plus an executable command; it assumes Claude's competence with no padding or concept explanations.	3 / 3
Actionability	Provides fully executable commands (python3 ./.trellis/scripts/get_context.py with concrete flags, cat of index files) plus a specific decision-routing table and copy-paste-ready branches.	3 / 3
Workflow Clarity	Clear Steps 1–4 sequence with an explicit decision tree in Step 4 (planning/no-prd, planning/prd, in_progress, no active task); operations are read-only context gathering so the destructive-validation cap does not apply.	3 / 3
Progressive Disclosure	Well-organized into concise sections that defer detail to one-level-deep, clearly-signaled read-on-demand references ("Full guide in .trellis/workflow.md (read on demand)", index files); no nested reference chains.	3 / 3
	Total	12 / 12 Passed

Description

85%

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, third-person description that clearly states capabilities and an explicit use trigger. The only weak spot is trigger phrasing, which uses scenario sentences rather than the crisp natural keywords users tend to say.

Suggestions

Add short natural keyword variations to the trigger clause (e.g., "new task", "resume session", "get project context") alongside the scenario phrasing.

Consider condensing "re-establishing project context" to a plainer term a user would actually say.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "reading workflow guides, developer identity, git status, active tasks, and project guidelines", "Classifies incoming tasks", "routes to brainstorm, direct edit, or task workflow" — matching the multiple-specific-actions anchor.	3 / 3
Completeness	Explicitly states what it does (initialize/classify/route) and when via an explicit "Use when beginning a new coding session, resuming work..." clause, satisfying both what and when.	3 / 3
Trigger Term Quality	Triggers like "beginning a new coding session, resuming work, starting a new task" are natural scenarios, but they lean phrase-based and technical ("re-establishing project context"), lacking crisper keyword variations users would say.	2 / 3
Distinctiveness Conflict Risk	Tied to a clear Trellis-specific niche with triggers referencing .trellis/ and session-start context, making conflict with other generic skills unlikely.	3 / 3
	Total	11 / 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: mindfold-ai/Trellis
Path: .agents/skills/trellis-start/SKILL.md
Commit: 12e279a

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.