trellis-continue

Resume work on the current task. Loads the workflow Phase Index, figures out which phase/step to pick up at, then pulls the step-level detail via get_context.py --mode phase. Use when coming back to an in-progress task and you need to know what to do next.

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

92%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 well-crafted routing skill: lean, fully sequenced, with an exhaustive decision table and clean deferral to the canonical workflow file. The only weaknesses are minor actionability gaps — an unexplained --platform flag and an unspecified lightweight/complex decision criterion.

Dimension	Reasoning	Score
Conciseness	Lean throughout: terse confirmations ("Confirms: current task, git state, recent commits."), a dense status/artifact routing table, and no explanation of concepts Claude already knows. Every routing bullet carries decision information, matching the "lean and efficient" anchor. Not 4: there is no trimmable over-explanation to remove.	5 / 5
Actionability	Commands are executable and copy-paste ready ("python3 ./.trellis/scripts/get_context.py --mode phase") and routing conditions are explicit, but there are minor gaps: "--platform codex" appears unexplained, "decide whether the task is lightweight or complex" gives no criteria, and "--step <X.X>" is a placeholder. Not 5: these gaps mean the guidance is not fully self-sufficient for every decision point.	4 / 5
Workflow Clarity	Clear ordered sequence (load context → load Phase Index → decide → load specific step) with explicit checkpoints: Step 1 confirms state, and the exhaustive status/artifact routing table covers every status value with a target step. No destructive or batch operations, so the validation cap does not apply. Not 4: checkpoints are explicit and complete, not implicit.	5 / 5
Progressive Disclosure	The body is an explicit entry point with a clearly signaled one-level-deep reference ("Full workflow and detailed phase steps live in .trellis/workflow.md") and well-organized sections; no bundle files exist to mis-structure. Not 4: nothing that belongs in a separate file is inlined beyond the resume-essential routing table.	5 / 5
	Total	19 / 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: third-person voice, concrete actions including an exact command, and an explicit "Use when" clause with a realistic trigger phrase. The only gaps are a couple of missing natural synonyms ("continue", "where I left off") and a lead trigger that is somewhat generic relative to sibling workflow skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Loads the workflow Phase Index", "figures out which phase/step to pick up at", "pulls the step-level detail via get_context.py --mode phase" — including an exact command, giving comprehensive coverage of what the skill does. Not 4: coverage is complete rather than gappy for this function.	5 / 5
Completeness	Explicitly answers both: the "what" via the three named actions, and the "when" via "Use when coming back to an in-progress task and you need to know what to do next" — a concrete trigger phrase. Matches the anchor-5 example structure exactly.	5 / 5
Trigger Term Quality	Natural phrases users would say are present ("Resume work", "coming back to an in-progress task", "what to do next"), but common synonyms like "continue" or "where I left off" are missing. Not 3: several genuinely natural trigger phrases exist, not just domain jargon.	4 / 5
Distinctiveness Conflict Risk	Niche-specific markers ("workflow Phase Index", "get_context.py --mode phase") distinguish it, but the lead trigger "Resume work on the current task" is generic enough to overlap with other task-management/workflow skills. Not 5: minor overlap risk remains with closely related resume-style skills.	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-continue/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.