CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

66

Quality

79%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/trellis-continue/SKILL.md

The canonical home for this skill is trellis-continue in mindfold-ai/Trellis

SKILL.md
Quality
Evals
Security

Quality

Content

75%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 resume-workflow skill with exact commands and a thorough routing matrix, appropriately deferring detail to .trellis/workflow.md. It is efficient and well-structured but stops just short of fully executable substitution and explicit validation checkpoints.

Suggestions

Enumerate the <X.X> step values or point to where they are listed so Step 4's command is copy-paste ready.

Add an explicit checkpoint in Step 3 (e.g. confirm git state / current task before routing) to strengthen the sequence's validation.

Trim the explanatory aside 'This command replaces the user needing to remember the Trellis flow' to keep the body fully lean.

DimensionReasoningScore

Conciseness

Lean, command- and routing-rule-dense body with no concept padding; a couple of mild over-explanation phrases (e.g. 'This command replaces the user needing to remember the Trellis flow') keep it just below the fully lean anchor.

4 / 5

Actionability

Provides exact executable bash commands and a concrete status-to-step routing matrix; the <X.X> placeholder is an explicit parameter, though its substitution values are not enumerated.

4 / 5

Workflow Clarity

Clear four-step sequence with an explicit decision matrix in Step 3 routing by status and artifact presence; non-destructive read/resume flow, so the destructive-cap does not apply, but an explicit confirmation checkpoint is implicit rather than stated.

4 / 5

Progressive Disclosure

Well-organized entry-point overview with a single, clearly signaled one-level-deep reference to .trellis/workflow.md; no bundle files exist, so the body is appropriately self-contained, with minor structural gaps.

4 / 5

Total

16

/

20

Passed

Description

83%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 that explicitly covers both what the skill does and when to use it, using concrete actions and a named command. Trigger language is natural and user-facing; minor room for more synonyms and a slightly more distinctive framing.

DimensionReasoningScore

Specificity

Names three concrete actions (loads the Phase Index, figures out which phase/step to pick up, pulls step-level detail via the named command get_context.py --mode phase), above the 1-2-action anchor but shy of fully comprehensive coverage.

4 / 5

Completeness

Explicitly answers both what it does (loads Phase Index, figures out phase/step, pulls step-level detail) and when to use it ('Use when coming back to an in-progress task and you need to know what to do next').

5 / 5

Trigger Term Quality

Includes natural user phrasing ('Resume work', 'coming back to an in-progress task', 'need to know what to do next') with good coverage, though a few natural synonyms are absent.

4 / 5

Distinctiveness Conflict Risk

Tied to a distinct Trellis Phase Index workflow with a clear trigger, but 'resume work on the current task' is broadly applicable language that could overlap with other workflow skills.

4 / 5

Total

17

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
EcoPasteHub/EcoPaste
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.