Linear Issue Assistant
Productivity skill, available on Zeplik
Linear Issue Assistant is a ready-to-run productivity skill on Zeplik. Not for sprint ceremonies (use sprint-planning). Ask in plain language and Zeplik applies the skill's method for you inside the conversation, on whichever AI model you prefer.
The Linear Issue Assistant skill loads automatically when your request matches it, or you can invoke it directly by typing /linear in any chat. It works with attachments, connectors, and any model that supports the task, so you get the same expert method every time without setting anything up.
What the Linear Issue Assistant skill can do
- Triage pasted bug lists by impact and frequency with priority calls
- Rewrite vague issue text into Linear-formatted issues with acceptance criteria
- Plan cycle scope from a backlog dump and stated capacity
- Draft status updates and retro summaries from issue exports
Try these prompts on Zeplik
Pick a prompt to open it in the Zeplik app. If you are not signed in yet, your prompt is waiting for you the moment you do.
How the Linear Issue Assistant skill works
/linear
Work with the user's Linear data in chat: they paste issue lists, CSV exports, cycle dumps, or screenshots of views, and you triage, plan, and draft in Linear's conventions -- producing output they can paste straight back into Linear.
Getting the data
Ask for whichever the user can easily provide:
- A pasted issue list or a CSV export (Linear exports include ID, title, status, priority, assignee, labels, estimate, cycle, created/updated dates)
- A pasted single issue for rewriting
- A description of the team's workflow states and label taxonomy if it deviates from Linear defaults (Backlog / Todo / In Progress / In Review / Done / Canceled; Urgent / High / Medium / Low / No priority)
Confirm scope before bulk work: which team, which cycle, what counts as high priority for them.
Linear conventions for drafted issues
Every issue you write follows this shape:
Title: <verb-first, specific, under ~70 chars: "Fix checkout timeout on 3DS retries">
Description:
## Context
<why this exists, links to evidence>
## Expected behavior
## Actual behavior (bugs) / Proposed solution (features)
## Acceptance criteria
- [ ] <verifiable outcome>
Priority: <Urgent | High | Medium | Low> -- with a one-line justification
Labels: <from their taxonomy; propose new ones explicitly>
Estimate: <points, using their scale if stated>
Vague input becomes concrete: "login is broken sometimes" -> reproduction conditions extracted from whatever the user provided, and an explicit list of what is still unknown.
Practical workflows
- Bug triage: rank pasted bugs by user impact x frequency, propose priority per issue, flag duplicates and stale reports, output an ordered list with one-line justifications.
- Cycle planning: from a backlog dump plus capacity (ask if missing), pick a coherent cycle scope, name a cycle goal, mark P0 vs stretch, and list what explicitly does not make the cut and why.
- Issue writing: turn feedback, support tickets, or a rambling paragraph into well-formed issues per the template; batch output as one paste-ready block per issue.
- Workload balance: group active issues by assignee from the export, flag overload (by count and by estimate sum), propose specific reassignments.
- Status updates: from issue statuses and dates, draft the project update -- shipped, in flight, blocked (with blockers named), at risk.
- Retro summary: for a completed cycle export, compare planned vs done, spot carryover patterns, and draft discussion points.
- Smart labeling: propose labels for unlabeled issues from their existing taxonomy; list any new label categories separately for approval.
Rules
- Never invent issue IDs, assignees, estimates, or dates not present in the pasted data; mark unknowns as
TBD. - Preserve their IDs (e.g.,
ENG-142) in all output so it maps back to Linear. - For bulk recommendations, explain the grouping logic before the list.
- Deliverables are paste-ready: clean Markdown blocks, or CSV matching their export columns when they want to re-import.
Usage
/linear $ARGUMENTS
How to use the Linear Issue Assistant skill
Sign in to Zeplik
Create a free Zeplik account or sign in. New accounts start with free credits, so you can try the Linear Issue Assistant skill right away.
Describe your productivity task
Ask in plain language, or type /linear to invoke the skill directly. Zeplik recognizes the Linear Issue Assistant skill and applies its method.
Review and refine the result
Zeplik returns a clear, structured answer. Ask follow-ups in the same chat to refine it or take the next step.
Source and credit
- Author
- davila7
- License
- MIT
Adapted from the open-source davila7/claude-code-templates project and tuned to run natively on Zeplik. View source on GitHub.
Frequently asked questions
- What is the Linear Issue Assistant skill?
- Linear Issue Assistant is a ready-to-run productivity skill on Zeplik. Not for sprint ceremonies (use sprint-planning). Ask in plain language and Zeplik applies the skill's method for you inside the conversation, on whichever AI model you prefer.
- How do I use Linear Issue Assistant on Zeplik?
- Sign in to Zeplik and ask in plain language, or type /linear in any chat to invoke it directly. The skill applies its method and returns a result you can refine in the same conversation.
- Which AI model does the Linear Issue Assistant skill use?
- Any model you choose. Zeplik works across every model in one chat, so the Linear Issue Assistant skill runs on your preferred model for the task.
- Where does the Linear Issue Assistant skill come from?
- The Linear Issue Assistant skill is adapted from the open-source davila7/claude-code-templates project (MIT) and tuned to run natively on Zeplik. The original source is linked on this page.
- How much does the Linear Issue Assistant skill cost?
- Using the skill is free to start. You only spend Zeplik credits when the assistant runs, and new accounts begin with free credits.
Related productivity skills
- Audio TranscriberUse when the user attaches audio or voice recordings to transcribe -- cleanup, speaker labels, timestamps, minutes or notes from a recording. Not for summarizing documents (use summarize-anything).
- Deadline PrepUse when a demo, standup, or delivery deadline looms: turn git history and notes into a structured demo outline. Not for sprint ceremonies (use sprint-planning) or capacity math (use capacity-plan).
- File OrganizerUse when designing a folder structure and reorganization plan for messy files -- downloads cleanup, duplicates, naming, archive rules. Not for converting file formats (use file-conversion).
- Marp Slide DecksUse when creating Markdown/Marp slide decks with themed embedded CSS the user renders via Marp CLI or VS Code. Not for general presentation building (use slides).
- Notion WorkflowsUse when designing Notion databases, templates, formulas, or workspace systems -- knowledge capture, meeting docs, specs, template businesses. Not for generic note-taking advice.
- Obsidian WorkflowsUse when working in Obsidian -- vault structure, Bases (.base files), wikilinks, callouts, plugins, zettelkasten, Web Clipper templates. Not for Notion (use notion-workflows).
More on Zeplik
- Linear integrationConnect Linear so the assistant can read and act in your account while this skill runs.
- Every AI model, one chatRun Linear Issue Assistant on GPT, Claude, Gemini, Grok and hundreds more; browse them all with live pricing.
- 997 integrationsConnect the apps you already use so skills can work with your real data.
Try Linear Issue Assistant on Zeplik
Every model, one chat. Bring the Linear Issue Assistant skill into your next conversation and let the assistant do the work.