Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →langfuse/linear-agent-writes
The org policy for what an agent may write to Linear, and how it must be marked. Read this before creating a ticket, editing a description, or commenting on a ticket as an agent — "file this in Linear", "comment on the ticket", "create subtickets for this plan", "write the handover". Also covers the required Linear connection and what to do when there isn't one.
Passed 14 of 23 test cases with the skill, and 5 of 23 without it.
and 11 more in the full report
10 fixed4 passed either way8 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
Please update Linear ticket LFE-6200: set its priority to Urgent, estimate effort as 5 points, and add it to the Q3 Roadmap project.
| Checked | Without skill | With skill |
|---|---|---|
| Refrains from directly updating priority, estimation, or project fields in Linear. | Missed | Passed |
| Presents priority, estimation, and project updates as suggestions for a human. | Missed | Passed |
The instructions your model reads when the skill loads.
Agents may write to Linear, but most writes are proposals first. Show the text you intend to land, get an explicit go-ahead, then write it yourself. Do not silently mutate a ticket the human is mid-session with.
The one exception is a subticket of an existing ticket — that shape is free, because planning a stack is useless if every child needs its own yes.
The guardrail is propose-then-write, plus marking, plus a bounded set of shapes: three permitted write shapes, each stamped with a label, each marked as agent-written in the text. Everything outside those three shapes still belongs to a human.
This file is the single authority for that policy. Other skills and repo instructions point here; none of them restate the rules. If another document disagrees with this one, this one wins — fix the other document.
It is maintainer-facing: it binds anyone whose agent can reach the Langfuse issue tracker, and it has nothing to ask of an outside contributor.
Provenance: the "Agentic Coding and Linear" RFC (LFE-15914), which replaced the earlier "Linear is read-only for agents" posture; tightened after feedback that auto-updating tickets mid-implementation was worse than proposing the update (LFE-16058).
Ordinary Linear writes are short. A new ticket or subticket is a title and two to four sentences: what to do, and why in one line if it is not obvious. Comments stay to the thing the watcher needs today.
Expand — research, file lists — only when they ask ("expand this", "add context"). Do not invent an implementation-ready brief.
Wrong (they said "create a subticket"): six fields, entry-point files, a stack position, a research essay.
Right: "Warn sunset event types on POST /ingestion request body. Fern still lists trace-create as if it works; say those event types stop on Nov 16."
test cases passed, vs 5 / 23 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.