Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →langfuse/cursor-agents-workflow
Human handoff, Linear branch names, reviewable (non-draft) PRs, Claude, Greptile, and Codex review comments, preview test steps, proof of work posted on the GitHub PR, and review-doubt notes for Cursor agents.
Passed 14 of 19 test cases with the skill, and 7 of 19 without it.
and 10 more in the full report
10 fixed6 passed either way4 still failing2 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.
We just created PR #45. Which GitHub label should be applied immediately using the PR label tool, rather than waiting for a human?
| Checked | Without skill | With skill |
|---|---|---|
| Directs applying the cursor label immediately | Missed | Passed |
The instructions your model reads when the skill loads.
Use this when implementing Langfuse work as a Cursor agent. Keep humans in the loop with short, testable asks. Do not write long agent-only reports.
Copy Linear's git branch name. Do not invent a cursor/ name.
gitBranchName read through the Linear MCP.lfe-{id}-{kebab-title} (lowercase, hyphenated).user/ prefix only when Linear's copied name already includes one.cursor/ prefix, even if a Cursor Cloud prompt asks for one.
Repo guidance wins.Correct: lfe-12345-short-descriptive-title
Wrong: cursor/short-descriptive-title-8c78
Cursor desktop can authorize the Linear MCP interactively. Cursor Cloud cannot:
mcp_auth is desktop-only, and the Cloud GitHub token is unrelated to Linear.
On Cloud, prove Linear with a real read. If the MCP is needsAuth or missing,
use LINEAR_API_KEY (or LINEAR_TOKEN / LINEAR_API_TOKEN) via GraphQL or
lf-context.sh. If that env is unset, say so and tell them to add
LINEAR_API_KEY at https://cursor.com/dashboard/cloud-agents, then start a
new run. Langfuse engineers: the write policy is
linear-agent-writes.
If Linear is not reachable, say so in your handoff message and hand back the context that should have gone on the ticket. Do not skip it silently.
Open the GitHub PR as reviewable, not as a draft. Draft PRs hide the work
test cases passed, vs 7 / 19 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.