meaningful-linear-issueslisted
Install: claude install-skill stealth-engine/skills
# Meaningful Linear issues
A good issue is **not** just a good description — that's the easy half. The half
agents skip is the **metadata** that makes Linear actually work as a planning tool:
estimates feed cycle velocity, labels feed breakdowns, milestones feed roadmaps, the
project feeds everything. Those fields are *optional in the API*, so agents leave them
blank and the user has to come back and ask again.
**Flip the default: metadata is opt-OUT, not opt-in.** Resolve and fill it **before**
calling `save_issue`, in one pass — propose concrete values, don't omit.
## Cardinal rule: never guess the project
The single worst failure is dropping an issue into the **wrong/random project**.
Resolve the project in this order — **stop at the first that's certain**:
1. **Context** — the issue's repo/area maps to a known project; the user named it; a
sibling issue you're relating to has one.
2. **Confirm** — call [`list_projects`](#discover-valid-values) and match by name; if
one clearly fits, state which and proceed.
3. **Ask** — if it's still ambiguous, **ask the user which project** rather than
picking one. A missing project is recoverable; a wrong one quietly pollutes the
wrong roadmap.
Never pass a `project` you inferred from vibes. Team is required too — usually
unambiguous from the project, but resolve it the same way.
## The one-pass workflow
1. **Discover** what's available (only what you don't already know): projects, the
team's label taxonomy, miles