agentleFS
rkhozinovrkhozinov/claude-skills/skills/linear/SKILL.md

linear

Skill0 starsChanged 4 months agoMITView on GitHub

Everyday Linear issue ops — create, list, comment, get, update, start/stop/close, assign. Use this for typical work like "create an issue", "comment on <prefix>-123", "what are my open issues". For projects, cycles, bulk operations, team transfers, attachments, advanced filters/templates, use the `linear-power` skill instead.

  • Reads credentials

83 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use agent-deep-links, helium-mcp and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • ComposioHQSkill

    agent-deep-links

    Build, validate, and troubleshoot deep links for Codex, Cursor, VS Code, Visual Studio, and similar tools. Use when users ask for clickable links (especially in Slack) that open threads, files, folders, or app settings.

    Also in 3 projects that use this

  • ComposioHQSkill

    helium-mcp

    Search real-time news with bias scoring, get live stock/ETF/crypto data with AI analysis, ML options pricing, balanced news synthesis, and meme search via the Helium MCP server.

    Also in 3 projects that use this

  • petestewartSkill

    datadog-logs

    Query Datadog logs via the Logs Search API v2. Use when the user asks to "check the logs", "search logs", "find errors in Datadog", "look up logs for", "show me production logs", "check for errors", "search Datadog", or any request involving log search, error investigation, or production debugging that requires Datadog log data.

    Also in 3 projects that use this

  • OpenAISkill

    pull

    Also in 5 projects that use this

  • SentrySkill

    datadog

    Query live Datadog telemetry (logs, metrics, traces, spans, monitors, incidents, dashboards, services, hosts) through Datadog's Pup CLI. Use when users ask to investigate production behavior in Datadog, including searching logs, checking monitor status, inspecting traces or spans, looking up incidents, finding services, or correlating metrics. Do not use it for Sentry issues, repository/source-code work, or ticketing.

    Also in 4 projects that use this

  • +7 more from ComposioHQ

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 79 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If --state "Name" fails validation: use --data '{"stateId": "UUID"}' with the workflow state UUID.

    line 63
  2. Distinctive:

    Default human table. Override:

    line 78
  3. Very specific:

    Use the name with --team. The key is the issue prefix (<prefix>-123).

    line 102

“Common” is measured: kept by at least 6 in 10 of the 79 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Linear CLI — Everyday

Bundled Python uv-script. Auth: $LINEAR_API_KEY. Invoke as ${CLAUDE_PLUGIN_ROOT}/skills/linear/bin/linear-cli (or just linear-cli if symlinked into PATH).

Defaults (env vars)

VarEffect
LINEAR_API_KEYAuth (required)
LINEAR_DEFAULT_TEAMUsed when --team is omitted on issues create, issues list, projects create
LINEAR_DEFAULT_PROJECTUsed as default --project on create/list when omitted

Set in your shell rc so you stop typing --team "<team>" on every command. CLI args still override env.

Quick reference

TaskCommand
Create issuelinear-cli issues create "Title" --team "<team>" -p 2
List my issueslinear-cli i list --mine --limit 10
List team issueslinear-cli i list --team "<team>" --state "In Progress"
Get issuelinear-cli i get <prefix>-123
Get with commentslinear-cli i get <prefix>-123 --comments
Update title/statelinear-cli i update <prefix>-123 -T "New" -s "Done"
Commentlinear-cli issues comment <prefix>-123 --body "Text"
Start (in progress + assign me)linear-cli i start <prefix>-123
Stop (back to backlog)linear-cli i stop <prefix>-123
Close (done)linear-cli i close <prefix>-123
Assignlinear-cli i assign <prefix>-123 me
Whoamilinear-cli whoami
Labels (preview before use)linear-cli labels list --team "<team>"
Epic childrenlinear-cli i get <prefix>-100 --output json | jq '.[0].children'
Attach to epiclinear-cli i update <prefix>-123 --parent <prefix>-100
Create under epiclinear-cli i create "Title" --team "<team>" --parent <prefix>-100

Create — flags

linear-cli issues create [OPTIONS] <TITLE> (title is positional, not --title).

FlagShortPurpose
--team-tTeam name (required) — "<team>", not "<prefix>"
--description-dMarkdown body. Use - to read from stdin
--priority-p0=none, 1=urgent, 2=high, 3=normal, 4=low
--state-sState name (e.g. "Backlog", "Todo")
--assignee-a"me", user name, email, or UUID
--labels-lRepeat for multiple
--duetoday, tomorrow, +3d, +1w, YYYY-MM-DD
--estimate-ePoints
--parentParent issue (epic) identifier or UUID
--dry-runShow payload without creating

Update

linear-cli issues update [OPTIONS] <ID> (ID positional). Title flag is -T (capital), not --title.

If --state "Name" fails validation: use --data '{"stateId": "UUID"}' with the workflow state UUID. Project: --project "Name" or --project none to clear. Parent (epic): --parent <prefix>-100 or --parent none to detach.

Epics / sub-issues

Linear has no "epic" type; an epic is a parent issue, children link via parentId. get returns parent {id, identifier, title} on every issue and children [{identifier, title, state}] (first 100). list returns parent only. Verify an attach with i get <child> --fields "identifier,parent.identifier".

History: before 2026-09-20 the CLI accepted --data '{"parentId": ...}' but never queried parent/children, so a successful attach read back as null and could not be verified from the CLI.

Output

Default human table. Override:

--output json       # structured JSON
--output ndjson     # one object per line
--fields "identifier,title,state.name"   # table honours the projection (nested keys ok)
--format '{{identifier}} {{title}}'
--id-only           # just identifiers, scripting-friendly

Common pitfalls

MistakeFix
--title "X" on createTitle is positional: create "X"
--status "Done"Flag is --state (or -s)
--team "<prefix>"Use full name: "<team>"
--label "nonexistent"Labels must exist; check with labels list --team "<team>"
show <prefix>-123Subcommand is get, not show

Team name → key

<team>=<prefix>, IT=IT, <team>=<prefix>, <team>=<prefix>, Data=<prefix>, <prefix>=<prefix>, <team>=<prefix>, <team>=<prefix>, <team>=<prefix>, <team>=<prefix>, <org>=<prefix>, <team>=<prefix>, <team>=<prefix>, <team>=<prefix>, <team>=<prefix>.

Use the name with --team. The key is the issue prefix (<prefix>-123).

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.