linear-issue-management
Skill75 starsChanged 4 months agoMITView on GitHub
Manage Linear issues safely through the GraphQL API, including team/project/label discovery, creating issues, updating issues, searching existing issues, handling mutually-exclusive labels, and using 1Password-backed Linear API auth without printing secrets. Use when filing, triaging, editing, or auditing Linear tickets such as CORE issues.
- Reads credentials
1 other project uses a version of this.
Adopted by
Most recently taken up by
- tim-osterhus/millrace-skillstheir own version, first seen Apr 28, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- tim-osterhus/millrace-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository59 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- skills/heygen-skills/CLAUDE.mdCLAUDE.md
- 1passwordSkill
- ask-curlSkill
- boardSkill
- cleanup-unused-filesSkill
- codeflow-maintainerSkill
- codex-session-managerSkill
- coven-astraSkill
- coven-board-entrySkill
- coven-charmSkill
- coven-cloud-maintainerSkill
- coven-codySkill
- coven-echoSkill
- coven-identity-canonSkill
- coven-kittySkill
- coven-parallel-workSkill
- coven-sageSkill
- coven-task-managerSkill
- daily-dev-agenticSkill
- discrawlSkill
- disk-space-optimizerSkill
- epubSkill
- familiar-board-stewardshipSkill
- heygen-avatarSkill
- heygen-videoSkill
- heygen-skillsSkill
- higgsfield-generateSkill
- higgsfieldSkill
- lit-ui-designerSkill
- lobsterSkill
- maintainer-barSkill
- memory-recallSkill
- memory-timeline-managerSkill
- ml-engineerSkill
- nodriverSkill
- ocrSkill
- openclaw-devSkill
- openclaw-trustSkill
- opencoven-designSkill
- OpenCoven Role Creation ProcessSkill
- pr-agentSkill
- project-managerSkill
- prompt-engineerSkill
- prompt-vaultSkill
- research-ingestionSkill
- ritual-dapp-frontendSkill
- rollcallSkill
- security-agentSkill
- skill-scannerSkill
- slidev-deck-pipelineSkill
- tauri-apple-releaseSkill
- threejs-animationSkill
- tinyfish-agent-runSkill
- tinyfish-browserSkill
- tinyfish-fetchSkill
- tinyfish-searchSkill
- tinyfishSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
19 rules. About 0 are common, 14 are distinctive, and 5 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈14
Distinctive · estimate
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Use this skill when working with Linear issues through the API.
- Distinctive: line 18
Search for an existing issue to avoid duplicates.
- Distinctive: line 25
Do not print, paste, log, or commit the Linear API token.
- Distinctive: line 26
Prefer 1Password-backed env injection or an existing secret manager.
- Distinctive: line 27
Treat issue creation, updates, comments, assignment changes, and state transitions as external state-changing actions.
- Distinctive: line 28
Use GraphQL variables. Do not interpolate untrusted user text into a GraphQL query string.
- Distinctive: line 29
Keep issue text factual. Do not file speculation as confirmed defects.
- Distinctive: line 30
Do not file in a team just because an issue key prefix looks familiar.
- Very specific: line 34
Use a Linear API key in LINEAR_API_KEY.
- Very specific: line 51
Never echo the token. If debugging auth, print only whether LINEAR_API_KEY is set, not its value.
- Very specific: line 55
Read references/graphql-recipes.md for query/mutation templates.
- Distinctive: line 57
Search existing issues by relevant keywords and repo/project names.
- Very specific: line 60
Create the issue with title, description, teamId, optional projectId, optional labelIds, and optional priority.
- Distinctive: line 66
If two requested labels conflict, choose the more precise/current one and mention the omitted label.
- Distinctive: line 71
Use this compact structure unless the user asks otherwise:
- Very specific: line 95
Search by issue key first if provided (CORE-14).
- Distinctive: line 96
Search by URL slug or title keywords when no key is available.
- Distinctive: line 98
Prefer additive updates unless the user explicitly asks to remove/replace labels, state, assignee, or project.
- Distinctive: line 102
When handing a Linear issue to Cody or another coding agent, include:
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Linear Issue Management
Use this skill when working with Linear issues through the API.
Prime directive
Discover before writing. Never guess the team, project, state, assignee, or label IDs from memory when creating or updating a Linear issue.
Before any mutation:
- Confirm the target workspace/team from the user request or current project context.
- Query Linear for the exact team/project/label/state IDs.
- Search for an existing issue to avoid duplicates.
- Show the intended mutation summary if the action is externally visible or ambiguous.
- Execute one focused GraphQL mutation.
- Return the issue key + URL and record any important follow-up context.
Safety rules
- Do not print, paste, log, or commit the Linear API token.
- Prefer 1Password-backed env injection or an existing secret manager. Do not write tokens to files.
- Treat issue creation, updates, comments, assignment changes, and state transitions as external state-changing actions. Get explicit user approval unless the user already gave a direct instruction in the current conversation.
- Use GraphQL variables. Do not interpolate untrusted user text into a GraphQL query string.
- Keep issue text factual. Do not file speculation as confirmed defects.
- Do not file in a team just because an issue key prefix looks familiar; confirm via API.
Auth pattern
Use a Linear API key in LINEAR_API_KEY.
Preferred shape:
op run --env-file <linear-env-file> -- <command using LINEAR_API_KEY>or, when the shell already has the token:
curl https://api.linear.app/graphql \
-H "Authorization: $LINEAR_API_KEY" \
-H 'Content-Type: application/json' \
--data-binary @payload.jsonNever echo the token. If debugging auth, print only whether LINEAR_API_KEY is set, not its value.
Workflow: create an issue
- Read
references/graphql-recipes.mdfor query/mutation templates. - Discover teams and choose the exact
teamId. - Search existing issues by relevant keywords and repo/project names.
- Discover labels/projects/states only after the team is known.
- Resolve label conflicts before mutation.
- Create the issue with title, description,
teamId, optionalprojectId, optionallabelIds, and optional priority. - Return the created issue identifier and URL.
Label rules
- Linear can have grouped labels where child labels are mutually exclusive.
- If two requested labels conflict, choose the more precise/current one and mention the omitted label.
- Known OpenClaw Linear rule:
InfraandImprovementare mutually exclusive grouped child labels. Do not apply both.
Writing good issue bodies
Use this compact structure unless the user asks otherwise:
## Problem
<what is wrong and who it affects>
## Evidence
- <specific file/log/error/link when available>
## Expected behavior
<desired end state>
## Proposed fix
<short implementation direction, if known>
## Acceptance criteria
- [ ] <verifiable outcome>
- [ ] <test or validation gate>For follow-up implementation tickets, include exact repo paths, config keys, issue IDs, and commands when known.
Updating/searching issues
- Search by issue key first if provided (
CORE-14). - Search by URL slug or title keywords when no key is available.
- Fetch current labels/state before replacing anything.
- Prefer additive updates unless the user explicitly asks to remove/replace labels, state, assignee, or project.
Handoff to coding agents
When handing a Linear issue to Cody or another coding agent, include:
- Linear key + URL
- Repo/path scope
- Summary of the intended code change
- Required verification commands
- Constraints: preserve dirty work, no secret printing, do not touch unrelated files
- Any linked docs/memory references needed for context
References
references/graphql-recipes.md— GraphQL discovery, search, create, update, and comment templates.
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
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.

