Search Linear Issues

SkillSearch

Use this skill whenever the user wants to search, list, or filter Linear issues — by state, assignee, label, or free text — even if they say 'find', 'show me', 'what's open', 'list my issues', or similar phrasing rather than 'search Linear'. Composes a Linear IssueFilter from structured flags, executes a cursor-paginated search scoped to the configured team, and renders a summary table of the results. Prefer this skill over raw GraphQL whenever the user's intent maps to a structured flag.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the Search Linear Issues skill

What this skill tells your AI

The instructions your AI receives, as published by atomicinnovation/accelerator in skills/integrations/linear/search-linear-issues/SKILL.md and read by ahel’s review.

!${CLAUDE_PLUGIN_ROOT}/bin/accelerator config context --skill search-linear-issues --fail-safe

Configuration: Set work.integration: linear in .accelerator/config.md. The team is fixed at /init-linear time (single-team scoping) — there is no per-search --team flag. See the ### work section of configure/SKILL.md for the full reference.

Search the configured Linear team using structured flags that compose into a Linear IssueFilter. Work through the steps below in order.

Step 1: Parse the flag set

Read the argument string and note each flag:

  • --state NAME — WorkflowState name. Resolved (case-insensitively) to its team-scoped UUID via the cached catalogue; an unknown state is an error.
  • --assignee NAME — assignee display name.
  • --label NAME — label name.
  • --text STR — free-text match on the issue title.
  • --limit N — page size (1..250, default 50). Pagination follows every page regardless; --limit only sets the per-request page size.

Step 2: Run the search

Run the search subcommand, passing the flags through verbatim:

${CLAUDE_PLUGIN_ROOT}/bin/accelerator linear search [flags]

Run the bare launcher directly as an executable; never prefix it with bash/sh/env and never pipe its output (a wrapper prefix or a pipe escapes the skill's allowed-tools permission and forces an unnecessary prompt).

The subcommand echoes the composed IssueFilter to stderr (INFO:) for auditability and emits a single merged JSON document with all pages under .data.issues.nodes, plus a top-level outcome keyword — results, empty, or truncated. When outcome is truncated (equivalently .data.issues.truncated is true), more pages remained than were fetched — say so.

Step 3: Render the results

Render a Markdown table with one row per issue:

IdentifierTitleStateAssignee

Read each row from .data.issues.nodes[]: .identifier, .title, .state.name, .assignee.name (show for an unassigned issue). Report the total count and note if the result was truncated.

!${CLAUDE_PLUGIN_ROOT}/bin/accelerator config instructions search-linear-issues --fail-safe

Signals

GitHub stars
31
Forks
1
Last commit
Sep 2026

ahel review

  • S4info
    community integration — published by atomicinnovation, not linear

Automated review, not a security audit. Ruleset v1.

Advanced
Catalog kind
skill
Gateway key
search-linear-issues
Source
github.com/atomicinnovation/accelerator