linear-resume
Resume in-flight work tracked in Linear by reading the latest handoff and surfacing where things stand + the reasoned next step.
Skill by thrawn01
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/thrawn01-linear-resume
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: backend, writing
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/linear-resume
What's inside
- Skill name
linear-resume- Description
- Resume in-flight work tracked in Linear by reading the latest handoff and surfacing where things stand + the reasoned next step. READ-ONLY: it reads, it does not branch, set up a worktree, change ticket status, or post anything. Use when the user says 'resume <project>', 'where did we leave off', 'pick up the git-server build', 'what's next on this ticket', '/linear-resume', or hands a Linear project/epic/ticket link and wants to continue. Two modes: (1) hand it a PROJECT or EPIC to learn which ticket is next, then move it to In Progress for dispatch; (2) hand it a single TICKET to re-hydrate a long-running, multi-session effort on that one ticket. Do NOT use to start work on a fresh ticket (dispatch launches /dispatch:build for that) or to write a handoff (that's /linear-handoff).
- License
- MIT
- Instructions
- 116 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- allowed-tools: must be a space-separated string
Files (1)
- SKILL.md
SKILL.md (first lines)
# Resume Linear-tracked work Read the **latest handoff** for whatever the user is resuming and turn it into a resume-from-here brief: where the build/ticket is, the open loose ends, and the reasoned next step. This skill is the **read** counterpart to `/linear-handoff` (which writes the handoff). It is strictly **read-only** — it never branches, creates a worktree, advances a ticket's status, or posts a comment/update. ## Prerequisites - Linear MCP connected (the `mcp__claude_ai_Linear__*` tools). If absent, stop and tell the user this skill needs Linear. ## The container model (project vs. issue) Linear stores a handoff in one of two places, and that is the only distinction this skill makes: | Resuming… | Handoff lives as | Read with | |---|---|---| | a **project** (a coordinated multi-ticket build) | the newest **status update** | `get_status_updates` `type:"project"` | | an **issue** — an **epic/parent** *or* a **standalone ticket** | the newest **handoff comment** | `list_comments` | Epic-vs-standalone makes no difference to the mechanism — both are issues, both store handoffs as comments. The only question is *project or issue?* A **handoff comment** is identified by convention: its body begins with a `## Handoff` heading (see `/linear-handoff`). When scanning an issue's comments, treat only those as handoffs; ignore ordinary discussion. ## 1. Resolve what to resume Resolve in order; stop at the first hit: 1. **Supplied** — the user named a project, or gave a ticket/epic id or Linear URL → use it. If it is an id/URL, `get_issue` it to learn its title, its `project`, and its `parent`. 2. **Current branch** — `git rev-parse --abbrev-ref HEAD` matches Linear's branch shape (`<user>/<team>-<num>-<slug>` or `ticket/<team>-<num>-<slug>`) → extract `<TEAM>-<NUM>`, `get_issue` it. If neither yields anything, ask the user which project/epic/ticket to resume. Never guess. **Decide project vs. issue:** - The user named a **project** (or you only have a project) → §2a. - The user handed an **issue** → §2b. (This is the same-ticket / epic-level case.) ## 2a. Read the latest project status update `get_status_updates` with `type:"project"`, the project name, `orderBy:"createdAt"`, `limit:1` (pull a few if you want the recent trail). The newest update is the resume point. If the project has **no** status updates, say so and fall back to listing the project's in-progress / recently-updated issues so the user can choose — there is no recorded handoff yet. ## 2b. Read the latest handoff comment on the issue `list_comments` for the issue, newest first. Find the first whose body begins with a `## Handoff` heading — that is the latest handoff. - **Found** → that comment is the resume point. - **None, but the issue has a `project`** → there is no per-ticket handoff; the coordinated build's state lives at the project level. Tell the user and offer to resume the **project** instead (re-run §2a against `issue.project`). - **None and no project** → there is no recorded handoff. Fall back to the issue's own description + most recent comments and say plainly that you are reconstructing from the ticket itself, not from a handoff. ## 3. Surface the resume brief Render what you read as a short, factual brief — do not dump the raw update/comment verbatim, distil it: - **Where it stands** — what last merged / what state the ticket is in (with ids/SHAs as written). - **In flight** — any open PR + its CI/review state, as recorded. - **Open loose ends** — deferred/skipped items, unresolved decisions, anything left red on purpose. - **The reasoned next step** — the next task and *why* it was chosen, copied from the handoff. If the handoff is stale or self-contradictory, say so rather than papering over it. If you read a project update naming the next **ticket**, name that ticket explicitly. If you read a single ticket's handoff, frame the next step as continuing *that* ticket. **Do not assert state the handoff did not claim.** If the handoff says "CI unverified," carry that caveat forward — do not upgrade it to "green." ## 4. Hand off to the next action (suggest, never execute) End by pointing at the next command — but **do not run it**; the user drives: - **Cross-ticket** (you resumed a project/epic and the next step is a *different* ticket) → give the ticket's id and suggest moving it to In Progress, so dispatch launches a `/dispatch:build <TEAM>-<NUM>` worker for it. - **Same-ticket** (you resumed one ticket to continue it) → if a worktree/branch for it already exists, give the user its path or branch to reopen (e.g. via `claude-workspace <branch>`); if not, suggest creating it the same way. Either way, this skill does not touch git. ## Boundaries - **READ-ONLY.** Never `git worktree add` / branch / checkout, never `save_issue` (no status or assignee change), never `save_comment` / `save_status_update`. Resume informs the next action; it is not the next action. - Do not move tickets or invoke `/linear-handoff` for the user — suggest the command and let them decide. - Do not re-derive sequencing the handoff already reasoned out — carry its "next" forward; only flag it if it's stale or wrong. ## Early exits | Condition | Action | |---|---| | No Linear MCP available | Stop — this skill requires Linear | | Nothing resolvable to resume | Ask the user which project/epic/ticket | | Project has no status updates | Say so; list in-progress issues to choose from | | Issue has no handoff comment but has a project | Offer to resume the project instead | | Issue has no handoff comment and no project | Reconstruct from the ticket; say you're doing so |
From thrawn01/claude-dotfiles, MIT.
More from thrawn01/claude-dotfiles
- 0.632score
review-tests
thrawn01
Review whether a feature's existing tests actually cover the acceptance criteria, scenarios, and correctness constraints documented in its Blueprint…
SkillAFreshness: A★ 11Claude Code +9 - 0.607score
herdr
thrawn01
Control Herdr, a terminal multiplexer for coding agents.
SkillAFreshness: A★ 11Claude Code +9 - 0.592score
no-ai-slop
thrawn01
Load and apply the No AI Slop output style — direct, opinionated answers with zero filler and a real point of view.
SkillBFreshness: B★ 11Claude Code +9 - 0.592score
html-explainer
thrawn01
Create a standalone HTML explainer that teaches a thing visually, from the outside in — leading with the perspective of the person who uses or calls it (a…
SkillBFreshness: B★ 11Claude Code +9 - 0.592score
lazy
thrawn01
Write the fewest words that carry the facts — terse, plain, human, not lawyerly.
SkillBFreshness: B★ 11Claude Code +9 - 0.592score
writing-prose
thrawn01
Write explanatory prose for a smart reader meeting the subject for the first time: newcomer explainers, concept sections, 'how it works' docs, the explanatory…
SkillBFreshness: B★ 11Claude Code +9 - 0.592score
writing-style
thrawn01
Write or edit long-form prose in the user's essayist voice.
SkillBFreshness: B★ 11Claude Code +9 - 0.543score
babysit-pr
thrawn01
Monitor and fix automated review comments (Copilot, SonarCloud) and CI failures on the current branch's PR.
SkillCFreshness: C★ 11Claude Code +9 - 0.542score
review-behavior-change
thrawn01
Review code changes for undocumented behavioral/surface changes.
SkillCFreshness: C★ 11Claude Code +9 - 0.542score
bug-detector
thrawn01
Detects bugs, logic errors, and edge case handling issues in code.
SkillCFreshness: C★ 11Claude Code +9 - 0.542score
handoff
thrawn01
Write a brief capturing the current state of in-flight work so it can be resumed in a fresh context window.
SkillCFreshness: C★ 11Claude Code +9 - 0.542score
review-for-reader
thrawn01
Review a PR/diff from the perspective of the next maintainer who never saw the change — catching comments, docstrings, and docs that only make sense to…
SkillCFreshness: C★ 11Claude Code +9
Signals
- Stars
- 11
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 20, 2026 (8 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/thrawn01/claude-dotfiles
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from thrawn01
- 0.632score
review-tests
thrawn01
Review whether a feature's existing tests actually cover the acceptance criteria, scenarios, and correctness constraints documented in its Blueprint…
SkillAFreshness: A★ 11Claude Code +9 - 0.607score
herdr
thrawn01
Control Herdr, a terminal multiplexer for coding agents.
SkillAFreshness: A★ 11Claude Code +9 - 0.592score
writing-prose
thrawn01
Write explanatory prose for a smart reader meeting the subject for the first time: newcomer explainers, concept sections, 'how it works' docs, the explanatory…
SkillBFreshness: B★ 11Claude Code +9 - 0.592score
lazy
thrawn01
Write the fewest words that carry the facts — terse, plain, human, not lawyerly.
SkillBFreshness: B★ 11Claude Code +9 - 0.592score
writing-style
thrawn01
Write or edit long-form prose in the user's essayist voice.
SkillBFreshness: B★ 11Claude Code +9 - 0.592score
html-explainer
thrawn01
Create a standalone HTML explainer that teaches a thing visually, from the outside in — leading with the perspective of the person who uses or calls it (a…
SkillBFreshness: B★ 11Claude Code +9
Cite this page
linear-resume skill. Agent Mart. https://agentmart.dev/skills/thrawn01-linear-resume (last updated 2026-10-24)