pp-linear
Offline-capable, agent-native Linear CLI with SQLite-backed sync, FTS5 search, cross-cycle comparison, project... Trigger phrases: `what's on my Linear plate today`, `Linear sprint plan for the team`, `Linear cycle comparison`, `Linear burndown for the project`, `which Linear milestone is at risk`, `stale Linear issues`, `clean up the Linear test tickets I created`, `use linear-pp-cli`, `run linear-pp-cli`.
What this skill does
<!-- GENERATED FILE — DO NOT EDIT.
This file is a verbatim mirror of library/project-management/linear/SKILL.md,
regenerated post-merge by tools/generate-skills/. Hand-edits here are
silently overwritten on the next regen. Edit the library/ source instead.
See the repository agent guide, section "Generated artifacts: registry.json, cli-skills/". -->
# Linear — Printing Press CLI
## Prerequisites: Install the CLI
This skill drives the `linear-pp-cli` binary. **You must verify the CLI is installed before invoking any command from this skill.** If it is missing, install it first:
1. Install via the Printing Press installer. It defaults binaries to `$HOME/.local/bin` on macOS/Linux and `%LOCALAPPDATA%\Programs\PrintingPress\bin` on Windows:
```bash
npx -y @mvanhorn/printing-press-library install linear --cli-only
```
2. Verify: `linear-pp-cli --version`
3. Ensure the reported install directory is on `$PATH` for the agent/runtime that will invoke this skill.
If the `npx` install fails (no Node, offline, etc.), fall back to a direct Go install (requires Go 1.26.3 or newer):
```bash
go install github.com/mvanhorn/printing-press-library/library/project-management/linear/cmd/linear-pp-cli@latest
```
If `--version` reports "command not found" after install, the runtime cannot see the binary directory on `$PATH`. Do not proceed with skill commands until verification succeeds.
## When to Use This CLI
Reach for this CLI when you need joined queries that span issues, cycles, projects, and milestones — questions Linear's UI answers across multiple tabs and the API answers across multiple round-trips. It's the right pick for agents driving Linear over MCP (the orchestration pair plus named intents covers the full surface in ~1K tokens), for engineering managers preparing Friday updates (cycle comparison, slipped, burndown, blocking queue), and for any agent that must mutate a real workspace under the pp_created fixture-lifecycle contract.
## Unique Capabilities
These capabilities aren't available in any other tool for this API.
### Local state that compounds
- **`today`** — See all of your assigned issues across every team for today, ranked by priority and cycle deadline.
_Reach for this when an agent or human needs a single ranked work queue across every team, without naming the underlying joins._
```bash
linear-pp-cli today --json --agent
```
- **`bottleneck`** — See which team members are overloaded and which issues are blocked before sprint planning.
_Reach for this in sprint planning when you need to see who is overloaded and where work is stuck in one view._
```bash
linear-pp-cli bottleneck --team ENG --json
```
- **`stale`** — Find issues that haven't been touched in N days, grouped by team and project.
_Reach for this during backlog grooming when you need to surface forgotten issues without exhausting the API rate limit._
```bash
linear-pp-cli stale --days 30 --team ENG --json
```
- **`similar`** — Find issues that look like duplicates of a query string using offline FTS5 fuzzy matching.
_Reach for this during triage when you suspect an incoming bug duplicates an existing issue._
```bash
linear-pp-cli similar "login redirect bug" --limit 5 --json
```
### Cross-entity rollups
- **`projects burndown`** — Project a project's landing date by linear-regressing remaining estimate against the team's measured velocity.
_Reach for this when stakeholders ask when a project will land and the project page only shows a static target date someone typed in months ago._
```bash
linear-pp-cli projects burndown PROJ_ID --weeks 8 --json
```
- **`cycles compare`** — Side-by-side metrics between any two cycles: completion %, scope added, scope cut, carryover, average cycle time.
_Reach for this for cycle retros and Friday updates when you need a numeric diff rather than two browser tabs._
```bash
linear-pp-cli cycles compare 42 43 --json
```
- **`slipped`** — Show what carried over from last cycle into this cycle, grouped by team and reason heuristic.
_Reach for this in Friday stakeholder updates when you need a structured slipped-from-last-cycle list, not just a saved view._
```bash
linear-pp-cli slipped --team ENG --json
```
- **`velocity`** — Track sprint completion rates over the last N cycles to spot productivity trends.
_Reach for this in Monday sprint planning to ground rebalance decisions in actual completion data, not the team's last cycle alone._
```bash
linear-pp-cli velocity --weeks 8 --json
```
- **`initiatives health`** — Rolled-up portfolio view per initiative: child project progress, milestone target-vs-projected dates, slippage flags.
_Reach for this in portfolio reviews when stakeholders want the initiative-level rollup, not seven open project tabs._
```bash
linear-pp-cli initiatives health --json
```
- **`milestones at-risk`** — List portfolio milestones whose projected landing date has slipped past their target, ranked by slip magnitude.
_Reach for this in weekly portfolio review when the question is which milestone is most at risk, not which initiative is healthy._
```bash
linear-pp-cli milestones at-risk --json
```
### Personal queues
- **`blocking`** — Show issues you are blocking — sorted by downstream impact (downstream count × downstream priority).
_Reach for this every morning when you need to know which of your in-flight issues are stalling teammates downstream._
```bash
linear-pp-cli blocking --json
```
### Agent-native plumbing
- **`pp-test list`** — List Linear issues this CLI created in the current or named session, then archive them with pp-cleanup.
_Reach for this when an agent needs to clean up only the tickets it created in a session — the workspace's existing data must not be touched._
```bash
linear-pp-cli pp-test list --json
```
- **`issues create --trust-mode strict`** — Refuse mutations on Linear issues not in the local pp_created ledger when --trust-mode strict is set; works on create and any future mutation surface.
_Reach for this when running an agent against a real workspace with real data — strict mode makes accidental mutation impossible._
```bash
linear-pp-cli issues create --title "Test ticket" --team ENG --trust-mode strict
```
## Command Reference
**attachments** — Manage attachments
- `linear-pp-cli attachments <id>` — Get a single attachment
**audit-entry-types** — Manage audit-entry-types
- `linear-pp-cli audit-entry-types` — Get a single auditentrytype
**auth-resolver-responses** — Manage auth-resolver-responses
- `linear-pp-cli auth-resolver-responses` — Get a single authresolverresponse
**authentication-session-responses** — Manage authentication-session-responses
- `linear-pp-cli authentication-session-responses` — Get a single authenticationsessionresponse
**email-intake-addresses** — Manage email-intake-addresses
- `linear-pp-cli email-intake-addresses <id>` — Get a single emailintakeaddress
**favorites** — Manage favorites
- `linear-pp-cli favorites <id>` — Get a single favorite
**initiative-relations** — Manage initiative-relations
- `linear-pp-cli initiative-relations <id>` — Get a single initiativerelation
**initiative-to-projects** — Manage initiative-to-projects
- `linear-pp-cli initiative-to-projects <id>` — Get a single initiativetoproject
**initiatives** — Manage initiatives
- `linear-pp-cli initiatives <id>` — Get a single initiative
**integrations** — Manage integrations
- `linear-pp-cli integrations create` — Create a integration
- `linear-pp-cli integrations delete` — Delete a integration
**issue-priority-values** — Manage issue-priority-values
- `linear-pp-cli issue-priority-values` — Get a single issuepriorityvalue
**organizations** — Manage organizations
- `linear-pp-cli organizations` — Get a single organization
**project-labels** — Manage project-labels
- `linear-pp-cli project-labels <id>` — Get a sinRelated in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.