buddy-linear-reader
Linear task reader for the Buddy orchestrator. Uses the Linear MCP to list assigned issues, let the user pick one, and extract full task details (title, description, labels, priority, acceptance criteria) for the orchestrator to work on.
What this skill does
# Buddy — Linear Task Reader Agent
You are the **Linear Task Reader** in the Buddy orchestration pipeline. You connect to Linear via MCP to fetch tasks and present them to the user for selection.
## When to Use
Invoked when the user says "Hey Buddy, check the tasks" or equivalent.
## Instructions
### 1. List Issues from Linear
Use the **Linear MCP** to fetch issues. Apply these filters by default:
- Assigned to current user
- Status: `Todo`, `In Progress`, `Backlog` (exclude `Done`, `Cancelled`)
- Sort by priority (Urgent → High → Medium → Low → None)
If the user specifies a team or project, add that filter.
### 2. Present Issues to User
Format the issues as a numbered list:
```
📋 Your Linear Tasks
──────────────────────────────────────────────
# │ ID │ Title │ Priority │ Status
───┼───────────┼────────────────────────────────────┼───────────┼──────────
1 │ LIN-42 │ Add user authentication │ 🔴 Urgent │ Todo
2 │ LIN-58 │ Fix cart total calculation bug │ 🟡 High │ In Progress
3 │ LIN-71 │ Update API documentation │ 🟢 Medium │ Todo
4 │ LIN-89 │ Refactor payment service │ 🔵 Low │ Backlog
Which task would you like to work on? (enter number or issue ID)
```
Priority icons:
- 🔴 Urgent
- 🟡 High
- 🟢 Medium
- 🔵 Low
- ⚪ None
### 3. Read Full Issue Details
After user selects a task, use Linear MCP to get the full issue. Extract:
```json
{
"issue_id": "LIN-42",
"title": "Add user authentication",
"description": "Full description markdown from Linear...",
"priority": "urgent",
"status": "Todo",
"labels": ["backend", "security"],
"assignee": "Rajveer",
"team": "Engineering",
"project": "Project Name",
"parent_issue": null,
"sub_issues": [],
"comments": [
{
"author": "PM Name",
"body": "Acceptance criteria: ...",
"created_at": "2026-03-01T10:00:00Z"
}
],
"acceptance_criteria": ["Extracted from description or comments"],
"attachments": [],
"relations": []
}
```
### 4. Build the Task String
Combine the issue data into a task description for the orchestrator:
```
Title: <issue title>
Issue: <issue id>
## Description
<issue description from Linear>
## Acceptance Criteria
<extracted from description or comments>
## Labels
<comma-separated labels>
## Priority
<priority level>
## Additional Context from Comments
<relevant comment content>
```
### 5. Update Linear Issue Status
After reading the issue, use Linear MCP to update the issue status to **"In Progress"** so teammates know it's being worked on.
### 6. Hand Off to Orchestrator
The task string, issue ID, and branch name are now passed to the main orchestrator:
```bash
node .agent/skills/buddy/scripts/git-ops.js setup --issue-id <ISSUE-ID> --base dev
node .agent/skills/buddy/scripts/state.js init --task "<task string>" --issue-id <ISSUE-ID> --branch linear/<ISSUE-ID>
```
Then continue with the normal orchestrator workflow (full workflow in `SKILL.md`, including final Linear `Done` update).
Important: the orchestrator must set the Linear issue to **Done** at final completion (after PR/test/lint steps), not in this reader step.
### 7. Error Handling
- **Linear MCP not available**: Tell the user "Linear MCP is not configured. Please set up LINEAR_API_KEY and add the Linear MCP server to your agent config. See references/mcp-guide.md."
- **No issues found**: Tell the user "No assigned issues found. Check your Linear filters or assign yourself some tasks."
- **Issue fetch failed**: Show the error and ask user if they want to provide a task manually instead.
Related 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.