atlassian-rest
Interact with Atlassian Jira and Confluence using REST APIs — no MCP server needed. Use this skill whenever the user mentions Jira, Confluence, Atlassian, tickets, issues, sprints, backlogs, epics, stories, or any project management task that involves creating/editing/searching/transitioning Jira issues, writing or reading Confluence pages, generating status reports, triaging bugs, converting specs to backlogs, capturing tasks from meeting notes, searching company knowledge, syncing local BMAD documents with Jira or Confluence, pushing docs to Jira, pulling from Jira, linking documents to tickets, downloading Confluence spaces to local markdown, or converting between Confluence storage format and markdown. Also trigger when the user says things like "move that ticket to done", "what's the status of PROJ-123", "create a bug for X", "search our wiki for Y", "file a ticket", "check for duplicates", "write a status update", "break this spec into stories", "sync this doc", "push to jira", "pull from jira", "sync to confluence", "link this to jira", "sync my epics", "download confluence pages", "sync confluence space", "convert confluence to markdown", or "pull docs from confluence". If there is even a chance the user wants to interact with Jira or Confluence, use this skill.
What this skill does
# Atlassian REST API Skill Portable Jira & Confluence integration via REST APIs. Works in any agent environment with Node.js 18+ — zero dependencies, no MCP server required. ## First-Use Setup `<skill-path>` throughout this document refers to the directory where this skill is installed. Resolve it from the skill invocation context (e.g., the path shown by `claude plugin list` or the skill's directory in `.claude/plugins/`). Before any operation, verify the user has credentials configured. Run: ```bash node <skill-path>/scripts/setup.mjs ``` If it fails, guide the user through the setup — the script prints step-by-step instructions. ### Required Environment Variables | Variable | Description | Example | |----------|-------------|---------| | `ATLASSIAN_API_TOKEN` | API token | *(generated at Atlassian)* | | `ATLASSIAN_EMAIL` | Account email | `[email protected]` | | `ATLASSIAN_DOMAIN` | Atlassian site domain | `company.atlassian.net` | --- ## How to Use This Skill When the user asks you to do something with Jira or Confluence, follow these principles: 1. **Resolve ambiguity first.** If the user says "create a ticket" but hasn't specified a project, run `node <skill-path>/scripts/jira.mjs projects` to list available projects, then ask which one. Same for issue types — run `node <skill-path>/scripts/jira.mjs issue-types <projectKey>` if unsure. 2. **Confirm before mutating.** Before creating issues, transitioning tickets, or publishing Confluence pages, show the user what you're about to do and get confirmation. Read operations (search, get, list) don't need confirmation. 3. **Never delete.** This skill does not support delete operations (issues, pages, attachments, boards, projects, accounts, etc.). If the user asks to delete something, direct them to the Atlassian web UI. This restriction is intentional and must not be bypassed. 4. **Compose operations naturally.** Many user requests require multiple script calls. For example, "assign PROJ-123 to Sarah" requires: (a) `lookup-user "Sarah"` to get the account ID, then (b) `edit PROJ-123 --assignee <accountId>`. 5. **Prefer sync.mjs for document-based operations.** When creating Jira issues from a local markdown file (story docs, specs, epics), use `sync.mjs` instead of raw `jira.mjs create` — it handles field mapping, link tracking, and sync state automatically. See the Document Sync Operations section below for details. Only use `jira.mjs create` for ad-hoc issues not backed by a local document. 6. **Use workflows for complex tasks.** If the user's request matches one of the workflows below, read the corresponding file and follow its step-by-step process. 7. **Read reference docs when needed.** Before writing JQL/CQL queries, consult `references/query-languages.md`. Before creating tickets, consult `references/ticket-writing-guide.md`. The reference docs exist to help you produce high-quality output — use them. ### Passing Long Content to Scripts For descriptions, comments, or page bodies longer than ~200 characters or containing special characters (backticks, quotes, `$`, newlines), **write the content to a temp file** and use the file-based flag: | Inline Flag | File Flag | Commands | |-------------|-----------|----------| | `--description "text"` | `--description-file /tmp/desc.md` | jira create, jira edit | | `<body>` (positional) | `--body-file /tmp/body.md` | jira comment, confluence comment | | `--body "text"` | `--body-file /tmp/body.md` | confluence create-page, update-page | | `--comment "text"` | `--comment-file /tmp/comment.md` | jira worklog | Write **plain markdown** to the file — scripts handle conversion to ADF (Jira) or storage format (Confluence) automatically. Prefer file-based input to avoid shell escaping issues. --- ## Jira Operations Script: `node <skill-path>/scripts/jira.mjs <command> [args]` ### Search Issues ```bash jira.mjs search 'project = PROJ AND status = "In Progress"' --max 20 ``` ### Get Issue Details ```bash jira.mjs get PROJ-123 jira.mjs get PROJ-123 --fields summary,status,assignee ``` ### Create Issue ```bash jira.mjs create --project PROJ --type Task --summary "Implement feature X" \ --description "Details here" --priority High --assignee <accountId> \ --labels "backend,urgent" --components "API,Auth" jira.mjs create --project PROJ --type Story --summary "User login" --parent PROJ-100 # For long descriptions, use a file: jira.mjs create --project PROJ --type Task --summary "Feature X" \ --description-file /tmp/desc.md --priority High ``` When creating child stories under an Epic, include `--priority Medium` unless the user specifies a different priority. ### Edit Issue ```bash jira.mjs edit PROJ-123 --summary "Updated title" --priority Medium jira.mjs edit PROJ-123 --labels "backend,v2" --components "API" # For long descriptions, use a file: jira.mjs edit PROJ-123 --description-file /tmp/desc.md ``` ### Comments ```bash jira.mjs comment PROJ-123 "Fixed in PR #456" # For long comments, use a file: jira.mjs comment PROJ-123 --body-file /tmp/comment.md ``` ### Transitions (move ticket status) ```bash jira.mjs transitions PROJ-123 # List available transitions first jira.mjs transition PROJ-123 31 # Then transition by ID ``` Always list transitions first to get the correct ID — don't guess. ### Projects & Issue Types ```bash jira.mjs projects # List all visible projects jira.mjs issue-types PROJ # List issue types for a project ``` ### Issue Links ```bash jira.mjs link-types # List available link types first jira.mjs link PROJ-1 PROJ-2 --type "relates to" ``` ### User Lookup ```bash jira.mjs lookup-user "john" # Returns account ID needed for --assignee ``` ### Worklog ```bash jira.mjs worklog PROJ-123 --time 2h --comment "Code review" ``` --- ## Document Sync Operations Script: `node <skill-path>/scripts/sync.mjs <command> [args]` When creating Jira/Confluence items from local markdown documents, prefer sync.mjs over raw jira.mjs/confluence.mjs — it auto-updates the source document with links and maintains sync state. ### Setup Field Mapping (first time per doc type) ```bash sync.mjs setup-mapping --type story --sample PROJ-200 # Auto-detect fields from existing ticket sync.mjs setup-mapping --type epic --sample PROJ-100 # Creates memory/jira-epic-field-mapping.json ``` Field mappings are stored in `<skill-path>/memory/` and define how markdown sections map to Jira fields. See `references/sync-mapping-guide.md` for the full schema. ### Link & Create from Document ```bash sync.mjs link <file> --type story --project PROJ --create # Create Jira issue + update doc sync.mjs link <file> --type epic --project PROJ --create # Create epic + child stories sync.mjs link <file> --type story --ticket PROJ-123 # Link to existing ticket ``` ### Push/Pull Changes ```bash sync.mjs push <file> # Push local changes to Jira/Confluence sync.mjs push <file> --delete-orphans # Push + prompt to delete orphaned Sub-* subtasks sync.mjs pull <file> # Pull remote changes to local sync.mjs diff <file> # Show per-section diff sync.mjs status <file> # Show sync status ``` When `push` reports orphaned subtasks (sections removed from local doc), ask the user if they want to delete them, then run with `--delete-orphans`. Only `Sub-*` issue types can be deleted — parent issues are skipped. ### Custom Instructions in Mapping Config The field mapping JSON (`memory/jira-<docType>-field-mapping.json`) supports an `instructions` field for additional agent guidance: ```json { "instructions": "Always set priority to High. Add label 'team-alpha'. Use Sub-Imp type for child items." } ``` When present, instructions are printed to stdout during `push` and `link` operations so the calling agent can follow them. ### Batch Operations ```bash sync.mjs batch # Scan all linked
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.