By Harsh1210
End-to-end Jira sprint workflow for Claude Code teams with a sandbox staging gate before prod. Four skills: (1) jira-setup — guided first-time setup that walks users through API token generation, auto-discovers account ID and projects, and validates live against Jira; (2) jira-story-design — brainstorms a feature, embeds the spec in Jira, generates an implementation plan, and creates 15 self-contained subtasks (Setup → Implement ∥ Test Cases → Code Review → Fix → UI Test → Fix → Local Smoke → Architect Review → Fix → Deploy to Sandbox → Sandbox Manual Test [human] → Fix → Merge to Sandbox Branch [human] → Push to Prod → Prod Sanity); (3) jira-story-execute — autonomously walks the 15-subtask chain to Done, pausing at two human checkpoints (sandbox manual test, merge approval), with full resumability from Jira state; (4) jira-architect-review — right-sized production-readiness review (3 / 5 / 7 / 10 angles based on the diff) at subtask 7 (pre-sandbox) or any time a change needs shipping-risk assessment. The design/execute/review skills all gate on config and hand off to jira-setup automatically if any value is missing.
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Perform a right-sized enterprise architect review on a feature branch for a Jira Story — autodetects feature size from the diff and applies the matching review checklist (3 angles for minor fixes, 5 for small features, 7 for medium, all 10 for large / framework-level changes). Use whenever the user says "review this branch", "architect review", "prod readiness review", or whenever subtask 7 of the jira-sprint-workflow chain fires. The sub-dispatched reviewer scales effort to the change — a 3-line typo fix does not need a 10-angle audit, and a 3000-line framework change should not get a 2-angle rubber stamp. Output is a categorized Jira comment with pass/block per angle plus a bundled-scope decision if out-of-scope commits rode along.
First-time setup walkthrough for the jira-sprint-workflow plugin — interactively collects Jira URL, credentials, project key, owner account ID, and components; guides the user to Atlassian Cloud to generate an API token; validates each value via a live API call; and writes everything to Claude Code's pluginConfigs so the jira-story-design / jira-story-execute / jira-architect-review skills have what they need. Use whenever the user says "set up the jira plugin", "configure jira-sprint-workflow", "I just installed the plugin, what now?", "walk me through jira setup", "first-time setup", or when any of the other skills in this plugin detect missing config and hand off to you.
Design a feature end-to-end in Jira — brainstorm, write spec, write implementation plan, and create a fully-loaded set of self-contained Jira subtasks that a teammate or sub-agent can execute without any local files. Use whenever the user wants to design, plan, brainstorm, break down, flesh out, turn a Jira Task into subtasks, or prepare any Jira intake ticket for execution. Also use when the user says "let's plan this", "let's design this feature", "create the subtasks", "break this down for the team", or asks for implementation planning on a Jira task. Do not skip this skill and improvise — the workflow here enforces brainstorming, plan writing, and self-contained subtasks that the team relies on.
Execute a Jira Story that's been designed with jira-story-design — autonomously walks the 15-subtask chain (Setup → Implement ∥ Test Cases → Code Review → Fix → UI Test → Fix → Local Smoke → Architect Review → Fix → Sandbox Deploy → Sandbox Manual Test [human
This plugin requires configuration values that are prompted when the plugin is enabled. Sensitive values are stored in your system keychain.
jira_urlYour Jira Cloud base URL, e.g. https://myteam.atlassian.net
${user_config.jira_url}componentsComma-separated list of your Jira Components / product areas (e.g. 'Backend,Frontend,Infrastructure'). Create these via Jira Project Settings → Components if they don't exist.
${user_config.components}project_keyThe Jira project key where Stories and Subtasks will be created (e.g. WFR, ENG, TECH)
${user_config.project_key}jira_usernameYour Jira account email (used with the API token for Basic auth)
${user_config.jira_username}jira_api_tokenOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimYour Jira API token — generate at https://id.atlassian.com/manage-profile/security/api-tokens
${user_config.jira_api_token}plans_directoryRepo path (relative to your working copy) where implementation plans and test plans are stored. Default: docs/superpowers/plans
${user_config.plans_directory}specs_directoryRepo path where design specs are stored. Default: docs/superpowers/specs
${user_config.specs_directory}default_owner_account_idDefault assignee for parent Tasks and the two human-gate subtasks: 10 (Sandbox Manual Testing) and 12 (Merge to Sandbox Branch). Use Jira account ID, not email. Find yours at https://<your-jira>.atlassian.net/rest/api/3/myself
${user_config.default_owner_account_id}npx claudepluginhub harsh1210/jira-sprint-workflow --plugin jira-sprint-workflowTwo skills that stop Claude from re-solving the same problems. knowledge-lookup consults a one-line index in your Obsidian vault before guessing from memory. knowledge-save captures gotchas and patterns after you solve them via a fixed checklist (surprises, silent failures, fixes that took >2 attempts, new patterns). Both auto-trigger from task context — no need to remember to say 'check the memory'.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
Browser automation and end-to-end testing MCP server by Microsoft. Enables Claude to interact with web pages, take screenshots, fill forms, click elements, and perform automated browser testing workflows.