rajshah4

Launch the visible sidekick Jira-to-PR demo from a Jira webhook event. Use when an OpenHands automation receives a Jira issue labeled sidekick-v2 and needs to start the docs, logs, repo scout conversations plus the main implementation conversation without embedding launcher shell details in the automation prompt.

Turn sparse GitHub or Jira bug reports and requests into OpenSpec-style change artifacts, scoped Petstore implementation, tests, and a human-reviewable PR for the SDLC Automation Demo.

Build or adapt parent-child delegated conversation workflows for OpenHands Replicated, Agent Canvas, SDLC automation, reusable software-factory patterns, supervisor conversations, child work cells, lifecycle reports, and prompt/blueprint scaffolding. Use when replacing label-by-label automations with one orchestrating conversation that delegates bounded child conversations, or when creating a reusable delegated workflow for another repo or team.

Build cost-aware context reuse reports for the SDLC Automation Demo by loading AGENTS.md, skills, existing logs, GitHub repo search results, and prior OpenHands conversation memory before broad model work.

GitHub PR code-review guidance for the SDLC Automation Demo, layering Petstore-specific correctness, risk, testing, and supply-chain checks onto OpenHands /codereview behavior.

Read-only context scout for sparse Jira-to-PR demo tickets. Use before the SDLC story skill when Codex needs to find likely docs, logs, repo files, missing context, and confidence without editing code, opening PRs, or mutating Jira/GitHub.

Build or extend the automated test suite for GitHub PRs in the SDLC Automation Demo, including Petstore API tests, UI evidence, and deterministic QA reports.

Offline Trivy and CVSS extraction workflow for deterministic dependency auditing in OpenHands.

Lightweight guidance for combining spreadsheet and PDF inputs into a deterministic result workbook.

Deterministic workflow for combining workbook and PDF data into a validated result workbook with derived sales metrics.

Lightweight guidance for extracting quarterly financial metrics into a fixed JSON output.

Deterministic workflow for extracting quarterly financial metrics and computing derived percentages from local SEC-style inputs.

Minimal procedural guidance for auditing a dependency lockfile and writing the tutorial report format.

Structured code review covering style, readability, and security concerns with actionable feedback. Use when reviewing pull requests or merge requests to identify issues and suggest improvements.

Generate formatted changelogs from git history since the last release tag. Use when preparing release notes that categorize changes into breaking changes, features, fixes, and other sections.

Add a new CI check to the Petstore repo from a labeled GitHub issue.

Audit and safely update Petstore dependencies with a reviewable PR.

Manually expand Petstore test coverage using focused skills-based instructions.

Fix a labeled Petstore bug from a GitHub issue and open a draft PR.

Launch or describe the visible parent/child conversation workflow for foundry RTL requests. Use when an OpenHands automation receives an RTL request and needs a parent orchestrator plus read-only child scout conversations before implementation.

Use for foundry RTL tasks involving ChipCraftX RTL generation, model-route evidence, GitHub implementation issues, and handoff to EDA validation.

Use for Foundry IT requests that need model/tool routing, child automation handoff, air-gapped handling, RTL implementation, or EDA validation policy.

Use for deterministic validation of foundry RTL changes with static checks and optional EDA tools such as Verilator, Icarus Verilog, and Yosys.

Read-only context scout for foundry RTL requests. Use before implementation when Codex/OpenHands needs to gather spec, repo, toolchain, and model-route context without editing code.

Worker skill for batching PR comments, bot findings, and CI failures; classify each item, fix real issues, reply with parser-recognized wording, and push one coherent update.

Implement one story into a story branch and open a PR into the epic feature branch using the repository's story workflow.

Run Go repository quality checks and decide which checks apply before story PR readiness.

Perform a local persona review before a story PR or final PR is marked ready for human approval.

Create or update focused unit, integration, or SAM sandbox e2e tests for implemented stories.

This skill should be used when the 'ready-to-implement' label is added to an issue. It implements features by executing the task list from the spec files on the existing feature branch, and opening a draft PR to main.

This skill should be used when the 'spec-approved' label is added to an issue. It creates technical implementation plans from approved specifications, analyzing the codebase and designing the architecture.

This skill should be used when a new issue is opened and needs a functional specification. It transforms rough feature ideas into detailed spec.json documents with user stories, requirements, and acceptance criteria, while also posting clarifying questions.

This skill should be used when the 'plan-approved' label is added to an issue. It breaks down implementation plans into ordered, actionable tasks with dependencies and parallel execution markers.

This skill should be used when a PR review is submitted. It evaluates feedback, addresses legitimate concerns, responds to comments, and pushes updates to the PR branch.

Create and manage OpenHands automations - scheduled tasks that run in sandboxes. Use for cron-scheduled automations.

Parse email newsletters into individual stories. Use when structural/heuristic parsing fails and LLM extraction is needed.

Deduplication strategy for identifying when multiple newsletters cover the same story. Use when reviewing or improving dedup logic.

Run the DailyMe newsletter processing pipeline. Handles email ingestion, parsing, dedup, ranking, and optional digest delivery.

Resolve readiness probe failures when startup appears successful but health checks fail.

Diagnose and remediate stale lockfile failures that return HTTP 500 after crashes.

Handle service failures caused by missing or invalid required environment variables.

Diagnose and resolve mismatches between expected probe port and actual bind port.

Use when the user has an AI system that is already running (production, pilot, or serious testing) and wants to know why it underperforms, whether it's actually working, or whether to keep going, change course, or kill it. Triggers include "why isn't this working", "metrics are flat", "users aren't adopting it", "should we keep investing in this", or any post-launch review. For projects not yet built, use frame-use-case instead.

Use when the user wants to frame a new AI use case, decide whether to build an AI system, scope an AI project, or pressure-test a project idea before building. Triggers include "should we build this", "help me frame this AI project", "we want to use AI for X", or any new AI system ask that hasn't been built yet. For systems already running, use diagnose-use-case instead.

Conventions for authoring and updating API integration tests in this repo. Use when reading a PR diff that changes an API surface, when generating tests for a brand-new endpoint, or when running an existing pytest suite against a real HTTP API. Covers test layout, naming, the pytest+httpx pattern used here, fixtures, assertions, error-path coverage, and how to keep tests honest (real network calls — no implementation-mocking of the system under test).

Behavior-driven UI testing patterns. Covers Vitest Browser Mode (preferred) and DOM Testing Library. Use when testing any front-end application, writing UI tests, querying DOM elements, or simulating user interactions. For React-specific patterns, see the react-testing skill.

Use the OpenHands Cloud V1 API from inside OpenHands Cloud or from a launcher script when a workflow needs to create conversations, poll start tasks, fetch conversation records, or inspect events. Use for exact API mechanics, authentication details, start-task handling, and helper-script driven Cloud automation.

Run Ralph/Wiggum-style relay workflows in OpenHands Cloud where each conversation completes one bounded repo step, writes durable handoff files, proactively rolls over before context gets too large, spawns the next Cloud conversation, and stops immediately. Use for sequential repo-improvement loops that should rely on files instead of long-lived conversation memory.

Generate and maintain durable repository documentation for humans and future coding agents. Use when asked to plan, initialize, update, repair, or automate repo docs, including OpenWiki-style docs and optional GitNexus-enriched docs.