warpdotdev-demos

Implement a fix or feature from a GitHub, Jira, Linear, or other issue-tracker issue by fetching issue context, inspecting the current codebase, making code changes, validating them, opening a GitHub pull request, and reporting progress back to the original issue.

Post a concise software-factory status update to a Slack channel via an incoming webhook after a factory phase completes a handoff. Use when a triage decision is made, a specs PR is opened, an implementation PR is opened, or an automated review verdict is published, and the SLACK_WEBHOOK_URL secret is configured.

Repo-specific code review guidance for this repository. Only the categories declared overridable below may be specialized here; the review output schema, severity labels, safety rules, and evidence rules are defined by the review-pr skill.

Review a pull request diff and write structured feedback to review.json for the workflow to publish. Use when reviewing a checked-out PR from local artifacts like pr_diff.txt and pr_description.txt and producing machine-readable review output instead of posting directly to GitHub.

Audit a pull request diff for common security concerns (input validation, sanitization, authentication and authorization, secrets management, unsafe dependencies, and related risks) and fold findings into the same review.json produced by the base PR review. Use as a supplement to `review-pr` whenever a code PR is being reviewed.

Audit a product or tech spec pull request diff for high-level security concerns (threat surface, authentication and authorization model, trust boundaries, sensitive data handling, secrets and key management, dependency posture, and abuse or misuse cases) and fold findings into the same review.json produced by the base review. Use as a supplement to `review-pr` whenever a spec-only PR (changes limited to `specs/` or docs) is being reviewed.

Coordinate spec-driven development for a GitHub, Jira, Linear, or other issue-tracker issue moved to the Spec status (or given an equivalent label) by using write-product-spec and write-tech-spec, creating PRODUCT.md and TECH.md, opening a pull request, and routing the issue onward.

Repo-specific triage guidance for this repository. Only the categories declared overridable below may be specialized here; the core triage contract (states, output shape, guardrails) is defined by the triage skill.

Daily outer loop that reviews human reactions to automated review-pr comments, synthesizes durable organizational knowledge, and opens a PR to update the review-pr skill when the feedback is worth remembering. Use when improving code-review quality from human feedback, running a scheduled review-skill retrospective, or incorporating maintainer corrections into review guidance.

Review a pull request diff and write structured feedback to review.json for the workflow to publish. Use when reviewing a checked-out PR from local artifacts like pr_diff.txt and pr_description.txt and producing machine-readable review output instead of posting directly to GitHub.

Sets up a beginner-friendly Oz cloud software factory that automatically triages new GitHub issues, specs issues labeled ready-to-spec, and implements issues labeled ready-to-implement. Use when a user wants to install, configure, test, or understand the Cloud Factory demo in a repository of their choice.

Implement a fix or feature from a GitHub, Jira, Linear, or other issue-tracker issue by fetching issue context, inspecting the current codebase, making code changes, validating them, opening a GitHub pull request, and reporting progress back to the original issue.

Coordinate spec-driven development for a GitHub, Jira, Linear, or other issue-tracker issue marked ready-to-spec by using write-product-spec and write-tech-spec, creating PRODUCT.md and TECH.md, opening a pull request, and routing the issue onward.

Triage an incoming GitHub, Jira, Linear, or other issue-tracker issue against the current codebase and related open issues, then return a structured decision with exactly one implementation-readiness state. Use whenever the user asks to triage, classify, assess, prioritize, or label an issue for implementation readiness, especially when an issue URL, key, or number is supplied in the prompt.

Re-platform a website off a hosted provider (Squarespace, Webflow, Wix, WordPress, Shopify, etc.) into static, source-controlled code in a modern JavaScript framework that deploys to a static host like Vercel, Netlify, or Cloudflare Pages. Use when the user wants to migrate a hosted site to static code, move a site off Squarespace/Webflow/Wix/WordPress/Shopify, or asks to "replatform" a website.

Run the replatform-site skill against one or more public websites, launch the generated apps, compare original and migrated sites with browser/computer vision, measure quality plus latency/tokens/credits, diagnose general replatforming failure patterns, and improve replatform-site through evidence-backed differential iterations. Use whenever the user asks to observe, benchmark, evaluate, visually compare, tune, self-improve, or run an outer loop on the replatforming skill.

Drive parallel replatforming observations across many public websites using Oz cloud agents. Fan out one computer-use-capable cloud agent per site with replatforming-observer, gather and validate results, aggregate cross-site visual/behavioral/efficiency findings, and optionally coordinate one centralized replatform-site improvement plus parallel verification. Use whenever the user asks to run replatforming observations in parallel, benchmark many sites with Oz, orchestrate the observer skill, or gather cloud-agent migration results.

Implement a fix or feature from a GitHub, Jira, Linear, or other issue-tracker issue by fetching issue context, inspecting the current codebase, making code changes, validating them, opening a GitHub pull request, and reporting progress back to the original issue.

Triage an incoming GitHub, Jira, Linear, or other issue-tracker issue against the current codebase and related open issues, then apply exactly one implementation-readiness label. Use whenever the user asks to triage, classify, assess, prioritize, or label an issue for implementation readiness, especially when an issue URL, key, or number is supplied in the prompt.

Observe how humans responded to past automated issue triage and propose improvements to the triage-issue skill via a pull request. Use on a schedule or on demand to evolve the triage skill from real feedback.

Triage a newly opened GitHub issue into one of three buckets (ready-to-implement, needs-info, duplicate), apply the matching label, and post a triage comment requesting feedback. Use when a new issue needs triage.

Judge Death by AI GitHub Edition response issues by reading the linked scenario and producing a cinematic verdict artifact without mutating GitHub.

Moderate Death by AI GitHub Edition scenario issues for public conference safety, premise fit, and engagement, returning a structured approval result without mutating GitHub.