Results for “pr-review”

Run the full autonomous shipping pipeline end-to-end, hands-off with no check-ins: plan, implement, review and fix, commit, push a branch, open a PR, and watch CI to green. Use only when the user explicitly asks to build or ship something autonomously all the way to an open PR, or invokes lfg directly — it pushes and opens a PR without stopping. Not for in-the-loop work where the user reviews each step: use ce-plan to plan, ce-work to implement a plan, ce-debug to fix a bug, or ce-commit-push-pr to commit and open a PR for existing changes.

Walks a person through code changes one step at a time in conversation, starting at the entry point and following the flow that changes, showing a small chunk per step and explaining it in plain language. Defaults to the current branch's changes, and walks the code from the perspective of any context provided instead — a file, directory, symbol, pull request, plan, or ticket. Use when someone wants to be walked through, taught, paced through, or shown around code or a branch step by step, or to learn how a change works before reviewing or extending it. Stops after every step and waits, so the learner sets the pace. Paces through code that already exists and builds nothing — to build new work while being paced through it, use pairing. Does not produce a written overview to read alone — use code-overview. Does not review code quality — use code-review. Does not diagnose bugs — use investigate.

Explains MariaDB Connector/Node.js specifics: Promise vs Callback API, placeholders, BigInt handling, batch inserts, query streams, pooling, transactions, and prepared statements, for writing or reviewing Node.js code that uses the `mariadb` package.

Manage project learnings. Review, search, prune, and export what gstack has learned across sessions. Use when asked to "what have we learned", "show learnings", "prune stale learnings", or "export learnings". Proactively suggest when the user asks about past patterns or wonders "didn't we fix this before?"

Sweeps a codebase or UI for places that would genuinely benefit from motion, applying a strict gate to reject over-animation, and proposes precise animation recipes without implementing them.

Design and apply Azure role-based access control with least privilege at the right scope. Use this skill when users ask about permissions, role assignments, access errors, or governance. Covers built-in roles, custom roles, managed identities, PIM, and access reviews per Well-Architected principles.

Use when making a forward-looking claim with a checkable outcome (reply within 24h, error rate will drop, this skill will see more use) — record to state/predictions.jsonl with a review horizon so reflection can grade you later. Closes the in-the-moment double-loop.

Runs a three-layer verification pipeline on AI-generated output: extracts verifiable claims, finds supporting or contradicting sources via web search, and produces a structured verification report with source links for human review.

Covers MariaDB-specific CREATE TRIGGER syntax and behavior, including OR REPLACE, DEFINER, multiple trigger events, FOLLOWS/PRECEDES ordering, OLD/NEW rules, and restrictions. Use when writing, generating, or reviewing CREATE TRIGGER statements for MariaDB.

Use for creating, splitting, reviewing, or debugging GitHub Copilot custom instructions in Visual Studio Code, including .github/copilot-instructions.md, .github/instructions/*.instructions.md, and AGENTS.md. Do not use for slash commands, Agent Skills, custom agents, hooks, or ordinary project documentation.

API service-layer patterns — axios/fetch client with interceptors, domain-scoped service objects (UserService, ProductService), auth-token refresh, request cancellation, and error normalisation. Use when adding or reviewing HTTP call sites, organising services under api/ or services/, or centralising cross-cutting request concerns.

Use when a research implementation plan exists in docs/superpapers/plans/ and the user is ready to execute it — collecting data, running analysis, producing outputs, writing the paper. Orchestrates task execution with replication-driven verification and two-stage review at phase boundaries.

Find over-permissive RBAC roles and service-account token abuse paths in Kubernetes using kubectl auth can-i, rbac-police, kubectl-who-can, and rakkess during authorized cluster security reviews.

Generates a post-release blameless retrospective from project signals — synthesizing DORA-like metrics, WorkItem outcomes, session timeline, and drift deltas into a structured Artifact + LogEntry. Use at the end of a release cycle when asked to run a retro, "post-release review", "retrospective", or "post-mortem".

Create publication-quality scientific diagrams using Nano Banana Pro AI with smart iterative refinement. Uses Gemini 3 Pro for quality review. Only regenerates if quality is below threshold for your document type. Specialized in neural network architectures, system diagrams, flowcharts, biological pathways, and complex scientific visualizations.

Use when a paper is complete or near-complete and a holistic pre-submission audit is needed. Cross-cuts text, code, tables, figures, results, citations, and reproducibility in a single pass and produces a persistent audit report. Works standalone on papers written outside the plugin.

Handles git and GitHub operations using the gh CLI, triggered by any github.com URL. Covers creating and reviewing PRs, watching CI checks, interactive rebasing, branch cleanup, submodule management, and repository archaeology.

General GitHub workflow — branching, commits, pull requests, code review, secrets hygiene, submodules, and git worktrees. Use when the user wants to save changes, push to GitHub, open a PR, work with a submodule, set up a worktree, or perform any git/GitHub operation.

Use for creating, reviewing, debugging, or testing GitHub Copilot agent hooks in Visual Studio Code, including .github/hooks JSON, lifecycle events, Python handlers, permissions, and structured stdin/stdout. Do not use for advisory instructions, one-off commands, CI workflows, or shell profile hooks.

Guides Cloudflare One Zero Trust and SASE work across Access, Gateway, WARP, Tunnel, Cloudflare WAN, DLP, CASB, device posture, and identity. Use when designing, configuring, troubleshooting, or reviewing Cloudflare One deployments. Retrieval-first: use current Cloudflare docs/API schemas instead of embedded product docs.

Author slide decks in Markdown using Marp, with native support for Mermaid diagrams and embedded HTML (compatible with the architecture/infocard/infographic skills). Export to PowerPoint (.pptx), PDF, and HTML via marp-cli. Best for engineering presentations, architecture reviews, and recurring decks regenerated from data.

Call a DeepSeek-backed OpenCode agent as a separate critique, writing, or revision agent from Codex. Use when Codex needs to delegate adversarial research critique, novelty skepticism, method review, manuscript prose, LaTeX section drafting, academic text revision, or paper-writing feedback loops to DeepSeek.

Reviews a product document (PRD, spec, design brief) BEFORE implementation to surface holes — undefined edge cases, missing states, policy gaps — by attacking what the document is SILENT about (things unwritten, and things written only for the happy path). Acts as a strict "sign-off manager," ruling Approve / Conditional / Reject and producing a polite, forwardable question list. Works for planners/PMs (self-review before sharing), engineers (blocking questions before coding), and designers (screen states with no mockup). Use whenever the user wants a spec/PRD/plan/brief checked for readiness or gaps, or says "review this spec", "find holes in this PRD", "poke holes in this", "is this plan good to build?", "can I start implementing this?", "what states/edge cases am I missing?", "what should I ask the PM before coding?", "run devil", or pastes/links a planning document and asks whether it's ready to act on. Do NOT use it to: write or draft a new spec, summarize or translate a document, estimate/break down tic

Create, update, and review Terraform provider documentation for Terraform Registry using HashiCorp-recommended patterns, tfplugindocs templates, and schema descriptions. Use when adding or changing provider configuration, resources, data sources, ephemeral resources, list resources, functions, or guides; when validating generated docs; and when troubleshooting missing or incorrect Registry documentation.

Use for creating, reviewing, debugging, or testing dbt SQL projects involving models, sources, ref, tests, macros, materializations, incremental models, snapshots, seeds, selectors, compiled SQL, or dbt artifacts. Do not use for generic SQL with no dbt graph, warehouse administration, semantic-layer product configuration, or orchestration outside dbt.

Write and refine user stories using INVEST criteria, the 'As a X, I want Y, so that Z' format, Gherkin acceptance criteria, definition of ready, anti-patterns, and a review checklist.

Use when auditing an ACL submission before an ACL Rolling Review cycle deadline, covering long/short paper page budgets, the mandatory Limitations section, Responsible NLP checklist, anonymized PDFs and supplements, preprint declarations, dual-submission rules, resubmission linking, and ARR desk-reject triggers on OpenReview.

Operate Heroku Key-Value Store with a read-only-first workflow. Use when the agent needs to inspect Redis-backed state, review credentials, promote a store, tune maxmemory or timeout policies, configure keyspace notifications, or reason about Heroku Key-Value Store operational guardrails.

Summarizes U.S. commercial lease agreements into structured transactional abstracts. Use when asked for a commercial lease summary, lease abstract, key lease terms, rent schedule review, default/termination analysis, or lease handoff. Produces party-to-obligation mappings, financial mechanics, risk flags, and critical date calendars.

Composite skill — full project health check across testing, config, hooks, performance, security, MCP, and plugins. Runs the audit skills in parallel and reconciles into one severity-ranked report with prioritized remediation plan. Use weekly per active project, before major releases, or as part of quarterly tech-debt review.

Produce a plain-language manual test plan from the context supplied to it — an executive summary, a high-level list of named tests, and a detail section per test with the steps a person follows by hand and the outcomes they should expect. Use when you want to create, draft, generate, or outline a manual test plan, manual QA steps, hands-on verification steps, or an acceptance walkthrough for a feature, change, branch, plan, or PR. When the plan holds more than five tests and at least two natural categories emerge, both the test list and the detail sections are organized under plain-language categories. When nothing in the supplied context can be manually tested, it says so and asks for more context instead of producing a document. Does not analyze code for automated test coverage gaps — use automated-test-planning. Does not write test code — use tdd. Does not review code quality — use code-review. Does not stress-test an existing plan — use iterative-plan-review.

Diagnoses structural problems in an existing test suite—brittleness, mock overuse, and other decay risks—drawing on twelve classic engineering books including xUnit Test Patterns and Working Effectively with Legacy Code.

Explains MariaDB Connector/Python's DB API 2.0 behavior, including qmark placeholders, autocommit, prepared statements, buffered cursors, connection pooling, and error handling, for writing and reviewing Python code that uses the mariadb module.

Manage Heroku Connect sync operations between Salesforce and Heroku Postgres. Use when the agent needs to provision Heroku Connect, install or inspect the Heroku Connect CLI plugin, review mappings, import or export config, diagnose sync failures, or reason about Heroku Connect API limits and operational guardrails.

Plan and execute multi-channel marketing campaigns from audience research through positioning, copywriting, and review. Orchestrates landing pages, email sequences, social posts, video scripts, ad copy, and content calendars for product launches.

Classifies a repository into one of six archetypes and installs a curated bundle of agent skills covering build, test, review, deploy, and docs, with a user-visible manifest and a recorded stack file.