Deploy applications to Render by analyzing codebases, generating render.yaml Blueprints, and providing Dashboard deeplinks. Use when the user wants to deploy, host, publish, or set up their application on Render's cloud platform.

Audit Claude Code instruction rules in .claude/rules/ and ~/.claude/rules/: frontmatter, paths glob validity against real files, symlink load status, and day-to-day usefulness, then update rules with the user. Use for first-time rules setup, rules that apply too often or never, or periodic rules hygiene. Not for Codex .rules command-approval files.

Operate recurring Bangle.io agent follow-ups after a thread has already started. Use when the user asks to continue, check status, decide what is next, push, create or update a PR, poll CI, rebase, merge, release, run Playwright/manual UX checks, spawn or aggregate code-review subagents, run thermonuclear review, address review findings, make a plan, add a project task, or asks "we good?", "pushed?", "PR?", "did you test?", "what should I test?", or similar follow-up prompts in the Bangle repo.

Integrate an application's backend with FastClaw cloud agents over the FastClaw API. Use when a project needs to chat with one or more existing FastClaw agents (agent-scope API key), or to create, update, delete and chat with agents on demand (user-scope API key) — e.g. "connect this app to FastClaw", "call my FastClaw agent from the backend", "let each user create their own agent".

Surface recent voice memos and ideas captured from any device. Use when the user asks "what ideas did I have?", "what were my recent memos?", "what did I record while walking?", or wants to recall a captured thought.

Compare two Google Search Console page exports (current vs previous period) to flag pages whose clicks or impressions fell by a chosen threshold, with a triage hint (refresh, query shift, consolidate, prune). The 20% default is a screening heuristic, not proof of decay. Use for "/blog decay", "content decay", "QoQ decline", "refresh declining posts". Needs two GSC exports; not for diagnosing a single traffic drop live (blog-google) or rewriting posts (blog-rewrite).

Reference desk for NVIDIA Nemotron 3.5 Lightning (30B-A3B), a hybrid Mamba-Transformer MoE with MTP built from Nano 3 Base by distillation from Super 3 Base, single-stage text SFT, RLVR, MTP boosting, and W4A16 NVFP4 quantization. Use when the user asks facts about Lightning 3.5 rather than building a pipeline.

Conventions every RSpec spec in ruby-git follows, unit or integration: naming the subject in `RSpec.describe`, one `describe` per method, the spec path, testing through the public interface, `context` and `it` wording, nesting, `subject` and `let`, `allow` and `expect`, verifying doubles, error assertions, edge-case placement, observable behavior, random order, the forbidden stubbing forms, no conditional logic or declared constants in a spec, and where shared contexts live. Use when writing, reviewing, or auditing any spec under spec/.

Addresses unresolved pull request review threads and suppressed (low-confidence) Copilot review comments on the current branch, folds each fix into the existing commit that last touched the same file, force-pushes with lease, resolves the addressed threads, and requests a fresh Copilot review. Use when addressing PR feedback, resolving review comments or threads, handling comments suppressed due to low confidence, amending fixes into prior commits, or asking Copilot to re-review after changes.

Implement @data-client Managers for global/background side effects - websocket, SSE, polling, real-time updates, subscriptions, logging, analytics, metrics/timing, error reporting (Sentry), toast notifications, refetch on window focus or network reconnect, cross-tab sync (BroadcastChannel), offline persistence (localStorage/IndexedDB), auth logout on 401, middleware, intercepting Controller actions, DataProvider managers prop, redux-style action handling. Use when adding cross-cutting store behavior, reacting to dispatched actions, or handling external event streams.

Use when tasks involve creating, editing, analyzing, or formatting spreadsheets (`.xlsx`, `.csv`, `.tsv`) using Python (`openpyxl`, `pandas`), especially when formulas, references, and formatting need to be preserved and verified.

Four-step image referring-expression pipeline: turns images plus KITTI bounding-box labels into region descriptions, scene captions, grounded referring expressions, and (optionally) verified expressions via VLM distillation. Use when the user wants to generate referring-expression annotations from images with KITTI labels, build region descriptions, produce grouped grounding phrases tied to bboxes, run a double-check verification pass on grounding expressions, auto-label traffic / scene images for referring datasets, or run the image_referring_expression pipeline. Triggers include 'referring expression', 'region description', 'KITTI labels', 'spatial relationship annotation', 'auto-label image referring expression', 'image_referring_expression'.

cuOpt REST server — start server, endpoints, Python/curl client examples. Use when the user is deploying or calling the REST API.

Use this skill for MolMIM, NVIDIA's BioNeMo NIM microservice for small-molecule latent-space generation and optimization. Invoke for MolMIM, molecular embeddings, hidden states, latent decoding, sampling around a seed SMILES, CMA-ES guided molecule generation, QED or plogP optimization, hosted NVIDIA API calls, or local Docker deployment.

Sweep open (or listed) PRs with up to 100 parallel agents: security-scan outside contributors, rebase onto main when behind (push --force-with-lease), approve pending first-time-contributor CI when relevant, optionally rebase in-house PRs, and report who should review. Supports full, changed-only, behind-only, and conflict-only scopes for cheap daily runs. Use when the user runs /pr-sweep (or /pr-inbound-sweep), or asks to "sweep PRs", "sweep inbound PRs", "security-check outside PRs", "rebase outsider PRs", "rebase our PRs", "approve waiting CI on PRs", "daily PR sweep", or "prep external PRs for review".

Use when writing a pull request title or body, when about to run gh pr create, when about to git push on a branch that already has an open PR, or when the user says /pr-description, "write the PR description", or "update the PR title". Don't use for commit messages, changelogs, or review comments.

Use when writing a pull request title or body, when about to run gh pr create, when about to git push on a branch that already has an open PR, or when the user says /pr-description, "write the PR description", or "update the PR title". Don't use for commit messages, changelogs, or review comments.

Benchmark React or Next.js changes on Vercel Sandbox VMs with paired A/B statistics: react PR/commit vs base, or Next.js PR/commit vs base, measured end-to-end through the bench/render-pipeline app (rps, latency, p95; TTFB, RSS and document/Flight bytes when the Next side captures them) and, for React changes, through the react repo's flight-ssr-bench fixture (Node AND Edge web-streams paths, Fizz and Flight+Fizz). Use whenever the user asks to bench, perf test, or A/B a React PR, a react-server-dom / Flight / vendored React change, or a Next.js PR ("is this PR faster", "does this regress RSC?", "measure the perf impact of <commit>"), even if they don't say "benchmark" — any request to quantify a server-side performance difference between two revisions belongs here. Runs remotely (laptop-free), applies correctness gates before measuring, and reports boot-level confidence intervals.

Audit code for memory leaks and disposable issues. Use when reviewing event listeners, DOM handlers, lifecycle callbacks, or fixing leak reports. Covers addDisposableListener, Event.once, MutableDisposable, DisposableStore, and onWillDispose patterns.