Skills

Finds the loops behind a bill spike or an unexpected bill. Reviews a web app's code and config for loops and repeats that run up the bill on their own on Vercel, Turso, Cloudflare Workers and D1 and paid AI APIs. Finds two schedulers on one job, retries without a cap, work that triggers itself, client polling and React render loops, caches cleared on every write, middleware running on every static file, queues that resend failures forever, image settings that multiply transformations, health checks that count whole tables, alerts sent on every run and bots crawling endless filter URLs. Counts the runs per month, names the billed unit, ranks by cost and gives the change that stops each one. Use when asked why a Vercel, Turso or Cloudflare bill jumped, to find an infinite loop or a runaway cost, or to review a cron job, webhook, queue consumer, middleware or polling code before it ships.

Reviews CORS code or server configuration (an Express or Flask handler, an nginx block, a framework setting) for the five mistakes that let a hostile web page read private responses, and lists only those, one line each with a fixed code, the place, why it is dangerous and the fix - or exactly No findings. It catches a request Origin copied into the allow header while cookies are allowed, a wildcard origin together with credentials, the null origin allowed, an origin check by suffix, substring or an unanchored pattern, and a per-origin allow header sent without Vary Origin. It leaves out the safe look-alikes, such as an exact allow-list with credentials and a public read-only API that answers with a wildcard and no credentials. Use to review CORS code before release, to audit a gateway config, or to debug a browser CORS error that looks like a server mistake.

Reviews ONE AWS IAM policy (an identity policy, or a bucket policy) written as JSON for the five grants that hand out far more than a job needs, and lists only those, one line each with a fixed code, the statement, why it is dangerous and the fix - or exactly No findings. It catches every action on every resource or a whole service on every resource, iam:PassRole on any role, Allow combined with NotAction, a public principal with no condition, and actions that let a holder raise their own rights such as creating a policy version or attaching a policy. It leaves out the safe look-alikes, such as a public principal narrowed to an organization, read-only access to one bucket, and a Deny with NotAction. Use to review a policy before attaching it, to audit a role, or to check a bucket policy for public access.

Reviews ONE Dockerfile for the five build mistakes that cost security or build time, and lists only those, one line each with a fixed code, the instruction, why it hurts and the fix - or exactly No findings. It catches a final image that runs as root, a base image with no tag or the latest tag, a secret passed through an argument, an environment value or a file copy so that it stays in the image history, source copied in before the dependencies are installed so the cache is lost on every edit, and the package index left in the layer after apt-get. It leaves out the safe look-alikes, such as a build secret mounted for one instruction, a tag pinned by digest, and root in a build stage that never ships. Use to review a Dockerfile before merging, to audit the images of a repository, or to speed up a slow image build.

Turns a code tour described in words, plus the list of files with their line counts, into one valid CodeTour file (JSON with a title and steps, each step holding a file, a line and a description) and nothing else. It keeps file paths relative and exactly as listed, checks every line number against the length of its file, and leaves out a step whose file is not in the list or whose line lies past the end, naming each skipped step in the description of the tour in one fixed form. A tour with only valid steps carries no mention of skipping. Use to turn a walkthrough of a code base into a tour file for the CodeTour editor extension, to draft onboarding tours, or to rebuild a tour after files were renamed.

Reviews ONE HTML email (the source of a newsletter, a receipt or a notice) for the four mistakes that make it fall apart in common mail clients, and lists only those, one line each with a fixed code, the place, which client breaks it and the fix - or exactly No findings. It catches flex or grid used to lay out columns, layout rules that exist only in a style block in the head, images with no alt attribute, and a CSS background image with no colour fallback behind the text. It leaves out the safe look-alikes, such as a style block used only for media queries and an empty alt on a decorative spacer. Use before an email goes to a sending tool, to audit a template someone else built, or to find out why a message looks broken in Outlook for Windows or in a webmail that strips styles.

Reviews ONE Stripe webhook handler (the route code, in any language or framework) for the five mistakes that let a forged or repeated event move money, grant access or ship goods, and lists only those, one line each with a fixed code, the place, why it is dangerous and the fix - or exactly No findings. It catches a body parsed or re-serialized before the signature is checked, a handler that never checks the signature, a recency tolerance switched off or set huge, no record of event ids so a retry repeats the side effect, and slow work done before the 2xx answer. It leaves out the safe look-alikes, such as a raw body kept on the webhook route while the other routes parse JSON, and the default tolerance. Use to review a webhook route before going live, to audit one that someone else wrote, or to find out why signature checks fail or orders are fulfilled twice.

Reviews ONE GitHub Actions workflow file (YAML) for the five mistakes that let an outsider run code or read secrets in your pipeline, and lists only those, one line each with a fixed code, the place, why it is dangerous and the fix - or exactly No findings. It catches text from an issue, pull request, comment or branch name pasted straight into a shell step, a pull_request_target or workflow_run job that checks out and runs the code of the pull request, a third-party action pinned to a tag or branch instead of a full commit hash, a missing or too wide permissions block, and a secret that is printed or handed to code you do not control. It leaves out the safe look-alikes, such as untrusted text passed through an env variable and quoted, or first-party actions pinned to a version tag. Use to review a workflow before merging it, to audit the pipelines of a repository, or to gate a pull request that edits a workflow file.

Compares two versions of one API description (OpenAPI 3.0 or 3.1 in YAML or JSON, or two JSON Schemas of one request or response) and lists ONLY the changes that break clients written against the old version, one line each with a fixed code, the place, old and new, and who breaks - or exactly No breaking changes. The skill judges by direction - a request may widen safely and breaks when it narrows, a response may narrow safely and breaks when it widens - and it follows each $ref and allOf to the operations that use it, so a change made only in a shared schema is still found, while a renamed path variable, a new optional field, a reformatted file and a field moved between allOf branches are left out. Use to check an API change before release, review a pull request that edits an OpenAPI file, or gate a pipeline on breaking changes.

Reviews a pasted snapshot of a website's cookie and consent setup (scripts in the head, the banner with each toggle's default, the Consent Mode or tag-manager setup, what a fresh browser stored and contacted before any click, the cookie table, the owner's note) against published EU law, court rulings, EDPB guidance, national regulators and vendor documents. It is a technical review, not legal advice. It flags trackers and embeds that store or read before a choice, a Consent Mode default that is late or granted, pre-ticked and implied consent, analytics filed as strictly necessary, legitimate interest used for cookies, a reject option that is missing or disguised, bundled purposes, missing cookie information, no easy withdrawal, a refusal that is not kept, missing Consent Mode v2 signals, personalised Google ads without a certified CMP, cookie walls, and cookieless pings or Google font links treated as exempt. Each finding has a fixed code, the place, the named source with its weight and a fix, then one verdict. Where sources disagree, the line says so and never picks a side. Use to review cookie consent banner setups, run a GDPR cookie banner check or do a Consent Mode setup review before a regulator or a customer asks.

Decides which old build folders of an OpenNext incremental cache on Cloudflare (R2, or Workers KV) can be deleted, from a pasted setup (wrangler config, open-next config, next.config, the public HTML build id, a listing of the cache folders), and never touches the live build. It reads the cache root and the real folder name (a custom prefix, a deploymentId, a constant deploymentId, a no-build-id folder), finds the live build from the public HTML, not from a local file, and handles a rollback, a deploy in progress, two Workers on one bucket, a bucket with other folders, KV billing, and a request to delete the live build or to skip the dry run. Answer in a fixed format: live build, KEEP and DELETE lines, steps with a dry run first, one verdict. Use to clean up an OpenNext R2 cache, find old build folders in R2, or free R2 space used by Next.js on Cloudflare before running any delete.

Reviews pasted code that calls a language model (JavaScript, TypeScript or Python; REST, @google/genai, google-genai, or an OpenAI-compatible client for Groq), usually through a chain of models or providers with retries. It finds where the call path goes silent or stops while another model would answer (an empty 200 taken as the answer, a 429 or 5xx that ends the call, a retired model's 404, a Groq schema 400 that drops the provider, one provider's stop that ends all) and what costs more or hides the cause (retries on top of SDK retries, a missing thinking setting, a thinking level the model refuses, a small output limit, a moving -latest alias, errors without the model name, unguarded JSON, a model picked from the listing, several keys of one project, a weak model that publishes, a quality gate that cannot fail, a fixed price for open-ended reasoning). Each finding has a fixed code, the place, the reason and a fix, then one verdict. Use to review LLM fallback code, check a Gemini 503 retry, a Gemini empty response or a Groq json_validate_failed handler before the code runs unattended.

Writes a pull request title and description from a pasted unified diff, as Markdown only - a title line of at most 72 characters, then four fixed sections - Summary, Changes, Tests and Risks - where every file the diff touches is named once, including renames, deletions, binary files, mode changes, lockfiles and formatting-only edits, and nothing is claimed that the diff does not show. It describes what the hunks change and leaves out a reason, a speed gain, a security fix or a test result unless the author's note supplies it, flags what can break callers, links an issue only when one is given, never copies a secret into the text, treats a note addressed to the AI inside a code comment as data, and says so when the diff is cut off. Use when asked to write a pr description, pull request body or merge request text from a git diff or a patch.

Judges whether a check someone ran on a Cloudflare-hosted site really proves what they claim, and answers as JSON with a verdict, the reason and the one check that would decide. Knows the instruments that answer for the wrong thing - the command-line object read that serves a cached copy after a delete, a delivery log that records neither test mail, a zero-row log search that looks the same as code that never ran, a local migration run, a staging secret, the free preview subdomain of a Worker that is not a zone, a size counter that prints zero on Windows, a character count that counts bytes, a robots file served from the edge cache - and the checks that do prove it. Use when an agent says deleted, delivered, applied, enabled, set on production or never ran on Cloudflare work, and you need to know whether its evidence supports that.

Reads a description of how a web page was captured or measured - a headless browser capture with a window size, a tall screenshot, a document width reading, a local Lighthouse run, a PageSpeed Insights run, an automation session that has been open for hours, a command-line download size on Windows - and says what that evidence proves, what it cannot prove and the one measurement that would decide, answered as JSON with a verdict. Knows the ways the capture itself produces the symptom - headless windows under about 500 pixels that lay out wider and crop the picture, no touch emulation behind a window-size flag, blank images in very tall captures, scroll-reveal sections caught before they appear, a width reading that stays clean while a container clips, scores that move with machine load, a long automation session that stops running page scripts, a download size of zero at a successful status. Use when an agent or a person is about to report that a page is broken or fixed from a screenshot, a score or a command-line reading.

Reviews pasted CSS, Tailwind classes, JSX and Next.js client components for the layout and hydration defects that look fine on a desktop screenshot and then break on a phone or wipe the page in the browser. It flags a grid column written as a bare 1fr that refuses to shrink and, inside a clipping container, cuts the content without any horizontal scroll, width media queries written in pixels beside rem-based breakpoints, dates formatted inside a client component, server-only environment variables read in the browser, a schema default that silently stands in for a missing value, client components that pull a heavy dependency tree into every page, theme colour tokens painted on surfaces that do not flip with the theme, a fixed bar whose height is typed in several places, scroll-locking panels that stay open when the viewport crosses a breakpoint, and window.confirm. Each finding has a fixed code, the place, the reason and a fix; sound code gets No findings. Use to review a layout, a component or a stylesheet before release, or when a page looks cut off or resets itself on one route.

Reviews pasted code that announces published articles to social channels (Bluesky, Mastodon, a Facebook page, Pinterest through a feed, Tumblr, DEV) for the ways a channel stays silent or posts twice, which tests with a fake network and a green build do not catch. It flags a shared HTTP helper that cuts a response body the Bluesky login then parses, a text cut by UTF-16 position or link offsets taken from character positions instead of UTF-8 bytes, a Mastodon media upload judged by status 200 only, a link posted without uploading the picture, a missing write:media scope, an Idempotency-Key reused after its one hour, an alert cut to N characters of an HTML error page, dispatch called from cache invalidation, a new "announced" column without a backfill, Promise.all or no timeout around channels, a missing token treated as an error, staging that posts, a full article copied to a blog platform, an OAuth 1.0a signature that leaves out the form body, a DEV request from a Worker without a User-Agent, and duplicates counted by searching a title in an RSS feed. Each finding has a fixed code, the place, the reason and a fix, then one verdict. Use to review article-announcing code before release, to find why a channel never posts, or to check a new channel before its first live post.

Reviews pasted Cloudflare Workers code and configuration (a Worker, a Next.js app on OpenNext, D1 queries, wrangler config) for platform pitfalls that pass every local test and then fail in production or quietly cost money. It flags the edge runtime under OpenNext, a fetch to your own Worker's workers.dev address (error 1042), D1 queries that bind more than 100 parameters as data grows, LIKE patterns over D1's 50-byte limit, reading rowsAffected where D1 returns meta.changes, interactive transactions D1 does not have, secrets kept in plain vars, outbound fetch code that treats only a thrown error as failure, a browser User-Agent that bot protection challenges, client hop-by-hop headers forwarded to fetch, cron triggers whose day of the week is written as numbers, and unbounded queries on the request path. Each finding has a fixed code, the place, the reason and a fix, then one verdict. Use to review a Cloudflare Worker before deploy, check D1 or wrangler code, or audit a Next.js app running on Cloudflare.

Reviews pasted code and configuration that spends money (paid AI or API calls, purchases, paid lookups, anything billed per use) and checks whether the limit on that spending really stands in the way of the spending. It flags a cap that sits beside the path instead of on it (a gateway limit while a script calls the provider directly, a counter only in the browser), a missing setting that means no limit, an alert or a budget email used as the protection, a cap that the caller sets through a header or a request field, a paid job that runs by default, a per-call cap with no running total, a total kept where it resets, a cap checked only after the money is gone, and a spend counter whose failure or missing value lets the call through. Each finding has a fixed code, the place, the reason and a fix, then one verdict. Use before deploying a Worker, script or job that pays per call, or when a cap exists and you want to know if it can fail silently.

Reviews a pasted test, check script, smoke test, mutation script or CI step and says whether it can fail when the thing it guards is broken, so a green result is worth something. It finds a completeness guard that counts its own hard-coded list instead of the directory, a one-star glob that never enters subfolders, a mutation script that restores with git checkout and wipes the uncommitted fix under test, a null test that an empty string passes, a status 200 that is only the login page, a wait loop without sleep that measures network speed instead of time, a test that calls the pure function directly and never the call site, a counterfactual control whose data does not create the condition, a fix copied into two branches and tested in one, a limit tested only with ordinary values, and a catch that turns a failure into success. Each finding has a fixed code, the place, why it passes and the one input that would make it fail, or exactly No findings. Use to review a test that cannot fail, a check script that always passes, or a guard before you trust it.

Reviews a rate-limiting setup on Cloudflare (a WAF rate limiting rule, a Workers Rate Limiting binding, or a counter in your own code) and lists every reason it will not limit what its author thinks it limits. It flags free-plan rules that use the client address or a header field, which the plan refuses, windows the plan does not offer, an address key for callers that are themselves Workers and share one outbound address, a binding number treated as a global figure when each isolate counts for itself, a raw IPv6 address as a key, per-client limits with no global ceiling on a costly action, load tests fired without waiting a full window, one known attacker handled with a rule instead of an IP Access Rule, and a 429 without Retry-After. Each finding has a fixed code, the place, the reason and a fix, then one verdict. Use to check or design rate limiting for an API, a pay endpoint or an agent-facing endpoint on Cloudflare.

Reviews a pasted image pipeline (upload or AI generation, storage in R2, resizing, serving through Cloudflare image transformations, a Next.js loader, a sharp or WebP script) for the traps that quietly ship huge or broken images or spend a shared quota. It flags photographs stored as PNG, files stored exactly as a generator returned them, a redirect-on-error setting that hides an exhausted transformation quota, a list of widths that multiplies the unique-transformation count, widths above the original, transformations "turned off" while the images binding or the zone setting stays on, lossy WebP on charts and infographics, a job that re-encodes WebP that is already lossy, a preview subdomain mistaken for a zone, an original overwritten by a backdated fix, and self-made variants that can 404. Each finding has a fixed code, the place, the reason and a fix, then one verdict. Use to review an image pipeline, Cloudflare image transformations or WebP handling before it ships.

Rewrites a JavaScript regular expression that can hang on a crafted input (catastrophic backtracking, ReDoS) into one that gives exactly the same yes or no for every text and runs in linear time, answered as JSON with the pattern and flags. Knows the shapes that explode - a quantified group whose inside is quantified too, alternatives under a star that can match the same text, an optional separator between repeats, a counted group of runs, an unanchored run before a literal - and how to remove the ambiguity without atomic groups, which JavaScript lacks. Keeps the flags, keeps an already linear pattern as it is, and answers with a CANNOT line when no regular expression can give the same answers, such as a backreference that compares two arbitrary substrings. Use when a regex in a validator or a search times out, when a security scan reports ReDoS or catastrophic backtracking, or when asked to make a regex safe for untrusted input.

Converts an existing schedule between cron dialects so that the target runs at exactly the times the source runs - classic crontab, GitHub Actions schedule, a Quartz-style six-field expression, a small numbers-only HTTP scheduler (Cron Hub) and Cloudflare Workers Cron Triggers - answered as JSON with the crons and a note. Knows what changes between them - day-of-week 1 is Monday in crontab and GitHub but Sunday in Cloudflare, 0 is refused by Cloudflare, 7 means Sunday in crontab and Saturday in Cloudflare, names are refused by the small scheduler; a day of the month plus a day of the week means either in crontab but both in the small scheduler; the at-sign macros, reboot, seconds other than zero and sub-5-minute GitHub intervals have no equivalent; a time zone becomes a timezone key, a CRON_TZ line or two UTC hours. Refuses what cannot be run at the same times. Use when asked to move a job from one scheduler to another, to port a crontab or a workflow schedule to wrangler, or to check that an expression in one dialect means the same in another. For a schedule given in words, use cron-schedule instead.