Official scripts
Explore our curated collection of scripts
Search Upwork Jobs
Search Upwork's public job board by free-text query, returns structured job cards (title, description, budget, skills, experience level) for one results page.
Get job description
Fetch a single Upwork job posting's full details by its ciphertext (the ~0… token in the job URL, returned by search_jobs). Covers title, full description, category, occupation, skills, budget or hourly range, workload and duration, experience level, screening questions and attachments. Also covers client activity (applicants, interviews, invites, hires) and the client: country, city, payment verified, member since, score and spend. Works signed out, so no Upwork account is needed; run it on the managed browser, since Upwork's Cloudflare check can block some paired browsers. A job that does not exist or was removed fails with a clear error. Read-only.
Get Ashby job posting
Read one Ashby job posting (jobs.ashbyhq.com/<board>/<jobId>), description HTML included.
Search HelloWork jobs
Search HelloWork's French job listings by keyword, optional free-text location, and page (30 offers/page). Returns total and jobs (jobId, title, company, url, location, contract, remoteTag, salary, superRecruiter, postedAgo). Salary and remote-work tags are only present when the listing/employer chose to show them, so they're frequently null.
Search Free-Work jobs
Searches job listings on free-work.com (IT/freelance), usable without logging in. `query` is a free-text keyword; `location` is a free-text city, resolved to the closest match — unresolved locations throw explicitly rather than silently searching everywhere. Defaults to searching all of France when no location is given. Returns title, full description, company, contract types, experience level, remote work, salaries (daily/annual), currency, skills, publish date, and URL. 1-based pagination, 16 results per page. One thing to check: requesting a page beyond the real number of pages doesn't return an empty result — it silently repeats the first page — so verify against `totalItems` before trusting a high page number.
Search ComeUp freelancers
Search ComeUp sellers/freelancers by keyword. Returns username, display name, verified badge and avatar for each match (ComeUp's seller-search results are minimal — use get_profile with the returned username for headline, bio, stats, portfolio and services).
List my assigned ClickUp tasks
Returns the tasks assigned to the signed-in person, as ClickUp's Home page shows them, with each task's status, priority, due date and the list it belongs to. Reports how the answer was confirmed, so an empty result is never mistaken for a page that had not finished loading.
List job board postings
List every open position on an Ashby-hosted job board (jobs.ashbyhq.com/<board>).
Search WeWorkRemotely jobs
Search We Work Remotely two ways: `query` hits the site's own "Search everything" full-text search (leaner fields: no absolute date, just relative postedAgo, plus salaryRange/companyHeadquarters); `category` reads the RSS feed for one category or the combined feed (richer fields: region/country/state/skills/absolute pubDate, no free-text search). They're separate site affordances, not merged — query takes priority if both are given.
Search Make.com public templates
Search Make's public template catalogue by name and/or by the apps a template uses.
Search Behance jobs
Search Behance's job board (freelance briefs and full-time/contract listings) by keyword, returning title, company, location, remote status, job type, salary and url.
Create a task in a ClickUp list
Adds a task with the given name to a ClickUp list and confirms it afterwards, reporting the new task's identifier and link. A rehearsal mode fills the task in without submitting it, so the inputs can be checked before anything is created. This version sets the name only; description, priority, assignee and due date are left at the list's defaults.
Search LinkedIn jobs
Search LinkedIn job postings by keywords, with optional location, date-posted window, workplace-type filter, sort, and pagination (25/page). Returns total, page, resolvedLocation, and jobs (jobId, title, company, location, benefits, postedAgo, easyApply, url). Searches worldwide by default, unlike LinkedIn's own UI which silently restricts to the viewer's country. Experience, salary, and industry filters are not exposed, and postedAgo is null when LinkedIn shows a "Viewed" marker instead of a date.
Search Built In jobs
Search Built In (builtin.com) tech/startup job listings by free-text keyword and optional free-text location (city). Returns id, title, url, company, companyUrl, postedAgo, remoteType (Remote/Hybrid/In-Office wording as shown), locations (array — cards with several offices list each one), salary (raw site text, e.g. "180K-201K Annually" — not split into min/max since the site itself only shows a range string, sometimes absent when undisclosed), seniority, industries (array), description, topSkills (array). Paginates via the site's own page param (page=1 default, 25 results/page); the reported last page reflects the true total, not just the current page's count. A query/location with no matches returns jobs:[] — not an error.
Search Threads posts
Search Threads for posts matching a keyword, hashtag, or topic and return the matching posts with author, text, and engagement counts.
List the tasks in a ClickUp list
Reads the tasks shown in one ClickUp list, in the order the list displays them, returning each task's identifier, name, status, assignees and link. Pair it with the ClickUp list lookup to go from a list name to its identifier.
Search Behance projects
Search Behance projects by keyword, returning title, url, owner, thumbnail, likes and views for each result.
Search Dribbble jobs
Search Dribbble's job board by keyword, location and job type, returning title, company, location, posted date and url.
Vercel — list invoices
List a Vercel team's billing invoices, newest first: billing period, status, total due, invoiced date, invoice id, a direct PDF download link, and a link to the invoice's detail page. Optionally pass a team URL slug; defaults to the account's own scope.
Canva — list designs
List the designs on the signed-in Canva account's Projects page (most recent first, owned or shared with the account): design id, title, edit link, design type (e.g. Video, LinkedIn post, in the account's interface language), page count and creation date. Read-only. Returns the designs the Projects page loads on first view, not the full archive. Signed out is a clear error, not an empty list.
Get ComeUp freelancer profile
Fetches a ComeUp seller's full public profile by username (from search_freelancers' username field, e.g. "guillaumetbc"). Returns display name, headline, bio, account type, review counts, top-seller badge, response time, portfolio, and their related services with price/rating.
Search talent.com jobs
Search talent.com's aggregated job listings by free-text keyword and optional free-text location (city/region; omit for a broad/geo-default search). Returns richer job data (salary, company, remote flag, job type, description) than what's shown on the page, read directly from the page's own underlying data rather than scraped visually — more stable against markup changes. Paginates via the site's own page param (page=1 default, ~18-20 results/page); no total-count field is exposed anywhere, so callers must page until an empty array comes back. Location text is matched loosely against talent.com's own place index (e.g. "paris" can resolve to Paris, TX, US rather than Paris, France) — this mirrors the site's own search box behavior, not an added restriction. A query with no matches returns jobs:[] — not an error.
Greenhouse: get company jobs
Fetch a company's live job postings from Greenhouse's public board API by board slug (boards.greenhouse.io/<slug>). Anonymous, no auth. Returns id, title, location, department(s), url, updatedAt, firstPublished. Throws (job board not found) if the slug isn't a Greenhouse customer.
List Slack channels
List the workspace's channels (public + private) with membership, member count, topic and purpose. One page per call; pass cursor to paginate and types/excludeArchived to filter. Requires login.
Get LinkedIn job
Fetch a LinkedIn job posting by numeric ID. Returns id, url, status (live/expired), title, company, location, posted, applicants, workplaceType, employmentType, description, and companyInfo (name, url, industry, followers, employeeRange, membersOnLinkedIn, description).