408 skills · sorted by relevance
Manage recruiting in Ashby with natural language requests from Claude Code. Create and update candidates, create jobs and applications, review interview schedules and candidate notes, and combine records to report on hiring progress.
Review module relationships and change history to identify structural improvements in a codebase. Receive ranked candidates with file references, suggested changes, and risks, plus a recommendation for where to start, without modifying code.
Manage recruiting in Ashby with natural language requests from Claude Code. Create and update candidates, create jobs and applications, review interview schedules and candidate notes, and combine records to report on hiring progress.
Generate new protein, peptide, antibody, or nanobody candidates that bind a chosen target using Boltz. The workflow covers target exploration, design setup, cost estimates, job submission, result downloads, and ranking by predicted binding confidence.
Screen job applications against requirements and score candidates objectively. Use when a user asks to review applications, evaluate candidates, screen resumes, rank applicants, assess qualifications against a job description, shortlist candidates, or build a hiring scorecard.
The English summary is being prepared. Showing the original description.
Find LinkedIn prospects, candidates, companies, posts, jobs, services, and groups through Curviate CLI, a command-line tool. Guides filter setup and multi-page retrieval so searches use the intended criteria and incomplete results are identified.
Use Curviate CLI to search LinkedIn sales prospects and recruiting candidates, manage saved lists and hiring projects, and send messages. It also explains how to diagnose failures caused by subscriptions, account seats, or beta permissions.
Supports job searches and hiring through WorkorAI, from finding vacancies and applying to reviewing and inviting candidates. Explains matches using skill requirements and interview evidence, helping users understand why a job or candidate may fit.
Track candidates from first outreach to offer acceptance, and review time spent at each stage, conversion rates, and recruiting sources. Use these measures to understand hiring progress and where candidates drop out.
Find prospective candidates on LinkedIn, check them against the role’s Greenhouse recruiting records, and prepare personalized outreach drafts. Each capped batch includes candidate details and match reasons for recruiter review, with sending left to the recruiter.
Develop solution ideas through repeated rounds of research, cross-domain borrowing, recombination, and evaluation. Receive ranked candidates with feasibility and novelty scores, supporting and opposing arguments, and a record of where each idea came from and how it changed.
Screen companies across markets within a chosen industry and narrow the list to three investment candidates. Compare financial health, lasting competitive advantages, valuations, and risks, while recording why other companies were excluded.
Screen public equity candidates and prioritize further research using company sources, market data, and supplied notes. Organize promising names, watchlist items, evidence gaps, and rejection risks into a concise review or standalone HTML report.
Screen supplied proteins, peptides, antibodies, or nanobodies against a target with Boltz. Prepares inputs, obtains a cost estimate for approval, downloads results, and ranks candidates by binding confidence, a score for predicted binding reliability.
Generate new small molecules intended to bind a target protein with Boltz. The workflow covers cost estimation, job submission, result downloads, and ranking candidates by binding confidence or a score for improving promising molecules.
Screen an existing compound library against a protein target with Boltz. Rank candidates by binding confidence or lead optimization score, download predicted structures, and review solubility, permeability, and lipophilicity results alongside the ranked hits.
Build a candidate sourcing strategy and outreach pipeline. Use when the user says "where do I find candidates for this role", "build a sourcing plan", "write a cold outreach message", "we're not getting enough applicants", "our pipeline is dry", "help me find passive candidates", "write a LinkedIn message", or wants to increase the volume or quality of candidates in the funnel - even if they don't explicitly say "sourcing strategy". Also use when a recruiter needs to go beyond job postings to find talent.
The English summary is being prepared. Showing the original description.
Find GIFs on Tenor or Giphy, preview candidates in a terminal interface, and download selected results. Extract a still image at a chosen time or create a PNG grid of frames for review and sharing.
Choose which competitors to compare based on a company's offer, audience, and positioning. Organize candidates into direct, adjacent, and aspirational groups, then narrow the list with selection scores and source links before detailed benchmarking.
Audit code and configuration for security flaws, documenting attack paths, impact, evidence, and coverage gaps. Static review works without running the application; qualified runtime profiles add isolated reproduction and proposed repairs while keeping verification claims separate.
Tidy a Paperclip Mine inbox by scanning entries and grouping archive candidates by work status and inactivity. Present checkbox confirmations, then archive only accepted selections, with undo details and no changes to the underlying tasks, branches, or workspaces.
Retrieve a point-in-time view of vessel positions from AIS, the automatic ship identification system. Limit results to a geographic area and optionally include tanker information and candidates for maritime disruption or concealed activity.
Compare two JSON records describing agent setups and their scores. Receive an overall similarity score with component details to help assess reuse, compare template candidates, identify overlapping work, or check how much a setup has changed.
Evaluate and improve the policy instructions that guide an AI agent using scored coding tasks. Run a learning cycle to compare candidates, or use the default dry run to inspect tasks and estimated costs without model calls.