1K skills · sorted by relevance
Compare competitors using evidence-backed scores for positioning, brand expression, services, credibility, and other dimensions. Produce consistent profile cards and a two-axis chart showing which rivals occupy the market position your client wants to claim.
Compare Claude, GPT, and Gemini on the same skill or prompt. Get a table of response times, token usage, and costs, with optional AI scoring to help choose a model for the task.
Check code and agent outputs, track reliability scores, and roll back changes that fail a chosen threshold. Includes quality reports, live monitoring, and integration with automated build and deployment workflows.
Design the processes connecting marketing, sales, and customer success. Produce documents for lead scoring, meaning prospect prioritization, along with assignment rules, handoff deadlines, deal stages, CRM workflows, and dashboards that show where prospects stall.
Design rewards for reinforcement learning, where feedback guides model behavior. Choose how to score outcomes and intermediate actions, check for scoring loopholes, and use independent tests to detect incomplete work presented as finished.
Automate daily literature discovery across multiple academic sources. Score and select relevant papers, read abstracts or full texts, deliver structured digests through messaging platforms, and archive classified notes while removing duplicate records.
Design criteria for using an LLM to judge AI responses through scoring or comparisons between two answers. Includes checks for order and length bias, plus validation against human judgments to assess evaluation reliability.
Create and run evaluations in Arize using an LLM as the judge. Define scoring criteria, connect them to actual data fields, evaluate recorded operations or experiment results, and set up continuous scoring for new data.
Assess a repository’s readiness for AI agents with AgentRC and generate a standalone HTML dashboard. Review scores across nine areas, see prioritized improvements, and optionally apply scoring policies tailored to an organization.
Design workflows that evaluate and refine AI outputs through self-review, separate generation and evaluation roles, tests, or weighted scoring criteria. Includes patterns for structured feedback, iteration limits, and stopping when quality stops improving.
Customize AgentRC readiness assessments to match team or organization standards. Choose or create policies that adjust check importance, disable irrelevant checks, set pass thresholds, and define requirements for automated checks in CI workflows.
Evaluate threat intelligence platforms, which collect and organize cyber threat information. Define requirements, compare integrations and operating costs, plan practical trials, and use weighted scoring to select a platform and outline its rollout.
Screen AI application inputs and historical logs for prompt injection, where malicious instructions try to redirect the model. Combine pattern matching, text structure scoring, and a DeBERTa classifier to flag suspicious content and produce JSON results.
Create a structured hiring interview kit with questions tied to job skills, clear scoring criteria, interviewer assignments, and a discussion template. Use shared questions and evidence from candidates’ answers to support consistent evaluations.
Build market research evidence by comparing two market-size estimates, calculating survey sample sizes for each customer group, and scoring potential segments. Outputs show methods and assumptions so teams can assess the basis for business decisions.
Assess security risks in AI systems by scanning prompts for known attack patterns and scoring data exposure, poisoning, and tool abuse risks. Map findings to MITRE ATLAS, an AI threat framework, and identify protective controls.
Review a deal before signing by scoring its margin and risks, flagging problematic contract terms, and recommending named human approvers. It prepares a consistent review packet for discount requests and policy exceptions without automatically approving them.
Evaluate changes to OpenSEO skills by running fresh Codex sessions against a local backend. Compare saved reports using weighted criteria, then inspect tool logs to understand failures and check whether revised instructions improve output.
Assess applications against a role's written scoring criteria, recording strengths, gaps, and supporting resume quotes. Save a structured review and propose tentative interview times for strong matches, while leaving all advancement and rejection decisions to the hiring manager.
Assign new HubSpot leads to sales representatives using territory, specialist rules, and weekly lead counts. The skill records assignment reasons, highlights strong buying signals in Slack, and escalates cases that need human judgment.
Review Agent-Native Research Artifacts, structured research packages for agents, across six dimensions of research quality. Produce a JSON report with scores, strengths, severity-ranked findings, practical improvements, and an overall acceptance or rejection recommendation.
Assess web content for AI citation readiness using a weighted scoring rubric. Get page and section scores, identify passages needing work, and receive concrete suggestions for clearer answers, stronger evidence, and more readable structure.
Generate PDF checklists, reports, and scorecards with Python. Organizes content into sections and tables, supports scoring criteria and status colors, and includes steps to locate and verify the generated files.
Generate PDF checklists, reports, and assessments with sections, tables, and scoring criteria using Python. Choose a suitable library, save the document for download, and check the output, with shell execution as an alternative when the sandbox fails.