Test design, vulnerability assessment, and quality assurance (13K skills)
Assess candidate security findings using focused reproduction, tests, or code tracing. Record the evidence, confidence, and remaining proof gaps for each candidate, helping determine which findings warrant reporting and which remain uncertain.
Turn vulnerability notes, proof-of-concept code, source code, or security findings into self-contained reports. The skill checks claims against evidence, explains prerequisites and demonstrated impact, and supports both individual vulnerabilities and collections of disclosure reports.
Run repeated, independent security reviews of an entire repository or a selected directory. The skill combines validated findings and coverage records into a final report, helping reduce variation between individual reviews.
Troubleshoot browser automation when clicks, typing, scrolling, or page snapshots fail on complex websites. Inspect page structure and errors, apply waits or alternative interaction methods, and verify the fix on both problematic and simple pages.
Record product demos that show real user actions and responses for each covered user journey. Add timed captions, inspect the finished clips, and include them in pull requests, with manual test instructions when recording is blocked.
Assess the full code change for effects on callers, configuration, and related behavior. Organize focused tests, execution evidence, and unverified areas to support decisions about whether a fix or pull request is ready.
Test Omnigent’s native Pi integration using the real terminal interface and a local server. Verify messages sent through the web or API, recorded replies, interruption, session resumption, authentication, and model settings to investigate integration problems.
Review code or changes for exposed secrets, injection risks, weak encryption, and missing permission checks. Produce a structured report with severity, location, recommendations, and confidence, with a separate reviewer checking findings for false positives.
Test Omnigent’s native Antigravity integration with a live local server and the real agy CLI. Verify messages traveling between the web interface and terminal, mirrored replies, permission requests, interruption, session resumption, and process cleanup.
Audit recovered bug reproduction tests before writing a fix or reviewing a pull request. Check that assertions reflect intended behavior, establish a valid failure on unfixed code, and verify the same test passes after the fix.
Test Omnigent’s setup, help, and terminal interactions by driving the real CLI in an isolated environment. Capture rendered screens and compare checks before and after a change to establish whether a reported interface problem was fixed.
Test Omnigent’s Cursor SDK integration against a live local server. Build test agents, run real conversations, and check authentication, model selection, and tool connections while investigating empty responses or bridge processes left after shutdown.
Test polly's coordination of coding agents using a scripted mock language model and live command-line tools. Check startup, task dispatch, safety rules, parallel delegation, and whether real agents make appropriate orchestration decisions.
Run concurrent Omnigent conversations with real hosts and runners while replacing the LLM with a zero-latency mock. Read the generated report to explain response-time distributions, throughput, and failures, helping assess Omnigent's own processing overhead.
Verify Omnigent behavior through real user actions in an isolated environment. Use a feature map to cover relevant web, terminal, and CLI entry points, preserving recordings and other evidence for bug reproductions and fixes.
Test Omnigent’s Antigravity SDK integration against a live local server. Build test agents and run real conversations to check Gemini authentication, model selection, tool connections, and failures across the full execution path.
Test Omnigent’s GitHub Copilot SDK integration on a live local server. Build test agents, run real conversations, and inspect authentication, model selection, tool connections, policy enforcement, and leftover processes to investigate integration failures.
Plan tests for APIs, interfaces, data pipelines, and infrastructure. Choose suitable test types, prioritize critical behavior, and produce a plan with coverage targets and example cases while balancing thoroughness, execution speed, and maintenance effort.
Review a design or web page against WCAG 2.1 AA, an accessibility standard. Organize findings on contrast, keyboard access, forms, and screen reader behavior, with severity levels and practical recommendations for fixes.
Review an AI tool deployment with six checks covering prompt protection, dangerous commands, malicious inputs, sensitive data transfers, Chinese compliance requirements, and audit records. The result summarizes protection status, risks, and proposed hardening actions.
Check structured medical study materials, including guideline summaries, exam preparation, and insurance policy notes, before delivery. The skill validates required headings, source links, and scope statements, then guides corrections when the format fails validation.
Review threat mitigations after a development phase is complete and update SECURITY.md with verification results. Use an existing security record or a threat model in the phase plan to guide the review.
Audit validation coverage for a completed development phase and fill missing checks. The skill updates VALIDATION.md, reconstructs missing validation records from existing project artifacts, and generates test files to address gaps.
Check implemented features through conversational acceptance testing, confirming behavior from the user's perspective. Record each result, retain testing progress, and diagnose reported problems to prepare verified repair plans for a subsequent execution step.