Agent skills for OpenAI Agents SDK

Rewrite AI-generated developer text to sound human — fix inflated language, filler, tautological docs, and robotic tone.

Refines AI-generated Korean text by removing mechanical patterns and translation artifacts to produce natural, human-sounding content.

Reescreve textos em português brasileiro para soarem mais humanos e naturais, reduzindo padrões típicos de escrita gerada por IA sem…

Refine an annotated implementation plan into a comment-free plan and a QA ledger while preserving the gen-plan schema.

Edit or audit an existing prose draft for clarity and natural phrasing while preserving facts and the requested voice.

Remove signs of AI-generated writing from text.

Refines AI-generated text by removing robotic patterns and optimizing for human-like engagement on social platforms.

Detects 55 AI writing patterns and rewrites text in five voice profiles so it reads like a specific human wrote it, with an optional 0-100…

Hunt CAPTCHA Bypass — 6 distinct patterns: (1) CAPTCHA field simply omitted from the request (server-side validation absent), (2) CAPTCHA…

Hunt CI/CD pipeline vulnerabilities — GitHub Actions workflow injection (pull_request_target Pwnrequest + ${{ }}-into-shell), self-hosted…

Hunt Clickjacking — missing X-Frame-Options / CSP frame-ancestors lets an attacker embed the target page in an invisible iframe and trick…

Hunt CORS Misconfiguration — origin-reflection with credentials, null-origin trust, subdomain-regex bypass (unanchored vs unescaped-dot vs…

Finds root cause before applying fixes for errors, crashes, regressions, failing tests, broken behavior, and screenshot-reported defects.

Hunt client-side DOM vulnerabilities — DOM Clobbering (overwrite JS globals via HTML injection), PostMessage hijacking (missing origin…

Hunt HTML Injection — user-supplied input is rendered as raw HTML in the response without sanitisation, allowing an attacker to inject…

Hunt HTTP request smuggling (CL.TE, TE.CL, H2.CL, H2.TE).

Hunt JWT cryptographic failures — alg:none signature-stripping and RS256→HS256 key-confusion that let an attacker forge a token for any…

Hunt Kubernetes & Docker — API anonymous access, kubelet 10250 exec (SPDY/WebSocket, NOT plain POST) and the simpler /run primitive, etcd…

Hunt Next.js specific vulnerabilities — Server Actions arbitrary function execution, Middleware auth bypass via static asset paths, ISR…

Hunt Node.js specific vulnerabilities — Prototype Pollution → RCE chains (lodash/merge/assign), Express trust proxy misconfiguration…

Detect data-staging activity (MITRE ATT&CK T1074) by analyzing EDR/Sysmon process-creation and file-system telemetry (Event ID 4688…