AI Agent Skills

Run the weak-agent adversarial test harness against docx-cli. Spawns weak exercise agents (Haiku by default, Sonnet to probe, or a local agent harness's pre-produced run…

Turn Claude Code into an autonomous QA agent — an explore, generate, run, heal, report loop that maps the app, writes tests for real user journeys, executes them, self-h…

Run an independent code review using the OpenAI Codex CLI in headless mode. Gets a second opinion from a different model family (the current Codex models) on recent chan…

Audit and enforce the core/client boundary in multi-client projects. Detects where shared platform code is tangled with client-specific code, finds hardcoded client chec…

Deep behavioral audit of a Lattice skill — proposes 3 review personas relevant to the skill, runs independent scenario analysis from each persona's perspective, then mer…

Generate complete, production-ready OpenAPI 3.x and Swagger 2.0 specifications from natural language descriptions, code, or partial specs. Use this skill whenever the us…

Analyze Newman test run output, JSON reports, and JUnit XML results to summarize failures, diagnose root causes, identify slow requests, and suggest fixes. Use this skil…

[EMNLP 2024 (Oral)] Leave No Document Behind: Benchmarking Long-Context LLMs with Extended Multi-Doc QA

Verify any change surface against approved acceptance criteria, run the real system, and preserve the report and test artifacts.

Build, maintain, and review document-control registers for Chinese investment-banking transactions. Use for IPO、再融资、并购重组、辅导 and diligence projects involving 材料清单、原件清单、签字…

Structure Chinese investment-banking due-diligence materials into traceable schedules, testing workpapers, exception logs, and closure records. Use for IPO、再融资、并购重组 or s…

Extracts conversational transcripts from Cyara XML test case files.

AD Health Check, Send HTML Email, Ping machines, Encrypt Password,Bulk Password,Microsoft Teams,Monitor Certificate expiry, Monitor cert expiry, AD attributes, IP to Hos…

A Python CLI to test, benchmark, and find the best RAG chunking strategy for your Markdown documents.

Guide the user through containerizing and serving a simple website or documentation folder with Docker — inspects the project to detect what to serve (ready-to-serve sta…

Automated E2E testing with Playwright including the auto-fix loop — generate test cases from the UI, run them, fix failures and re-run until passing, then produce a huma…