Skills for your AI
Plans, executes, and maintains software localization for global markets, covering formats, dynamic content, translation, compliance, multimedia, QA, and project documentation. Use when adapting software to target locales, translating content, meeting regional
Analyzes software performance data such as profiles, logs, metrics, and query plans to find bottlenecks and recommend optimizations. Use when the user shares code, profiler output, memory or CPU data, network metrics, query logs, load test results, or asks to
Guides systems analysts through enterprise software selection, from market research and requirements gathering to cost, risk, and decision documentation. Use when evaluating software vendors, comparing features, analyzing costs or security, or documenting a se
Guides IT project managers through the full software selection lifecycle, from requirements and tool research to PoC, procurement, implementation and post-implementation review. Use when selecting, comparing, costing, piloting, procuring or evaluating software
Plans, interprets, and reports soil, water, contaminant, and groundwater analyses for environmental consultants. Use when planning soil sampling, selecting or interpreting water quality parameters, evaluating soil nutrients or pH, identifying contaminants and
Analyzes soil contamination data to identify sources, plan sampling, quantify contaminants, assess risk, compare remediation options, check compliance, write reports, map contamination, monitor long term, evaluate biological methods, model transport, and produ
Collects and analyzes solvency data, builds and stress-tests risk models, checks Solvency II compliance, calculates solvency ratios and capital adequacy, and documents results for insurance actuaries. Use when the actuary asks for solvency assessment, risk mod
Converts process walkthroughs, transcripts, notes, and how-to docs into clean numbered SOPs with roles, decision points, exceptions, and library-matched style. Use when drafting, pressure-testing, restyling, or auditing standard operating procedures.
Generates, remixes, polls, lists, downloads, and deletes Sora video clips through OpenAI's API using a bundled CLI. Use when the user wants to create a Sora video, remix an existing clip, check job status, batch-generate variants, or list and delete videos.
Plans, reviews, and documents sound design for film, games, VR, podcasts, ads, and live events, from mood boards to post-production. Use when starting sound design, briefing or sourcing sound designers, giving draft feedback, building soundscapes, teaching wor
Analyzes film and game soundtrack genres — musical elements, cultural influences, market trends, and composition techniques — so composers can make informed choices. Use when asked to identify a soundtrack's genre, break down instrumentation, mood, tempo, harm
Hunts exposed source code and build artifacts on an authorized target web app, checking for source maps, Swagger/OpenAPI specs, .env files, .git exposure and other leaked files with exact evidence. Use when recon starts on a target, when source-code or config
Extracts backend API hosts, routes, and secrets from a SPA's JavaScript bundles and tests discovered endpoints for missing authentication and broken access control. Use when analyzing an authorized SPA target, mapping its API surface from JS bundles, or probin
Runs a short onboarding questionnaire, then creates the agents and connectors the user needs based on their answers. Use when a new user needs setup, asks what to configure first, or wants agents created from their stated needs.
Guides setup and verification of an ML environment on NVIDIA DGX Spark (GB10 Grace Blackwell, aarch64, SM121, CUDA 13) across NGC containers and bare pip. Use when choosing a container or pip approach, running or pinning containers, executing the pip sequence,
Preflights and diagnoses the ten known ML training failure modes (G1–G10) on NVIDIA DGX Spark, covering CUDA ABI, attention, unified-memory OOM, thermals, bandwidth, contention, precision, playbooks, containers and dual-Spark parallelism. Use when a Spark trai
Launch N parallel subagents in isolated git worktrees to compete on the session task. Use when the user runs /hub:spawn or asks to start the competing agents for an initialized AgentHub session.
Use when the user asks to write specs before code, define acceptance criteria, plan features before implementation, generate tests from specifications, or follow spec-first development practices.
Use when the user says 'build me an app', 'create a project from this spec', 'scaffold a new repo', 'generate a starter', 'turn this idea into code', 'bootstrap a project', 'I have requirements and need a codebase', or provides a natural-language project speci
Use when Codex should act as the Chief of Staff specialist from Agency Agents. Master coordinator for founders and executives — filters noise, owns processes, enforces consistency, routes decisions, and positions outputs for impact so the boss can think clearl
Use when Codex should act as the Civil Engineer specialist from Agency Agents. Expert civil and structural engineer with global standards coverage — Eurocode, DIN, ACI, AISC, ASCE, AS/NZS, CSA, GB, IS, AIJ, and more. Specializes in structural analysis, geotech
Use when Codex should act as the Cultural Intelligence Strategist specialist from Agency Agents. CQ specialist that detects invisible exclusion, researches global context, and ensures software resonates authentically across intersectional identities.
Use when Codex should act as the Developer Advocate specialist from Agency Agents. Expert developer advocate specializing in building developer communities, creating compelling technical content, optimizing developer experience (DX), and driving platform adopt
Use when Codex should act as the Document Generator specialist from Agency Agents. Expert document creation specialist who generates professional PDF, PPTX, DOCX, and XLSX files using code-based approaches with proper formatting, charts, and data visualization
