Default reference pipeline for image, video, and audio projects — routes through media-image / media-video / media-audio atoms based on the project kind, wraps the output in a live artifact, and devloops on critique-theater until the score converges.
Run a scored, converge-or-cap code-review loop on a diff or surface — a read-only critic raises evidence-backed findings, a read-write fixer addresses only those findings, then re-audit until two clean rounds or a cap. Use when reviewing a PR, hardening a changed file, or iterating to a clean bill of health without…
Draft a GitHub pull request that edits a founder-kernel page. Kernel pages under docs/founder-kernel/ are PR-only per spec §4 (never written by the runtime); this skill walks the user through reading the current markdown, applying the requested change, validating wikilinks + manifest counts, and opening a draft PR for…
Create, review, audit, migrate, or update scoped AGENTS.md files with clear rules, verified commands, action limits, instruction order, and checks that prove the work is done. Use also when verified, durable repository guidance emerges during authorized work and should be captured at the narrowest applicable scope.
Fetch daily arXiv announcements (cs.RO), filter by research relevance, generate a structured markdown digest, and sync matched papers to a Zotero collection with arXiv PDFs attached.
Turn anything — a plan, architecture, design, technical decision, brainstorm, braindump, hunch, or half-formed idea — into a confirmed pre-intent through epistemic investigation: resolving inspectable facts yourself and grilling only the consequential judgments. Use for requests to grill, challenge assumptions…
Use TreeWork Manual when the user asks for it, or when the Agent judges that organizing ongoing, multi-part work as a persistent Markdown Tree would improve direction, continuity, recovery, or handoff. Adapt the Tree's depth and document detail to the user's needs, domain, and situation rather than a fixed threshold.
A project-initialisation skill that creates a lightweight structure of guides for AI coding agents. It maps project areas and adds sections such as contents, locations, commands, working methods, and cautions.
Build image2-first classroom PPT page images from a topic, source files, reference PPT style, and iterative user feedback. Use when Codex needs to create image2-ready per-page prompts, generate polished PPT page images, QA a contact sheet, insert the final images into a PPTX wrapper, and write a timed presentation…
Search for music tracks using natural language prompts or video content via the Harmix AI API. Use when the user asks to find music, search for songs, discover tracks, needs music recommendations based on mood/genre/tempo/scene, or wants to find music for a video, video soundtrack, or music that matches video content.
Use when writing C# / VB.NET / F# code that reads, writes, manipulates, or exports Excel (.xlsx / .xls) files, generates PDF or HTML from Excel, or produces data-driven reports with FlexCel Studio for .NET (TMS Software). Triggers include Excel/xlsx from C#, XlsFile, FlexCelReport, FlexCelPdfExport, FlexCelHtmlExport…
Initiate the orchestrator-worker cost model for this session. The main-loop model (expensive, metered) orchestrates, specs, verifies, and validates only; ALL drafting and mechanical work (code, docs, tests, sweeps, research) runs in Opus 4.8 subagents billed to plan allowance. Invoke at session start or whenever token…
Use when a user asks what Atlas Flight Booking can do, wants to authorize Atlas, search or compare flights using exact or flexible dates and time preferences, verify a current fare, choose baggage or seats, create and pay for an order, or check ticketing status.
Use when designing, reviewing, refactoring, or enforcing Angular application architecture with isolated lazy features, eager core/layout, reusable ui/pattern architecture building blocks, one-way dependency graphs, eslint-plugin-boundaries rules, or folder placement decisions. This skill takes precedence over…
Audit an app, website, metadata, SDKs, and marketing for privacy, security, AI transparency, consumer claims, subscriptions, content rights, user-generated content, children, health, financial, export, and platform-policy risks. Use before TestFlight, submission, release, paid marketing, or after adding tracking…
Cryptographic compliance verification. Sign security tool output into verifiable CPOEs (JWT-VC), verify vendor proofs via trust.txt, detect drift with diff, and assess third-party risk. Use when the user mentions compliance proofs, CPOE, trust.txt, SCITT, vendor assessment, GRC evidence, or compliance drift.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: