Provides guidance for fine-tuning LLMs using the Tinker cloud training API from Thinking Machines Lab. Use when running supervised fine-tuning, reinforcement learning (GRPO/PPO), or LoRA training on cloud GPUs via Tinker's managed infrastructure instead of local compute.

Compact the current chat context into a concise summary. Use when the user invokes /compact, context capacity is running low, or a long session needs a smaller continuation state.

Download updated expected app size files from Azure DevOps CI artifacts for the current branch. Use when app size tests fail in CI and the user wants to update the expected files locally. Trigger on "update app size", "download expected files", "fix app size test", or "update expected app size files".

Investigate and fix flaky/random CI test failures in dotnet/macios. Trigger on GitHub issues describing intermittent test failures, CI postmortem issues, or when asked to fix a flaky test. Analyzes test code, identifies root causes (shared state, environment dependencies, race conditions), and applies fixes.

Guide for adding new LLM models to Letta Code. Use when the user wants to add support for a new model, needs to know valid model handles, or wants to update model-specific compatibility behavior. Covers runtime catalog sources, CI test matrices, and handle validation.

Use when writing medical, biological, or clinical research papers - provides IMRaD structure and reporting guidelines

Turn a wiki topic into a cited Markdown briefing, plain-language explanation, or progressive lecture. Use this skill for topic-based briefing, explanation, and lecture requests that must stay within the evidence compiled in an Obsidian vault.

Data-layer invariants for the collector — SQLite patterns, transactions, time keys, backendId isolation, ClickHouse read/write topology. Use when writing queries, touching repositories, or debugging data drift.

Test Architect & Quality Advisor (Quinn). Use for comprehensive test architecture review, quality gate decisions, and code improvement. Provides thorough analysis including requirements traceability, risk assessment, and test strategy. Adv... Triggers: qa gate, quality gate, code review, qa, @qa, test strategy, secu...

EXECUTE lean Full Story Development Cycle for one story: plan via CLI, run validate → develop → review (QG loop) → close with Sequence Lock, durable progress under .aiox/sdc/. Use when: full-sdc, full cycle, SDC, run story end-to-end.

Implement a story (Ready → InProgress → ready for review). Runs the OSS develop task. Use when: develop story, *develop, /develop-story, implement ACs.

Create a local conventional commit for AIOX work. Never pushes. Use when: committing, /aiox-commit, or local git commit.

Implement a story (Ready → InProgress → ready for review). Runs the OSS develop task. Use when: develop story, *develop, /develop-story, implement ACs.

EXECUTE lean Full Story Development Cycle for one story: plan via CLI, run validate → develop → review (QG loop) → close with Sequence Lock, durable progress under .aiox/sdc/. Use when: full-sdc, full cycle, SDC, run story end-to-end.

Extracts YouTube transcripts and generates professional Flutter showcase blog posts in Markdown format. Use when you need to create a technical marketing case study from a video success story.

Build local React changes in the bundle variants consumed by Next.js, sync them into a local Next.js checkout, and test the resulting integration. Use when working on React changes that need validation in Next.js, or when asked to run buildForNext, pnpm sync-react, or synchronize a React checkout with Next.js.

Maintain @next/rspack-core and @next/rspack-binding packages. Use when editing rspack/package.json, rspack/crates/binding/Cargo.toml, rspack/rust-toolchain.toml, or packages/next-rspack/package.json. Covers upgrading @rspack/core npm version, rspack_* crate versions, Rust toolchain version, building and linking for local testing, and NEXT_RSPACK environment variable usage. Does NOT apply to root rust-toolchain.toml (that's for Turbopack).

Use when the user wants to systematically fix AI code slop — duplicated logic, over-engineering, silent error swallowing, convention drift, cargo-cult patterns, and other LLM-introduced architectural decay — over a specified duration

Client-facing red-team deliverable format — codifies the Subject / Observations / Description / Impact / Recommendation / PoC structure used for external red-team engagements (not bug-bounty platform reports). Different audience, different tone, different cadence. Built from an authorized engagement deliverable where 14 findings were packaged into a 52KB MD + 2.2MB DOCX with 16 embedded screenshots. Use when the engagement is "external red team for an enterprise client" (not H1/Bugcrowd/Intigriti), when generating the final report, when the client has specified a custom report format, or when packaging findings into DOCX/PDF.

Hunting skill for xxe vulnerabilities. Built from 10 public bug bounty reports including SVG-upload XXE, Office-doc (PPTX/DOCX) XXE, SOAP XXE, SAML AssertionConsumer XXE, blind OOB XXE via DTD callback, parameter-entity XXE, XXE-to-LFI, XXE-to-SSRF, and XXE-to-RCE chains (Adobe Commerce CosmicSting CVE-2024-34102). Use when hunting XXE on any target — emphasis on OOB-Or-It-Didn't-Happen Gate for blind cases.