Loading...
Loading...
Found 11,879 Skills
Build and operate multi-agent workflows with OpenAI Agents SDK (Python): define agents/tools/handoffs, add guardrails, run conversations, and debug orchestration behavior. Use when users ask for agent orchestration with OpenAI-native patterns, handoff routing, or production-ready agent loops.
Bump a pinned dependency (TransformerEngine, Megatron-LM, NRX, etc.), regenerate the lockfile, open a PR, and drive it to green by attaching a watchdog to the "CICD NeMo" workflow and quarantining failing functional tests as flaky until the run is green.
Use when the agent wants to define, list, inspect, or execute GUI macros via the MacroCLI CLI. Macros are parameterized, CLI-callable workflows — the agent invokes `macro run <name>` and the system handles backend routing (plugin, file transform, accessibility, compiled GUI replay).
PE deal sourcing workflow — discover target companies, check CRM for existing relationships, and draft personalized founder outreach emails. Use when sourcing new deals, prospecting companies in a sector, or reaching out to founders. Triggers on "find companies", "source deals", "draft founder email", "check if we've seen this company", or "outreach to founder".
Stein integration. Manage data, records, and automate workflows. Use when the user wants to interact with Stein data.
Create a complete SPEC from scratch through an exhaustive requirements interview before any planning or implementation. Use this skill whenever the user asks to create, define, clarify, scope, or write a spec/SPEC/PRD/requirements document from an idea, especially when they want to avoid assumptions, start at "step zero," or prepare input for later planning workflows. This skill must question goals, requirements, constraints, edge cases, business rules, and acceptance criteria before drafting the final spec.
Router skill for LLMQuant commodities workflows. Use when the user needs commodity spot, futures curve, inventory, roll yield, or macro linkage analysis.
Router skill for LLMQuant risk workflows. Use when the user needs fear scoring, VIX regime, hedge design, or research health checks.
Universal release workflow. Auto-detects version files and changelogs. Supports Node.js, Python, Rust, Claude Plugin, GitHub Releases, annotated tags, historical release backfill, and generic projects. Use when user says "release", "发布", "new version", "bump version", "push", "推送", "release notes", "GitHub Release", or "回填 Release".
Turn the working tree into logical, atomic Conventional Commits — classify uncommitted files as in-scope vs out-of-scope against the branch's merge base, show a staging plan, and create one commit per coherent unit (type + optional scope + British-English body; `!` / `BREAKING CHANGE:` for breaking changes). Never `git add -A`; files that look like they belong to another branch/worktree are never staged silently. Use when asked to commit uncommitted work, tidy WIP into atomic commits, or as the commit step inside a ship flow (e.g. `/send-it`). It commits only — no push, PR, changelog, or Linear writeback.
Select available tools based on research tasks, data, and operating environment; works without a preset local research-lab. Use when the user asks for "which tool to use for research tasks", "help me choose research tools", "is this repo useful", or requests the rw-research-lab-router workflow. Runs without a private local workspace or preset research-lab; uses user-provided materials and bundled public-source methods.
AI SDLC evidence-backed retrospective workflow. Use when delivery work is complete or paused and an AI assistant needs to capture observations, connect them to validation or artifact evidence, formulate reviewable process or policy improvement proposals, assign ownership, and preserve the rule that policy changes require an accepted decision. Supports `--quick-flow` for focused learning and `--full-flow` for strict evidence and decision gates.