Stars1233

Analyze current OpenClaw setup and generate a migration package (ZIP) for importing into HiClaw as a managed Worker

Use before direct filesync calls, reading non-task shared files, pushing mid-task progress, or troubleshooting missing shared files. Do not use for normal task acceptance or submission; taskflow ack_task and submit_task handle lifecycle sync internally.

Discover and install agent skills from the open ecosystem. Use when you encounter an unfamiliar domain, framework, or workflow that you lack specialized knowledge about, or when your coordinator suggests searching for skills before starting a task.

Use only when you need to look up team topology, worker phase, runtime state, or identity that is NOT available from the current message context. Do not use for standard task flows — the coordinator is the message sender, and the task room is in meta.json.room_id.

Sync files with centralized storage. Use when your coordinator or another Worker notifies you of file updates (config changes, task files, shared data, collaboration artifacts).

Discover and install agent skills from the open ecosystem. Use when you encounter an unfamiliar domain, framework, or workflow that you lack specialized knowledge about, or when your coordinator suggests searching for skills before starting a task.

Sync files with centralized storage. Use when your coordinator or another Worker notifies you of file updates (config changes, task files, shared data, collaboration artifacts).

Discover and install agent skills from the open ecosystem. Use when you encounter an unfamiliar domain, framework, or workflow that you lack specialized knowledge about, or when your coordinator suggests searching for skills before starting a task.

Diagnose and safely recover stuck terminating Kubernetes pods on Marin CoreWeave clusters, especially node-bound GPU pods. Use for deletion hangs, suspected uninterruptible GPU/NCCL waits, node cordoning or reboot decisions, and force-deletion requests.

Refresh Marin TPU-vLLM forks from a tpu-inference release/LKG pair, update exact SHA pins, run TPU smokes, and open the Marin PR.

Lint, run the pre-PR checks, commit, push, and author or update the branch's pull request in the required plain-text format. Use when committing, pushing, or creating/updating a PR.

Launch, monitor, and seal Marin canary and daily ferry runs.

Multi-agent correctness review of a pull request.

File a GitHub issue for a bug or improvement found this session.

Multi-session research workflow: compose logbooks, experiment issues, documentation updates, and snapshot discipline for long-running investigations.

Create stable commit or tag snapshots for task milestones, experiment results, and reproducible artifact links.

Guides repo-local skill creation and updates. Use when adding or editing .agents/skills, SKILL.md frontmatter, references, scripts, or skill routing.

Guides t-wada Red-Green-Refactor TDD. Use when implementing features, fixing bugs, or refactoring logic with strict test-first development.

Runs the full PR lifecycle. Use when creating a branch, committing, pushing, opening a PR, requesting AI review, and driving CI and review to completion.

Creates atomic Conventional Commits. Use when committing code changes, splitting hunks into revertable units, or writing detailed commit messages.

Guides ccusage monorepo development. Use when editing packages, docs, shared configuration, bundled CLI packaging, dependencies, exports, or validation commands.

Profiles ccusage performance. Use when debugging slow Rust CLI commands, TypeScript package scripts, launchers, benchmarks, packaging hot paths, or branch-vs-main speed changes.

Guides ccusage Rust and Vitest tests. Use when adding or fixing cargo tests, CLI snapshots, Claude model pricing, LiteLLM compatibility, Vitest tests, or fixture-backed tests.

Guides ccusage TypeScript and JavaScript work. Use before reading or editing .ts, .tsx, .js, or .jsx files, including package launchers, Vitest tests, Bun scripts, schemas, mocks, and typed fixtures.

Creates tests for an existing feature following OpenAEV patterns: fixture class, composer, integration test with @Nested groups, and optionally unit tests. Use when asked to add tests or improve test coverage.

Scaffolds a complete feature end-to-end: JPA entity, repository, service, DTOs, mapper, controller, migration, tests (fixture + composer + integration test), and frontend actions/page. Use when asked to create a new feature or module.

Step-by-step general code review procedure for OpenAEV pull requests. Covers architecture, conventions, code quality, and delegation to specialized agents.

Frontend review checklist for OpenAEV React/TypeScript code: component patterns, forms, MUI usage, permissions, i18n, state management, dead code. Use when reviewing PRs or auditing frontend features.

Step-by-step tenant isolation audit for OpenAEV pull requests. Use when reviewing PRs that touch entities, repositories, native queries, or migrations.

Creates a Flyway Java-based migration for schema changes. Handles table creation, column additions, tenant isolation, and ES reindex. Use when asked to modify the database schema.

Performance review checklist for OpenAEV code: N+1 queries, fetch strategy, pagination, indexing, memory usage. Use when reviewing PRs or auditing performance of a feature.

Create a GitHub pull request with the NemoClaw template. Then, monitor CI and automated reviews. Use this skill when the user asks to create, open, push, or submit a PR for review. Trigger keywords - create PR, pull request, new PR, submit for review, open PR, push for review.

Scan recent git commits for user-facing changes, update the corresponding documentation, and create the canonical dated MDX changelog entry for pre-tag release prep. Use when docs have fallen behind code changes, after a batch of features lands, before opening a release-note docs PR or cutting a release tag, or when recovering missed post-release docs. Trigger keywords - update docs, draft docs, docs from commits, sync docs, catch up docs, doc debt, docs behind, docs drift, release prep docs, pre-tag docs, release note docs, changelog entry.

Run one NemoClaw daytime maintainer pass. Prioritize items for the release version. Select a merge, salvage, security, test, conflict, or sequencing workflow and report progress. Use during the workday to land PRs and close issues. Designed for /loop, for example /loop 10m /nemoclaw-maintainer-day. Trigger keywords - maintainer day, work on PRs, land PRs, make progress, what's next, keep going, maintainer loop.

Provide read-only NemoClaw maintainer policy. Use for questions about Issue Type, labels, Project fields, release labels, triage, duplicates, blocked items, and maintainer decisions. Trigger keywords - maintainer policy, workflow policy, project workflow, issue type, labels, label taxonomy, needs labels, project status, blocked issue, duplicate issue, daily release label, release train, triage policy.

Drafts the post-tag NemoClaw Announcement from live GitHub tag and compare data. Produces three lead paragraphs, categorized shipped changes, why-it-matters bullets, and external-only contributor thanks. Use after cutting a release tag or when asked to draft an announcement or summarize v0.0.x. Native `docs/changelog/YYYY-MM-DD.mdx` entries belong to the pre-tag `nemoclaw-contributor-update-docs` workflow.

Collaboratively investigate a GitHub issue or bug — trace history, understand architecture, diagnose root cause

Guided interactive PR review — understand the history and context before forming opinions

Collaboratively investigate a GitHub issue or bug — trace history, understand architecture, diagnose root cause

Guided interactive PR review — understand the history and context before forming opinions

Documentation guidelines for Mastra. This skill should be used when writing or editing documentation for Mastra. Triggers on tasks involving documentation creation or updates.

Create custom LLM evaluation benchmarks using the BYOB decorator framework. Use when the user wants to (1) create a new benchmark from a dataset, (2) pick or write a scorer, (3) compile and run a BYOB benchmark, (4) containerize a benchmark, or (5) use LLM-as-Judge evaluation. Triggers on mentions of BYOB, custom benchmark, bring your own benchmark, scorer, or benchmark compilation.

Query and browse evaluation results stored in MLflow. Use when the user wants to look up runs by invocation ID, compare metrics across models, fetch artifacts (configs, logs, results), or set up the MLflow MCP server. ALWAYS triggers on mentions of MLflow, experiment results, run comparison, invocation IDs in the context of results, or MLflow MCP setup.

Run, monitor, analyze, and debug LLM evaluations via nemo-evaluator-launcher. Covers running evaluations, checking status and live progress, debugging failed runs, exporting artifacts and logs, and analyzing results. ALWAYS triggers on mentions of running evaluations, checking progress, debugging failed evals, analyzing or analysing runs or results, run directories or artifact paths on clusters, Slurm job issues, invocation IDs, or inspecting logs (client logs, server logs, SSH to cluster, tail logs, grep logs). Do NOT use for creating or modifying evaluation configs. WARNING — this skill performs privileged operations; it SSHes to remote cluster hosts, executes shell commands on cluster infrastructure, transfers files via rsync, and may modify cluster configuration fields (e.g., the SLURM account). Only use with trusted cluster credentials and configs from trusted sources, and require explicit user confirmation before SSH/rsync operations or any cluster-config change.

Interactive config wizard for NeMo Evaluator Launcher (NEL). Use when the user wants to create a new evaluation config from scratch, set up an evaluation from existing configs, or modify a NEL config (deployment, tasks, multi-node, interceptors). ALWAYS triggers on mentions of creating configs, setting up evaluations, configuring models for evaluation, or modifying NEL YAML files. Do NOT use for monitoring, debugging, or analyzing already-running evaluations.

Run, monitor, analyze, and debug LLM evaluations via nemo-evaluator-launcher. Covers running evaluations, checking status and live progress, debugging failed runs, exporting artifacts and logs, and analyzing results. ALWAYS triggers on mentions of running evaluations, checking progress, debugging failed evals, analyzing or analysing runs or results, run directories or artifact paths on clusters, Slurm job issues, invocation IDs, or inspecting logs (client logs, server logs, SSH to cluster, tail logs, grep logs). Do NOT use for creating or modifying evaluation configs.

Creates and edits trusted local Letta Code mods, including tools, slash commands, local-only model providers, lifecycle/turn events, scoped conversation helpers, panels, and capability-gated behavior. Use when asked to make a mod, add an agent-callable tool, add a slash command, add a local provider/model adapter, transform turns, react to app events, or add lightweight mod UI outside the dedicated /statusline flow.

Modify Letta Code's own memory, model, context window, system prompt, compaction, permissions, toolsets, mods, skills, channels, schedules, and local runtime settings. Use when the user asks you to change how you behave or how the harness runs you.

Comprehensive guide for initializing or reorganizing agent memory. Load this skill when running /init, when the user asks you to set up your memory, or when you need guidance on creating effective memory files.

Dispatch stateless coding agents (Claude Code or Codex) via Bash. Use when you're stuck, need a second opinion, or need parallel research on a hard problem. They have no memory — you must provide all context.

Use when writing tests for the Walkontable rendering engine - has its own separate test pipeline, runner, and configuration distinct from main Handsontable E2E tests

Use for ANY work touching the `handsontable/` core package: fixing bugs, adding features, modifying TypeScript types, removing as-casts, writing or debugging plugins, editors, renderers, validators, cell types, hooks, shortcuts, selection, helpers, index translations, or i18n. Also use for how-to questions about core internals (plugin lifecycle, coordinate systems, hook registration, TypeScript conventions). Triggers on file paths under `handsontable/src/` (excluding `3rdparty/walkontable/` which has its own skill), or when the user describes a symptom in the core grid without naming a file. This is the primary entry point for all core Handsontable development — when in doubt, load it.

Use when writing or modifying Jasmine/Puppeteer E2E tests (*.spec.js) for Handsontable, or when a bug fix or feature change needs E2E test coverage. Covers standard boilerplate, async/await rules, global helpers, event simulation, plugin lifecycle patterns, and writing theme-agnostic assertions that pass under all themes without branching on theme name.

Use when writing or modifying Jest unit tests (*.unit.js) or TypeScript type tests (*.types.ts) for Handsontable core, plugins, or utilities, or when a bug fix or internal refactor needs unit or type test coverage - covers Jest setup, test location conventions, mocking patterns, module aliases, type test patterns (no declare, real assignments, ESM + UMD patterns), and when to choose unit tests over E2E tests

Use when Qwen Code Autofix runs from GitHub Actions or an operator dry-run to choose an approved issue, implement it, or address review feedback on an existing autofix PR.

Review changed code for correctness, security, code quality, and performance. Use when the user asks to review code changes, a PR, or specific files. Invoke with `/review`, `/review <pr-number>`, `/review <file-path>`, or `/review <pr-number> --comment` to post inline comments on the PR. Add `--effort low|medium|high` to trade depth for speed (defaults to high for PRs, medium for local changes).

Gatekeep and review GitHub issues and pull requests for Qwen Code maintainers. Use for GitHub Action issue triage, PR admission checks, product-direction review, KISS-focused PR review, and staged bilingual GitHub comments.

Apply RustFS security lessons distilled from repository GitHub Security Advisories. Use when making or reviewing RustFS code changes, doing security checks, handling PR review for auth/authz, IAM, storage, RPC, logging, CORS, console/browser, encryption, policy, or endpoint changes, and when deciding which security regression tests are required.

Execute the Adversarial Validation policy from the root AGENTS.md — run the seven reviewer roles (correctness, simplicity, security, concurrency/durability, compatibility, performance, test coverage) with RustFS-specific attack probes. Use on every behavior-affecting code change, bug fix, or design proposal before declaring it done.

Launch and supervise OpenShell gator agents. Use when starting gator on issues or PRs, checking gator sandboxes, building the gator sandbox image, restarting stuck gators, inspecting gator logs, or experimenting with gator harness/model overrides. Trigger keywords - launch gator, start gator, run gator, gator sandbox, supervised gator, gator logs, restart gator.

Debug why an OpenShell gateway deployment is unhealthy, unreachable, or unable to create sandboxes. Use when the user has a gateway health failure, Docker/Podman runtime issue, Helm install failure, Kubernetes scheduling issue, TLS secret issue, VM driver issue, or sandbox startup problem. Trigger keywords - debug gateway, gateway failing, deployment failing, helm install failing, cluster health, gateway health, gateway not starting, health check failed, sandbox pending, docker driver, podman driver, vm driver.