Loading...
Loading...
Found 1,176 Skills
Multi-agent coordination, inter-terminal messaging bus, distributed file/mutex locking with monotonic fencing tokens, orchestrating multi-stage DAG task pipelines, cluster health watchdog sweeping, and worker queues over Redis. Use when coordinating work between multiple AI assistants or terminal sessions, acquiring distributed mutex locks before editing shared files or running migrations/deployments, generating monotonic fencing tokens to prevent zombie writes, dispatching tasks or RPC queries to peer agents, producing/consuming from competing-consumer work queues, orchestrating multi-stage pipelines with automatic dependency resolution, reliably claiming tasks with leases and ack/DLQ handling, scattering tasks to a pool for quorum aggregation, sharing scratchpad memory, managing floor control in roundtable brainstorming, setting and checking run cancellation tokens, running blind consensus ballots without anchoring bias, electing resilient mesh leaders with automated lease failover, auditing cluster health and sweeping dead agent/listener garbage, or discovering active teammates and their status. Triggers: 'rhizo', 'coordinate with the other terminal/agent', 'talk to agent', 'send task to', 'ask the other assistant', 'inter-agent chat', 'lock file', 'lock resource', 'mutex lock', 'prevent concurrent edits', 'fencing token', 'monotonic counter', 'zombie writes', 'work queue', 'enqueue task', 'claim task', 'ack task', 'reliable queue', 'dead letter queue', 'dlq', 'blackboard', 'scratchpad', 'shared memory', 'floor control', 'speaker ring', 'moderated roundtable', 'pass floor', 'yield floor', 'cancel task', 'cancel run', 'cancellation token', 'abort run', 'ballot', 'vote', 'consensus', 'blind voting', 'leader election', 'acquire leader', 'failover', 'mesh leader', 'scatter', 'gather', 'quorum', 'workflow', 'dag', 'pipeline', 'task dependencies', 'resolve step', 'workflow next', 'sweep', 'clean dead agents', 'stale locks', 'garbage collection', 'cluster watchdog', 'who is online', 'agent status', 'rhizo', 'Redis bus'.
Organize checkout/worktree topology, dependent branch/PR stacks, and unified delivery boundaries for change workstreams using Git/GitHub: identify normalized repositories and isolate regular implementations with an owning worktree by default, with worktree also permitted by default for explicit PR requests; determine commit, push, and PR actions in order of user-specified explicit endpoints, default Draft PR for normalized repositories, and local-only default for non-normalized repositories; publish safely from main/master; follow up on conflicts, CI status, and local commit/push for existing PRs. Applicable to worktree creation, migration, secure cleanup, "branch already checked out" scenarios, post-implementation Git delivery, splitting stacked/dependent PRs, using `gh stack` to create, view, sync, or land stacks, as well as PR merge conflicts, failed checks, fixing PRs to mergeable state, and uncommitted or unpushed fixes. It only owns Git topology and delivery, and does not take over domain implementation or project design; the exact syntax of `gh stack` is discovered from local `--help` output. Default delivery does not grant authorization to implicitly switch the main working tree branch, mark as Ready, merge, retarget, release, or force-push.
Postgres schema and query rules, independent of the calling language. TRIGGER — load BEFORE writing or editing a .sql file, a migration, or any schema, index, constraint or query change against Postgres: new tables, foreign keys, status columns, claim or lease queries, backfills, ON CONFLICT upserts. SKIP for MySQL, SQLite and other engines, and for code that never touches SQL.
Build an AG2 network `workflow` channel — the orchestrated N-party adapter driven by a declarative `TransitionGraph`. Use when the user needs conditional handoffs, multi-step pipelines, context-aware routing, feedback loops, or is migrating from the classic `GroupChat` + `Agent.handoffs` pattern. Covers `TransitionGraph`; factories `TransitionGraph.sequence(...)` / `.round_robin(...)`; built-in targets (`AgentTarget`, `RoundRobinTarget`, `StayTarget`, `RevertToInitiatorTarget`, `TerminateTarget`); built-in conditions (`Always`, `FromSpeaker`, `ToolCalled`, `ContextEquals`); the typed `Handoff` return for dynamic routing; channel-scoped context via `set_context`; `register_target` / `register_condition` for custom subclasses; the packet execution model and idempotent-tool requirement; eight cookbook patterns (pipeline, hierarchical, escalation, feedback loop, triage, and more); and side-by-side migration from classic `GroupChat`. Load this after `ag2-network-quickstart`.
Read-only audit of a database layer — schema anti-patterns (EAV, generic keys, imprecise types), query and index fit (SELECT *, N+1, unindexable predicates), integrity and concurrency, migration and tenancy hygiene — with evidence per finding and a SHIP / FIX / BLOCK verdict. Use when asked to audit the database, review the schema or migrations, judge a data model, or 'проверь схему базы'. Never edits schema or data. Do not use for runtime profiling (awesome-performance-audit), SQL injection (awesome-security-audit), or data-access style (awesome-code-standards).
Authoritative reference and rules for developing with Zotero — the Web API v3 (read/write requests, file upload, syncing, streaming, OAuth, item types & fields), the desktop client's internal JavaScript API, building Zotero plugins (7–10, incl. Zotero 10 migration notes), writing translators (web/import/export/search), and creating/editing CSL citation styles. Use whenever the user asks to query or write to a Zotero library via the API, build or debug a Zotero plugin, write a Zotero translator, work with citeproc-js / CSL styles, sync Zotero data programmatically, or script the Zotero client.
Actively use when the user requests software development, bug fixing, project continuation, refactoring, migration, or infrastructure changes; first confirm the host, installation scope, and same-source integrity, supplement the DevFlow Skill and the current platform's native roles as needed, and then continuously route four-role delivery. Explanations, general advice, standalone review or testing, documentation-only changes, and minimal risk-free edits do not start the full process.
Clean, profile, validate, reshape, and document messy tabular, text, JSON, and relational data through an evidence-first, reproducible workflow. Use when preparing data for analysis, reporting, modeling, ingestion, migration, or matching, including AI-suggested repair, entity-match review, score calibration limits, and reversible repair ledgers. Do not use for statistical modeling, dashboard design, or operating a named data platform; route those tasks to data-scientist, data-engineering, or the relevant tool skill.
Reports how hardcoded style values on a page, file or diff map onto a project's existing design tokens, purpose first, then value. Use for "are we using our tokens here", "which hardcoded colors map to which tokens", a token audit or planning a token migration. It never edits and never creates or renames tokens. Fixes and whole-app consistency go to design-system-boss.
Plan and execute infrastructure, architecture, and database migrations; choose and explain a strategy with the user, build a parallel alternative, transfer traffic, and retire the legacy path.
Write, review, audit, refactor, and diagnose POSIX `sh` code and configuration. Use it whenever code is intended to run under a POSIX shell or a migration targets POSIX `sh`. Use it across `.sh` files, `#!/bin/sh` entrypoints, extensionless commands, sourced libraries, hooks, startup fragments, generated shell fragments, and other shell code with no identifiable shell dialect. Do not use when the requested output is only code for a non-POSIX shell.
SuiteScript 1.0, 2.0, and 2.x to 2.1 migration assistant. Analyzes, converts, explains, and validates script upgrades. Covers 125+ API mappings, 34 object conversions, 13 unmapped API workarounds, all script type entry point changes, SuiteScript 2.0/2.x to 2.1 upgrade guidance, and 16 categories of breaking behavioral changes. Essential for modernizing legacy SuiteScript codebases.