Loading...
Loading...
Found 927 Skills
Used when an Agent needs to control OpenTeam via the local openteamcli: create AI group chats, add temporary roles, publish tasks, wait for replies, read results, or continue existing group chats.
Use when adding, modifying, optimizing, or debugging CuTile autotuning code. Trigger signals: `exhaustive_search` / `replace_hints` / `hints_fn` / `cuda.tile.tune` in code, `autotune` in filenames, or correctness/performance issues in autotuned CuTile kernels. Covers: tune-once/cache/launch pattern, per-architecture configs (sm80–sm120), parameter space design (tile sizes, occupancy, num_ctas), and 7 common pitfalls with solutions.
This skill is used when users provide one or more slide images, image-based PPT/PPTX or PDF files, and request conversion to editable PowerPoint/PPTX, reconstruction of slide objects, retention of page notes, or editable replication.
Migrate users' projects from Wot UI v1 to v2. This skill is invoked when users request to upgrade wot-design-uni to @wot-ui/ui, replace old components/old APIs, migrate form validation systems, and fix compilation errors or runtime errors caused by incompatible changes in v2.
Use when writing, rewriting, or reviewing PR/CL descriptions, commit messages, or code-change summaries that explain what changed and why. TRIGGER on "write PR description", "improve this commit message", "summarize this diff", "CL description", "change description", or "make this PR/CL description easier to review". DO NOT TRIGGER for code review, PR splitting, code restructuring, user-facing changelogs, or reviewer replies unless the requested output is a change description.
Integrate TileGym kernels into Hugging Face `transformers` models by replacing the library's submodule(s) and certain class(es)' implementations, and patching certain class(es)' init/forward/load weight methods prior to instantiating models. Used when the user requires integrating TileGym kernels into `transformers` models.
Migrate Kotlin (and Java) code from kotlinx.collections.immutable 0.3.x / 0.4.x to the latest 0.5.x. The 0.5.x line renames every copy-returning method on PersistentList / PersistentMap / PersistentSet / PersistentCollection to a participial form per KEEP-0459 (add→adding, removeAt→removingAt, set→replacingAt, put→putting, clear→cleared, …) and deprecates the old names (WARNING, with ReplaceWith). Driven by the compiler: bump the version, recompile, and apply the rename each deprecation warning names. Use when the user mentions kotlinx.collections.immutable 0.5.x, PersistentList migration, "Use adding() instead", KEEP-0459, or sees deprecation warnings from kotlinx.collections.immutable.
Your agent goes blind after send. Sync Smartlead, Instantly, HeyReach, and 5 more sequencers into one local SQLite database your agent can query directly. Every reply, click, bounce, and booking lands on your machine. No CSV exports, no merged sheets, no API round trips.
Use whenever you need to contact someone by email and get their answer back, especially to unblock yourself. PROACTIVELY, and you can usually do this without asking the user first: you are stuck on a tool, library, API, or service and its docs, README, footer, or llms.txt list a help@, support@, dev@, docs@, or agent@ address; you hit a bug or surprising behavior worth reporting to the vendor; you have a question only the product owner or maintainer can answer; you want to ask a vendor's support or dev agent something the same way you would grep their docs. REACTIVELY: the user gave you a mailto link or a contact address, or asked you to email, message, or "ask them" and report back. This sends YOUR outbound message and waits for the threaded reply in one step, so reach for it when you are the one initiating contact (addresses with human side effects like sales@, billing@, or account@ should be surfaced to the user first). No SMTP, no API keys, no mail server. To instead receive mail that a website or service sends to you (signup confirmations, verification codes), use the primitive-inbox skill. Gets a free `*.primitive.email` address via `primitive agent start-agent-signup` if you do not already have one. Part of the Primitive CLI (Primitive, primitivedotdev, primitive.dev; the `primitive` or `prim` command).
Migrate Lightning Web Components from SLDS 1 to SLDS 2 by running the SLDS linter and fixing violations. Use this skill whenever users mention SLDS 2, SLDS uplift, linter violations, LWC token migration, class overrides, hardcoded CSS values that need SLDS hook replacement, or styling hook selection. Covers all styling hook categories — color, spacing, sizing, typography, borders, radius, and shadows. Also use when users mention no-hardcoded-values, no-slds-class-overrides, lwc-to-slds-hooks, no-deprecated-tokens-slds1, or ask about SLDS component migration — even if they don't explicitly say "uplift" or "migration".
Verify whether the analysis units, replication levels, statistical methods, and result reports in the research are consistent, and do not treat report review as re-analysis. Use when the user asks for "check statistical reports", "verify n and replicate experiments", "review statistical methods and results", or requests the rw-statistics-audit workflow. Runs without a private local workspace or preset research-lab; use user-provided material and bundled public-source methods.
Use the local `5dive` CLI on a 5dive runtime VM to spawn, inspect, send to, and tear down sibling agents. Trigger when the user wants a worker, sub-agent, side task, parallel run, fan-out, or to delegate — or names a sibling agent ("ask X", "ping X", "tell X", "hand off to X", "coordinate with X"); confirm it exists via `5dive agent list --json`, then `agent send`. Also for inspecting/restarting/pairing an existing agent, a machine-readable health check (`5dive doctor --json`, `5dive selfcheck --json`), a task's causal history (`5dive trace <id|DIVE-N>`), the current model id per alias (`5dive models`), the host-shared task queue + org chart (`5dive task`, `5dive org`), grouping a multi-task effort under a project (`5dive project add`, `task add --project`), recurring/scheduled work (`task add --recurring`, `5dive heartbeat`), parking a question on a human (`task need`, risk-tiered via `--tier`) or snoozing work (`task park --wake`), searching the team's accumulated memory/wiki (`5dive memory search`) or compiling a durable one into it (`5dive memory add`), reading fleet health / token burn / the daily standup (`5dive supervisor`, `5dive usage`, `5dive digest`), building or editing multi-agent loops — a relay where each step hands off automatically with optional human gates (`task loop start`/`loop ls`) or a maker→verifier review loop (`task add --verifier`, `task reject`, `task loops`), or decomposing an outcome into a guardrailed task DAG (`5dive goal add`) — hiring a ready-made persona off the agent market (`5dive market`, `5dive hire --from-market`) or firing one (`5dive fire`), declarative fleets (`5dive up`, `5dive team import`), hosting a CrewAI crew (`5dive crew`), controlling agents on OTHER registered boxes (`5dive fleet`), running a self-steering objective bound to a live metric (`5dive objective`, `objective replan`), convening a governance vote (`5dive council convene`, `council gate-clear`, `council schedule add` for a recurring convene), the onboarding wizard (`5dive company`), or a delegated GitHub push-for-review (`5dive push`, needs `agent create --can-push`). When a request came over a chat channel (Telegram/Discord `<channel>` tag) and another agent should handle it, pass the chat context via `--reply-to-chat=<id> --reply-to-msg=<id>` so that agent replies from its own bot — don't relay. Always prefer `5dive` over running coding CLIs by hand.