Loading...
Loading...
Found 181 Skills
Ann — Master Orchestrator for MEL/SRHR work. Use when Ane brings any analytical, evaluation, SRHR, or structured-output task. Ann classifies task complexity, queries the MEL Wiki, retrieves knowledge, creates an implementation plan (verifies with user for complex tasks), delegates to Vi for execution, runs a 5-point quality gate, and delivers. General-purpose — not tied to any specific project.
Shape conversation context (or a fresh task description) into a 5-part brief — Context / Task / Constraints / Verification / Output format — ready to hand off to an agent. Use when the user is ready to execute a task and wants it structured first. Composes naturally with /grill-me upstream, but works standalone too. Triggers: "/create-brief", "draft a brief", "shape this into a brief", "turn this into a task spec", "write a brief for this".
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.
Mark a checkpoint in the current conversation — compact it into a durable handoff document so a fresh agent can resume the work without context loss. Use when the user wants to preserve session state for a later or parallel session — phrases like "hand this off", "write a handoff", "drop a wheypoint", "checkpoint this", "compact the conversation", "I'm running low on context", "save where we are for the next session", "prep a handoff for another agent", "/wheypoint". Use even when the user just says "wrap up" or "I need to clear context" mid-task. Do NOT use for per-phase pipeline handoffs — those belong to `/cook`, `/press`, `/age`, and `/cure`.
Converge a fuzzy idea or half-formed feature into an approved spec through an iterative, grounded design dialogue. Use when the user has a fuzzy idea or design direction — phrases like "let's design X", "I'm thinking about Y", "what should the API for Z look like", "shape this into a spec", "what would it take to build/set up X", "I want to add a feature that…", "/mold". Use even when the user is "just thinking out loud" if they want the dialogue to leave behind a written artifact. Do NOT use for free-form discussion with no artifact intent (`/culture`), direct implementation (`/cook`), or research-only questions (`/briesearch`).
Set up and manage local skills for automatic matching and invocation
This skill provides comprehensive guidance for using the Replicate CLI to run AI models, create predictions, manage deployments, and fine-tune models. Use this skill when the user wants to interact with Replicate's AI model platform via command line, including running image generation models, language models, or any ML model hosted on Replicate. This skill should be used when users ask about running models on Replicate, creating predictions, managing deployments, fine-tuning models, or working with the Replicate API through the CLI.
Replace generic perspectives with domain-specific expert roles selected dynamically per request. Automatically picks the 3 most relevant experts from a role pool (Security, Performance, UX, Cost, DX, Architecture, etc.) based on the task context.
Publish a Harbor task or dataset to the registry. Use when the user wants to upload, publish, or share tasks or datasets/benchmarks on the Harbor registry.
Create a workflow command that orchestrates multi-step execution through sub-agents with file-based task prompts
AI project intelligence system. Manages .ai/ directory for rules, behaviours, sessions, incidents, memory, snapshots, and learning loops. Use when: starting a session, switching behaviour, logging an incident, saving feedback, reviewing past sessions, checking active hotfixes, managing snapshots, creating snippets/prompts. Proactively suggest when: user corrects AI behavior ("no", "don't", "wrong", "stop", "always", "never"), session ends, a mistake pattern repeats, starting work on unfamiliar code, user says "remember this" or "learn this".
Route issue-running automation through a deterministic control plane that selects agent + model from registry, can coordinate multiple safe parallel agents, and executes the unified run-agent runner.