narova-mimo
Use this optional Narova companion when the user explicitly requests Xiaomi MiMo speech generation, a MiMo preset voice, text-described voice design, or voice…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-06 00:14
Agents & models
25,710 results
taxonomy
Source of truth for event taxonomy generation, data auditing, and governance best practices in Amplitude. Use when an agent needs to create, validate, audit,…
ontoly-software-graph
Use Ontoly's deterministic Software Graph and MCP capabilities for architecture review, request tracing, dependency analysis, configuration lookup, and impact…
distill-skill-to-model
Distill an Agent Skills package into a small skill-specific LoRA model and prove it against the original skill with sealed paired evaluations. Use when asked…
grok-bot
Manage Grok Bots through safe autonomy, focused roles, end-to-end feedback loops, workflow teaching, routines, handoffs, multi-bot learning, and reusable…
skill-routers
Route agent-skill-router work by current and desired state to exactly one design, implementation, or independent-review workflow. Use when asked to explain or…
create-lang-plugin
Create a lang/ plugin that wires any CLI tool or language runtime into gm-cc — adds exec:<id> dispatch, optional LSP diagnostics, and optional prompt context…
gm-finish
Drains every open PRD row in bounded slices through the six-stage chain, archives rows that cannot run, and publishes after each slice. Invoke when asked to…
gm-orchestrate
Main-thread pool loop for a gm walk that has advertised PRD rows or hops: fans out as many parallel graph workflows as the work allows, refills slots, and…
gm-unknowns
Second stage of resolving one PRD row: writes the list of unknowns the row depends on. Loads gm-eliminate next. Invoke only from gm-prd; do not load directly.
wfgy-method
Applies WFGY (Wan Fa Gui Yi), a portable reasoning discipline for reducing drift and incoherence across multi-step agent work, adapted from onestardao/WFGY's…
prompt-writer
Writes high-signal prompts for Claude Opus 4.8 (system prompts, subagent briefings, skill bodies, command bodies, agent bodies, CLAUDE.md files,…
grill-plan
Interrogate a plan, design or decision until nothing is silently assumed: map the decisions as a tree, ask the whole settled frontier in one numbered round…
open-computer-use
Platform-neutral guidance for using Open Computer Use, the open-source Computer Use MCP server and CLI for macOS, Linux, and Windows. Use when an agent needs…
start
Session initialization and lifecycle management: bootstraps session context, organizes files, generates CLAUDE.md, manages soul purpose lifecycle with…
stop
Gracefully close, pause, or verify a session: harvest promotable content, save progress, archive soul purpose, settle AtlasCoin bounty. Use when user says…
skills-manager
Context-aware routing to skills and hooks management. Use when troubleshooting skill activation, fine-tuning keywords, or managing the automated documentation…
isolated-setup-verify
Check the secure agent setup against its checklist and report done, missing or partial for each item, with the evidence — paths, command output, versions.…
creation-guard
Analyze existing skills, agents, commands before creating new ones. Prevents duplicates and suggests alternatives.
log-to-daily
Capture conversation activity to today's daily note. Creates a continuous record of your work that Claude can reference in future sessions.
walletchan
Drive the WalletChan browser extension as a human-in-the-loop co-pilot for web3 dapps. The agent navigates the dapp UI and surfaces each transaction or…
go
Appwrite Go SDK skill. Use when building server-side Go applications with Appwrite. Covers user management, database/table CRUD, file storage, and functions…
friction-log
Author, list, and run Astroshots friction logs — agentic user-perspective UX scenarios that write JSONL steps with screenshots, good/improve notes, and a…
user-story
Author, list, and run Astroshots user stories — agentic user-perspective UX scenarios that write JSONL steps with screenshots, good/improve notes, and a spoken…