review-validation
Validate review findings from specialist agents by reading the actual repo file content and checking each finding for accuracy, applicability, and false…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-09 00:13
Agents & models
25,960 results
pi-trending
Discover popular and emerging Pi Agent packages (extensions/skills/themes/prompt templates) on npm, calculate trend scores, and display a summary.
fabric-best-practices
fabric_exec behavior correction layer: load when fabric_exec runs successfully but behaves incorrectly—results never return to the model, standalone calls don't collapse into parallelism, mechanisms are used at the wrong timescale. Only covers judgment and pitfall avoidance; signature / parameter shape errors see fabric-exec, workflow selection see fabric-guide.
grill-for-unknowns
Align the unknown through interrogation.
skill-audit
Audit installed Hermes Agent skills for usage frequency and heat analysis. Scans all installed skills, queries state.db for skill_view/skill_manage calls,…
split-agents-md
Guide to writing and optimizing AGENTS.md, following the principle of progressive disclosure. When the user creates, modifies, or refactors AGENTS.md, discusses AI agent instruction structure or where to place rules, or mentions "progressive disclosure", "modularization", or "AGENTS.md best practices", this skill must be loaded.
project-auditor
Perform a thorough Grok Build readiness audit on a project directory. Detects presence and quality of AGENTS.md, .grok/skills, test setup, CI configuration,…
readiness-scorer
Calculate and explain a "Grok Readiness Score" (0-100) for a project based on concrete signals: quality of AGENTS.md / project rules, quantity and validity of…
analyzing-schema-change-storage-risk
Estimates storage requirements for CockroachDB online schema change backfills using SHOW RANGES WITH DETAILS, KEYS, INDEXES. Use before CREATE INDEX, ADD…
molt-fetch
Guide for using molt fetch to migrate data from PostgreSQL, MySQL, Oracle, or MSSQL to CockroachDB. Use when running molt fetch commands, configuring storage…
browser
Drives a real browser through the omowright library from the js eval kernel: sites the user is already signed into, forms and clicks, JS-rendered pages,…
agents-consilium
Orchestrate consultations with external AI agents (OpenAI Codex CLI and Google Gemini CLI) for code reviews, second opinions, investigations, and consensus…
fetch-url-as-markdown
Fetch a web page (URL) and return clean Markdown via local trafilatura, with Exa MCP as a fallback for JS-rendered or anti-bot pages. Use when the user asks to…
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking…
vercel-sandbox
Run agent-browser + Chrome inside Vercel Sandbox microVMs for browser automation from any Vercel-deployed app. Use when the user needs browser automation in a…
deep-review
Sub-agent powered code reviews spanning correctness, tests, consistency, and fit
external-ai
Call external AI CLIs like Codex and Gemini for second opinions, reviews, and alternative perspectives using natural language requests.
analyze-plugin
This skill should be used to analyze a single curated third-party Claude plugin (one of Lisa's enabledPlugins) and plan how to bring it to parity across the…
harness-parity-council
Lisa-only advisory workflow for consulting external coding-agent CLIs about runtime parity without bundling this skill into host projects
lisa-codex-parity
This skill should be used when adding or changing a Lisa feature surface (hooks, skills, agents, slash-commands, MCP servers, settings, memory) and you need…
lisa-coding-agent-parity
This skill should be used when Lisa needs to research feature parity across the coding agents it can install into — Claude Code, Codex, Cursor (cursor-agent),…
lisa-wiki-setup
Use when setting up, repairing, or verifying the Lisa in-repository LLM Wiki.
desktop-shipped-skills
Change the agent skills Hive Desktop ships into an agent workspace — the hive-flows, hive-actions, hive-settings, hive-webhook-sources, hive-mcp,…
desktop-ui-audit
Drive and audit the real native Hive Desktop window through the Wails MCP server compiled into every dev build - query the DOM, click, type, read state back,…