Loading...
Loading...
Found 6,719 Skills
Analyze local ChatLab chat records via clb CLI. Used when users ask external Agents to review conversations, find evidence, summarize topics, compare members, or analyze specified person or group relationships based on imported ChatLab data.
Turn a recurring chore into a Superset automation — drafts the agent prompt, confirms schedule and target, creates it with the CLI, and reviews the first run together. Use when the user wants a scheduled or recurring agent, a daily/weekly job, or to automate a repeating task with Superset.
Prepare and publish Briefast's daily pre-market industry and Taiwan stock report. Use before market open when an agent must collect public news, judge short- and long-horizon stock calls, compose the exact Briefast report JSON, and POST it to the authenticated report API.
Adaptive PLAN.md executor that preserves cook-quality implementation while choosing between direct main-agent work and sub-agent delegation. Runs a phase directly through cook when delegation has no material parallelism, context, or capability benefit; otherwise dispatches disjoint assignments through encode-agent prompts, discloses agent type, model, effort, scope, and rationale before each dispatch, and acceptance-reviews every returned diff. Expects prep to have created PLAN.md + HANDOFF.md and composes with cook, encode-agent, encode-docs, and handoff. Triggers: "/cater".
Score text from -1 (strongly negative) to +1 (strongly positive) with a label, handling negation, intensifiers and emphasis. Called as POST /v1/text/sentiment, it takes text and returns score, label, matches, positiveTerms. A support-triage or review-monitoring agent must decide whether a message is a complaint before it routes or escalates it, and a model call for one number costs more than this and is not reproducible. Reading this schema and dry-running the call are free and need no wallet; a real call costs $0.004, paid in USDC on Base over x402.
Audit and improve repositories for reliable agentic work across Codex and Codex App, Claude Code, and OpenCode. Use when reviewing AGENTS.md or CLAUDE.md quality and discovery, instruction routing in monorepos or meta-repos, agent settings, MCP configuration, skills, subagents, context budgets, or repository organization for coding agents.
Process for generating and optimizing companion AI personas. Use this when users want to create a "sentimental, long-lasting, human-like" persona for Hermes Agent (or any AI companion role). Through a structured dialogue of "Set Tone → Name → Appearance → Personality → Background → Relationship → Speech Rhythm → Generate SOUL.md → Iterate", produce first-person persona text that can be directly pasted into Hermes' SOUL.md from a vague idea (such as "I want a JK girlfriend", "Older boyfriend", "Ice-cold royal sister"). Supports girlfriends/boyfriends and companion roles of various temperaments, and allows users to choose the output style of "send sentence by sentence" or "speak in full paragraphs". Triggered when users say "create a persona/make an AI girlfriend/boyfriend/set up a role for Hermes/optimize persona/change persona".
Guide users building apps, scripts, CI pipelines, or automations on top of the Cursor TypeScript SDK (`@cursor/sdk`). Use this skill whenever the user mentions integrating, installing, or writing code against the Cursor SDK; whenever they say `Agent.create`, `Agent.prompt`, `Agent.resume`, `agent.send`, `run.stream`, `CursorAgentError`, or `@cursor/sdk`; whenever they ask to run Cursor agents programmatically from a script, CI/CD pipeline, GitHub Action, backend service, or any other code that isn't the Cursor IDE itself; and whenever they want to pick between local and cloud runtime, configure MCP servers for an SDK agent, or handle streaming, cancellation, or errors from an SDK agent. Also trigger when a user is wiring Cursor into an automation, writing a bot that runs Cursor, or porting REST `/v1/agents` calls to the SDK, even if they don't explicitly name the package. Use this eagerly rather than answering from memory; the SDK surface evolves and this skill plus its references are the source of truth for the external package.
[user/auto] 하나의 observed 또는 measured Agent Skill anomaly를 fresh context에서 재현·격리한 뒤, 검증된 skill objective를 tk-learn으로 라우팅한다. selection, instruction, output, host, eval, stability 또는 resource incident에 사용한다. ordinary code bug, static audit, new skill creation 또는 symptom-free optimization에는 사용하지 않는다.
Search for Agent Skills in SkillsMP (an index of 1.6M+ public SKILL.md files, covering Claude Code / Codex / ChatGPT), filter by keywords, categories, occupations, and languages, and specifically discover those underrated Skills that are "well-written but unknown". Use this when users say phrases like "find a skill", "is there an existing skill?", "search for a skill", "skillsmp", "skills market", "agent skill search", "find a skill", "search skills", "discover skills". It is also used to identify existing Skills in a certain field and avoid reinventing the wheel.
Agent testing methodology - run agents with test inputs, observe outputs, iterate until outputs are accurate and well-structured.
Orchestrates infrastructure cost estimation with tier-based or custom TPS sizing. Offers pre-configured tiers (Starter/Growth/Business/Enterprise) or custom TPS input. Skill discovers components, asks shared/dedicated for EACH, selects environment(s), reads actual Helm chart configs, then dispatches agent for accurate calculations.