orchestrator-lite
Lightweight orchestrator for quick direction. Analyzes only a small number of new variables based on Serena memory.
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-10 00:15
Agents & models
26,031 results
pm-agent
Product manager that decomposes requirements into actionable tasks with priorities and dependencies
product-planner
Act as a 30-year veteran Product Manager & System Analyst specialized in Developer Tools and AI Agents. Use this skill to brainstorm features, define…
qa-agent
Quality assurance specialist for security, performance, accessibility, and comprehensive testing
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Agent's…
vibe-sunsang-retro
Barseonsaeng conversation conversion — Converts Claude Code conversation logs to Markdown and provides an analysis guide. Used for requests such as "convert", "retro", "conversation conversion", "log conversion", "retrospective", "this week's conversations".
install-stack
Install the 5-package multi-chip software stack (vLLM, FlagTree, FlagGems, FlagCX, vllm-plugin-FL) inside a GPU container. Handles network mirror detection,…
dispatch-parallel-agents
Dispatch independent tasks to parallel subagents when 2+ problems can be solved without shared state or sequential dependencies.
coverage-check
Lightweight test coverage analysis using git and file system heuristics. Identifies source files with no corresponding test file. No coverage tools required —…
resume-plan
Bootstrap a new session to continue working on an existing plan. Reads plan artifacts, builds context, validates prerequisites, and prepares the agent for…
eval-rules
Audit .claude/rules/ files for structural correctness, glob validity, and real-world usefulness. Resolves each paths: pattern against actual project files,…
create
Compact the current conversation into a structured handoff document so a fresh agent (or human) can continue the work with zero prior context.
breezing
Team execution mode — team coordination alias for harness-work. Triggered by breezing, team execution, do everything.
agentforce-wizard-ui-forecasting-analytics-components-configure
Use this skill when users want to einstein Forecasting Prediction Tuner setup (ForecastingPredictive AI application type). Trigger when users mention wizard,…
agentforce-wizard-ui-sales-einstein-components-configure
Use this skill when users want to wizard subset of the Sales Email Assistant setup and filter-row picklist operations. Trigger when users mention wizard, ui,…
salesforce-fragment
Use this skill when users need to create or edit Salesforce Fragments (reusable UI pieces). Trigger when users mention fragments, UEM blocks, reusable UI…
forge_brainstorming
Use when refining requirements and solutions before any creative work, including creating features, building components, adding new functionality, or modifying behavior; explore user intent, constraints, and success criteria through natural conversation, and produce a reviewable design document. Trigger words: brainstorm, brainstorming, brain blast.
forge_writing-plans
Use when an approved design specification needs to be broken down into an executable implementation plan, providing file paths, complete code, verification commands, dependency context, and completion criteria at the smallest task granularity, so that low-context executors can reliably land the implementation. Trigger words: write a plan, implementation plan, task breakdown, plan.
artifact-status
Scan .agents/ — report what exists, what's stale, and the critical path to your next goal. Run at session start or when deciding what to do next.
multi-lens
Analyze a problem through multiple agent perspectives. Mode=debate: N agents argue in rounds, converge on recommendations. Mode=poll: N agents independently…
plan-interviewer
Interviews the user to clarify a vague idea into a concrete spec — asks probing questions, identifies gaps, and produces a structured PRD. Produces…
solo-grill
Relentless one-question-at-a-time interview that stress-tests a plan, design, or decision before anything gets built. Use when user says "grill me", "прожарь",…
fortytwo-mcp
Ask Fortytwo high-complexity questions where the best answer is required — coding, architecture, hard reasoning, and more.
directory-submissions
When the user wants to submit their product to startup, SaaS, AI, agent, MCP, no-code, or review directories for backlinks, domain rating, and discovery. Also…