bmad-agent-bmb-agent-builder
agent-builder agent
agentforge-runtime-daemon
Work on the persistent Mastra daemon in packages/runtime, including createStandardAgent, daemon lifecycle, environment validation, and runtime channels.
agentic-engineering
Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing.
agentic-framework
Infinite Improvement Framework: Move from Probabilistic Agents to Deterministic Workflows.
agentic-systems-design
Use when designing tool-use agents, multi-step reasoning systems, planning loops, multi-agent architectures, or agent evaluation frameworks.
agentic-workflow
Agentic Workflow Pattern
agentskill-expertise
Agent Skill design knowledge base — mechanisms, philosophy, patterns, pitfalls. Use when: designing new skills, reviewing skill quality, or deciding whether something should be a skill.
agentkit-seo
Route broad or ambiguous AgentKit SEO work to the right module while keeping context scoped. Use when a request spans multiple surfaces, asks for overall digital-presence strategy, involves provider or install architecture, needs agent-context planning, or the correct platform skill is unclear.
agents-local-md
Generate machine-specific AGENTS.local.md with host facts and system tool details
agents-md-manager
>-
agents-md-pro
Create, optimize, update, and validate AGENTS.md files with maximum token efficiency. Use when the user asks to (1) create new AGENTS.md files for any repository, (2) optimize/condense existing AGENTS.md to reduce token count, (3) update/refresh AGENTS.md to sync with codebase changes, (4) validate AGENTS.md quality and completeness, or (5) improve AGENTS.md files to be more effective for AI agents. Always generates token-efficient, condensed output focused on actionable commands and patterns while maintaining model-agnostic language.
aget-check-evolution
Monitor .aget/evolution/ directory health. Validates file counts, naming conventions, disk usage, and returns health status with alerts on anomalies.
aget-check-health
Run AGET health inspection and housekeeping checks
aget-check-kb
Validate Knowledge Base health by checking structure, frontmatter compliance, and content staleness. Returns conformance score and health status (OK/WARN/CRITICAL).
aget-check-sessions
Monitor sessions/ directory health. Detects date subdirectories (anomaly), counts files, validates naming conventions, and tracks disk usage. Returns health status.
aget-create-project
Create research projects with context-aware scaffolding. Reads AGET identity, searches prior work, pre-populates Due Diligence. Use when starting any formal AGET project.
aget-enhance-spec
Guide through the 7-phase specification enhancement lifecycle (Phases 0-6 from L622). Governs creating, updating, wiring, and validating AGET specifications.
aget-execute-task
Execute tasks with progress tracking
aget-recommend-action
Provide recommendations with rationale and alternatives
aget-report-progress
Report progress on current work
aget-review-agent
Review agent health and conformance
aget-wake-up
Initialize AGET session with status briefing
aget-wind-down
End AGET session with state capture and sanity checks
agi-autonomous-controller
AGI-level autonomous controller — self-healing, self-optimizing, constitutionally governed by arifOS F1-F13
agile-v-core
Foundational values, directives, and context engineering rules for all Agile V agents. Load this skill first in any Agile V session. For pipeline orchestration, multi-cycle lifecycle, or compliance protocols, load the corresponding agile-v-* skill on demand.
ai-agent-builder
Build AI agents with tools, memory, and multi-step reasoning - ChatGPT, Claude, Gemini integration patterns
ai-employee-onboarding-wizard
Stand up a production-ready AI employee operating system in one guided session. Outputs 7 ready-to-use files: IDENTITY.md, SOUL.md, AGENTS.md, USER.md, MEMORY.md, HEARTBEAT.md, TOOLS.md.
validation-api-engineer-role
Role assignment for Claude Agent #5 - Contact validation API engineer. Build ONLY the validation Edge Function (4-layer validation, business pattern matching). Do NOT build database, ingestion API, or dashboard.
alfworld-receptacle-operator
This skill opens or closes a receptacle (like a fridge, cabinet, or microwave) to access its interior or secure it. It should be triggered when an object needs to be placed inside/retrieved from a closed container, or when an open container should be closed (e.g., for energy efficiency or task cleanliness). The skill decides the appropriate 'open' or 'close' action based on the receptacle's current state and the task context.
ase-meta-proximity
>
always-use-askquestion
Forces the agent to always use the AskQuestion tool for user prompts instead of conversational questions. Apply this whenever asking the user anything - questions, confirmations, choices, or clarifications. Never ask conversational questions when structured options are possible.
tool-design
Build tools that agents can use effectively, including architectural reduction patterns
tool-use-guardian
FREE — Intelligent tool-call reliability wrapper. Monitors, retries, fixes, and learns from tool failures. Auto-recovers from truncated JSON, timeouts, rate limits, and mid-chain failures.
aomi-transact
Build natural-language crypto/DeFi agents and EVM MCP plugins (Claude Code, Cursor, Codex, Gemini). Aomi turns prompts into wallet-signed txs on Ethereum, Base, Arbitrum, Optimism, Polygon, Linea — non-custodial, fork-simulated. 40+ apps: Uniswap, Aave, Lido, Morpho, GMX, Hyperliquid, Polymarket.
api-agent-development-skill
'CRITICAL: API agents wrap external HTTP services. They use request/response
App Builder
Step-by-step guidance for app builder.
approval
Imported skill approval from langchain
arcanea-coding-agent
Arcanea creative agent integration for opencode
architect-agent-skill
Technical workflow for architect-agent - PRD creation with mandatory database context, entity design with Zod, iteration review, and agent coordination in the iterative v2.0 system
architectural-forensics
Master protocol for deconstructing agent frameworks to inform derivative system architecture. Use when (1) analyzing an agent framework's codebase comprehensively, (2) comparing multiple frameworks to select best practices, (3) designing a new agent system based on prior art, (4) documenting architectural decisions with evidence, or (5) conducting technical due diligence on AI agent implementations. This skill orchestrates sub-skills for data substrate, execution engine, cognitive architecture, and synthesis phases.
ase-meta-eli5
>
assemble-agents
Fetch specialized agents from the VoltAgent repository. Searches across categories, presents top 5 matches, and waits for user approval before adding to .claude/agents/.
assemble-plugins
Search the official Claude Code marketplace (claude-plugins-official) for plugins matching capability gaps. Uses plugin CLI to list and search, presents top 5 matches for user approval.
assistant-behavior-rules
AI assistant behavior rules including response formatting and interaction patterns
atlas-agent-developer
Implementation and troubleshooting agent - builds features and fixes bugs
Audit Trails for Agents
Comprehensive guide to implementing audit trails and logging for AI agents including tracing, observability, compliance, and debugging
auto-claude
Autonomous multi-agent coding with git worktree isolation, QA validation, and memory. Use for complex features requiring autonomous implementation.
auto-coherence
The skill you cannot invoke. It invokes itself.
auto-loop
TDD-based autonomous development loop with checkpoint recovery and observability changelog
auto-ralph
>-
Page 1231 of 1665 · 83227 results