jam
Structured multi-approach exploration using parallel perspective panels to generate, implement, and evaluate distinct variants, then synthesizes the best…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-01 00:15
Agents & models
25,377 results
omakase-off
Intercepts build/create/implement requests as an entry gate and offers a choice between brainstorming together or omakase (chef's choice parallel design…
modular-synthesis-philosophy
Apply modular synthesis principles to system design, workflow architecture, and conceptual frameworks. Use when designing modular systems, creating…
erc-8004
Register AI agents on Ethereum mainnet using ERC-8004 (Trustless Agents). Use when the user wants to register their agent identity on-chain, create an agent…
refining-workflows-from-artifacts
Refines a reusable agent workflow based on an actual execution result, review, failure, or simulation output. Classifies problem causes…
ac-stop-hook-analyzer
Analyze context and decide on continuation via Stop hook. Use when determining if work should continue, analyzing completion status, making continuation…
autonomous-session-manager
Session lifecycle management for autonomous coding. Use when starting new coding sessions, resuming work, detecting session type (init vs continue), or…
claude-advanced-tool-use
Advanced tool use patterns including tool search, programmatic calling, and production orchestration. Use when scaling to 10,000+ tools, optimizing token…
claude-context-management
Comprehensive context management strategies for cost optimization and infinite-length conversations. Covers server-side clearing (tool results, thinking…
claude-opus-4-5-guide
Comprehensive guide to Claude Opus 4.5, Anthropic's most intelligent model with effort parameter for reasoning control. Covers model capabilities, benchmarks,…
multi-ai-skill-builder
Meta-skill for building Claude Code skills using Multi-AI research, planning, and implementation. Coordinates Claude, Gemini, and Codex for comprehensive…
generate-ors-env
Builds an Open Reward Standard (ORS) variant of an RL environment using the official `openreward` Python package. Use whenever someone asks to scaffold an ORS…
audit-agent-context
Audit whether the current repo's AGENTS.md and/or CLAUDE.md still reflect the project reality (structure, commands, conventions, scope) and report…
create-harness
Guide the user, step by step and with questions, to design their own harness — a small, single-purpose workflow, assembled from the combination of…
goal-gate
Gate whether a coding-agent task benefits from a durable, verifiable contract, then draft, validate, start, continue, or close it for Codex, Grok, Claude Code,…
remember
Save branch context or project learnings as agentic memory
meta-planning-ai-planning
AI specification planning frameworks. Use when a spec touches model calls, prompts, retrieval, tool calling, agentic loops, or evals. Covers approach…
mobile-storage-watermelondb
WatermelonDB reactive local database for React Native - schema, models, decorators, reactive queries, relations, writers/readers, batch operations, migrations,…
analyzing agentscope library
This skill provides a way to retrieve information from the AgentScope library for analysis and decision-making.
telegram-bot-flow-patterns
Implement a multi-step Telegram bot conversation. Covers five session-FSM primitives (typed step enum, cancel, per-step handler, flow-timeout sweeper,…
spec-kit-clarify
Use when an existing Spec Kit `spec.md` has high-impact ambiguity (for example `[NEEDS CLARIFICATION]`, unresolved scope decisions, or unquantified…
algolia-agent-studio
Product-specific Algolia Agent Studio implementation, validation, and optimization guidance. Use when planning, building, integrating, or auditing Agent Studio…
asta-flows
Plan and execute autonomous research as a graph of typed tasks tracked in beads. Use when working from a mission.md to drive multi-step research with explicit…
altinity-clickhouse-expert
ClickHouse incident response, periodic audits, and ad-hoc debugging via focused agents (run in waves). Uses ClickHouse system tables to diagnose slow…