Agents
Agents d’IA i automatització
specification-writing
EpicenterHQ
Write technical specifications that give agents enough context to implement features while leaving room for autonomous research and decision-making. Use when planning features, documenting architecture decisions, or creating implementation guides.
context-compression
guanyang
This skill should be used when the user asks to "compress context", "summarize conversation history", "implement compaction", "reduce token usage", or mentions context compression, structured summarization, tokens-per-task optimization, or long-running agent sessions exceeding context limits.
dbos-typescript
dbos-inc
DBOS TypeScript SDK for building reliable, fault-tolerant applications with durable workflows. Use this skill when writing TypeScript code with DBOS, creating workflows and steps, using queues, using DBOSClient from external applications, or building applications that need to be resilient to failures.
langchain
vamseeachanta
Build production-ready LLM applications with chains, agents, memory, tools, and RAG pipelines using the LangChain framework
interview-me
mycelium-hq
Use when an ask is underspecified ("build me X" without who it's for, why now, or what success looks like), when a request is conventional rather than specific ("a dashboard", "make it faster" with no number), when Claude catches itself silently filling in ambiguous requirements before any plan, spec, or code exists, or when the user says "interview me", "grill me", "are we sure?", or "stress-test my thinking". Needs a live user; not for CI, scheduled runs, or autonomous loops.
evolve
mycelium-hq
Use when many related hardened instincts (high-confidence feedback_*/discovery_* memories) have piled up in one domain, when the user runs /evolve or asks to promote, cluster, graduate, or consolidate accumulated instincts into a Command, Skill, or Agent, or when files in Instinct Proposals need review. Part of the Instinct Engine. Not for one-off pattern capture (use patterns), daily journaling, or sharing instinct packs (use instinct-export / instinct-import).
prompt-engineering
cosmix
Designs and optimizes prompts for large language models including system prompts, agent signals, and few-shot examples. Covers instruction design, prompt security, chain-of-thought reasoning, and in-context learning for orchestrated AI agents. Trigger keywords: prompt, LLM, GPT, Claude, AI, system prompt, user prompt, few-shot, chain of thought, CoT, in-context learning, prompt template, prompt injection, jailbreak prevention, agent signal, agent instruction, agent orchestration, reasoning, instruction tuning.
recall-sessions
allenhutchison
Search past agent conversations to recall prior discussions, decisions, and context. Activate this skill when users ask about previous conversations, want to resume past work, or reference earlier decisions.
cosmos-dbt-core
astronomer
Use when turning a dbt Core project into an Airflow DAG/TaskGroup using Astronomer Cosmos. Does not cover dbt Fusion. Before implementing, verify dbt engine, warehouse, Airflow version, execution environment, DAG vs TaskGroup, and manifest availability.
customaize-agent:create-workflow-command
NeoLabHQ
Create a workflow command that orchestrates multi-step execution through sub-agents with file-based task prompts
customaize-agent:context-engineering
NeoLabHQ
Understand the components, mechanics, and constraints of context in agent systems. Use when writing, editing, or optimizing commands, skills, or sub-agents prompts.
sadd:do-and-judge
NeoLabHQ
Execute a task with sub-agent implementation and LLM-as-a-judge verification with automatic retry loop
customaize-agent:agent-evaluation
NeoLabHQ
Evaluate and improve Claude Code commands, skills, and agents. Use when testing prompt effectiveness, validating context engineering choices, or measuring improvement quality.
customaize-agent:apply-anthropic-skill-best-practices
NeoLabHQ
Comprehensive guide for skill development based on Anthropic's official best practices - use for complex skills requiring detailed structure
customaize-agent:create-agent
NeoLabHQ
Comprehensive guide for creating Claude Code agents with proper structure, triggering conditions, system prompts, and validation - combines official Anthropic best practices with proven patterns
fpf:propose-hypotheses
NeoLabHQ
Execute complete FPF cycle from hypothesis generation to decision
customaize-agent:test-skill
NeoLabHQ
Use when creating or editing skills, before deployment, to verify they work under pressure and resist rationalization - applies RED-GREEN-REFACTOR cycle to process documentation by running baseline without skill, writing to address failures, iterating to close loopholes
dart-audit-agent-compliance
dartsim
"DART Audit Agent Compliance: audit and fix gaps when agents miss or cannot discover documented rules"
moai-workflow-thinking
modu-ai
Sequential Thinking MCP and UltraThink mode for deep analysis, complex problem decomposition, and structured reasoning workflows. Use when performing multi-step analysis, architecture decisions, technology selection trade-offs, breaking change assessment, or when --ultrathink flag is specified. Do NOT use for simple decisions or straightforward implementation tasks.
deepchat-data-import
ThinkInAIXYZ
Help developers build third-party tools that import, inspect, migrate, or analyze DeepChat data. Use when Codex needs to work with DeepChat provider configuration, model configuration, MCP/app settings, sessions, messages, legacy chat data, agent.db, chat.db, SQLCipher encrypted SQLite, Electron safeStorage wrapped passwords, Tauri importers, or native macOS/Windows/Linux data access.
memory-management
ThinkInAIXYZ
Guide the agent to recall, remember, and route durable learning into Memory, Skills, Scheduled Tasks, or Tape.
workflow-automation
JoelLewis
"Workflow automation for securities operations: BPM concepts, task routing, approval chains, escalation rules, SLA monitoring, and process orchestration patterns."
ralph-wiggum
fstandhartinger
Autonomous AI coding with spec-driven development. Implements Geoffrey Huntley's iterative bash loop methodology where agents work through specs one at a time, outputting a completion signal only when acceptance criteria are 100% met.
hai-razor
hylarucoder
Audits whether each requirement, workflow step, role, field, state, module, layer, abstraction, or rule deserves to exist and returns a razor verdict: an evidence table, a Keep/Merge/Defer/Delete/Replace/Prove-first classification of every concept, the strongest survival argument for anything cut, the complexity that must be preserved, a concrete cut/proof list, and — for full audits — before/after Mermaid diagrams plus an HTML report. Use whenever the user wants to apply Occam's razor, simplify or trim a PRD / architecture / workflow / data model / state machine, challenge whether something is necessary, or spot fake requirements, premature abstractions, or over-engineering — even if they never say "razor." Trigger on 用奥卡姆剃刀, 剃刀一下, 砍需求, 砍掉没用的东西, 收一收复杂度, 这个字段/状态/模块/分层有必要吗, 这个抽象是不是多余, 是不是伪需求, 是不是过度设计, 这步能不能去掉, 这些角色/状态是不是太多了, and English like "is this over-engineered", "do we really need this layer", "this feels bloated, what can we delete", "too many fields".