Enforce policies, guardrails, and permission boundaries; refuse unsafe actions and apply least privilege. Use when...
AI & LLM
LLM integrations, prompt engineering, and AI orchestration
7,400 技能
Find failure modes, edge cases, ambiguities, and exploit paths in plans, code, or designs. Use when reviewing...
Execute the Debug Code Change workflow end-to-end with safety gates. Use when debugging code changes, investigating...
Break a goal into subgoals, constraints, and acceptance criteria. Use when planning complex work, creating work...
Split work across subagents with explicit contracts, interfaces, and merge strategies. Use when parallelizing tasks,...
Produce clear reasoning with assumptions, causal chains, and evidence. Use when clarifying decisions, teaching...
Create a new artifact (text, code, plan, data) under specified constraints. Use when producing content, writing...
Anchor claims to evidence from authoritative sources. Use when validating assertions, establishing provenance,...
Request clarification when input is ambiguous. Use when user request has missing parameters, conflicting...
Combine heterogeneous data sources into a unified model with conflict resolution, schema alignment, and provenance...
Execute a composed workflow by name. Use when running predefined workflows, orchestrating multi-step processes, or...
Quantify values with uncertainty bounds. Use when estimating metrics, calculating risk scores, assessing magnitude,...
Change persistent state with checkpoint and rollback support. Use when modifying files, updating databases, changing...
Watch and report current state of a target system, process, or entity. Use when monitoring status, inspecting live...
Write stable learnings, decisions, and patterns to durable storage like CLAUDE.md or knowledge files. Use when...
Create an executable plan with steps, dependencies, verification criteria, checkpoints, and rollback strategies. Use...
Forecast future states or outcomes based on current data and trends. Use when estimating future values, projecting...
Retrieve prior decisions, rationale, and learned patterns from memory to apply consistently. Use when needing...
Ingest and parse incoming messages, events, or signals into structured form. Use when processing external inputs,...
Fetch known facts or data from specified sources with citations and evidence pointers. Use when you know what you...
Safely undo changes by restoring to a checkpoint. Use when verify fails, errors occur, or explicit undo is...
Find relevant items under uncertainty across repositories, databases, web sources, or any searchable corpus. Use...
Emit a message or event to an external system with policy enforcement and approval gates. Use when publishing...
Run what-if scenarios to explore outcomes and test hypotheses. Use when evaluating alternatives, stress-testing...