zy839971925-zyy/Agent--deep-research-Workflow-Skills / integrations/deepseek-harness/skills/reasoning-workflow
reasoning-workflow
VerifiedDefault silent workflow for everyday questions, research, writing, design and engineering. Match effort to the request, resolve costly ambiguity, find specialist resources and verify the requested outcome. Explicitly selectable with “调用我的 workflow skills”.
families/core-reasoning.md
View on GitHub# Core Reasoning
Always available for substantive tasks. Start light; load only the references needed by the current problem-model gap.
> Return to the governing router after the current module. `Related` never means auto-load.
## References
- [writing-for-the-reader](../references/writing-for-the-reader.md) — Draft or edit in the register the reader needs, preserving facts and voice.
- [specialist-resources](../references/specialist-resources.md) — Find an appropriate specialist or maintained reference and verify how it applies to this stack.
- [`clarification-gate`](../references/clarification-gate.md) — Load when a material ambiguity could justify a user question; resolve accessible context, project evidence, external facts, and safe derivations first.
- [`problem-framing-and-effort`](../references/problem-framing-and-effort.md) — Load only when the active gap matches one of: framing, depth, autonomy, clarification, task-profile, representation.
- [`reasoning-structure-and-decomposition`](../references/reasoning-structure-and-decomposition.md) — Load only when the active gap matches one of: decomposition, recomposition, structure, granularity, reasoning-stagnation.
- [`relationships-and-systems`](../references/relationships-and-systems.md) — Load only when the active gap matches one of: causal-chain, systems, relationships, feedback, mechanism.
- [`hypotheses-and-bias-control`](../references/hypotheses-and-bias-control.md) — Load only when the active gap matches one of: hypotheses, competing-explanations, bias, falsification.
- [`human-context-and-interpretation`](../references/human-context-and-interpretation.md) — Load only when the active gap matches one of: human-context, interpretation, statement.
- [`worked-examples`](../references/worked-examples.md) — Load only when the active gap matches one of: examples, workflow-example.
- [`model-adaptation`](../references/model-adaptation.md) — Load when GPT-6+ and current frontier-model/runtime behavior, compute allocation, delegation, or compaction materially affects the route.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| brainstormingobra/superpowersYou MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation). | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| brand-guidelinesanthropics/skillsApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| frontend-designanthropics/skillsGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| mcp-builderanthropics/skillsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK). | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |