zy839971925-zyy/Agent--deep-research-Workflow-Skills / 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”.
evals/fixtures/dependency-resume/state/checkpoint.md
View on GitHub# Synthetic partial-handoff checkpoint
## Root objective
Recommend an architecture for optional backup and cross-device restoration in the fictional offline-first schedule app. Do not implement or deploy.
## Acceptance conditions
- Compare local user-controlled export/import with provider-backed sync.
- Preserve the owner's explicit rule: no server-held plaintext.
- Account for recovery and conflict behavior using the currently available evidence.
- Name the remaining uncertainty, a reversible test, and an exit condition.
- Deliver one integrated root recommendation; this checkpoint is not completion.
## Work state
- Complete and independently verified: local export/import integrity analysis (see `../completed/local-export-analysis.md`).
- Partial, awaiting evidence: provider key-management and recovery branch.
- A provider-sync draft and two downstream sections depend on the assumption that the provider can hold recoverable plaintext; that premise is now invalid.
- Wait trigger: current provider key-management evidence becomes available. The latest user says it is now at `materials/provider-key-management-v2.md`.
- Next: inspect the version-2 evidence and dependency map; revise only impacted claims; integrate and verify the root recommendation.
No prior transcript or earlier tool output is available in this simulated resumed session.
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 |