AI Skillstore Marketplace

The nature-data skill is designed to help researchers prepare or review Data Availability statements, data repository plans, dataset citations, and FAIR metadata checks specifically for submissions to Nature or Springer Nature journals.

Key Capabilities

• Drafting Statements: Generates Data Availability statements ready to be pasted into manuscripts.
• Pre-submission Review: Audits weak or incomplete data availability descriptions.
• Data Mapping: Maps datasets supporting specific results to repositories, accession numbers, DOIs, or access paths.
• Data Categorization: Distinguishes between public data, controlled access data, third-party data, supplementary material, and non-applicable scenarios.
• Metadata & Citation Checks: Prepares FAIR metadata and DataCite-style dataset citation checks.
• Gap Identification: Flags missing repository records, licenses, sources, embargo details, and access conditions.
• Bilingual Support: Translates Chinese author notes (e.g., "数据可向通讯作者索取", "原始数据") into professional Nature-style English phrasing, providing Chinese confirmation items when necessary.

Design Principles

• No Hallucinations: The skill will not invent accession numbers, licenses, restrictions, or repository metadata. If information is missing, it provides a draft and a checklist of items the author must confirm.
• Traceability: It requires every dataset supporting a paper's conclusion to have a clear, traceable access path.

Cloudflare Flagship is a feature flag service designed to control feature visibility without requiring code redeployments. It allows you to define flags with targeting rules and percentage-based rollouts.

Core Capabilities:

• Feature toggles: Simple on/off switches.
• Gradual rollouts: Percentage-based releases to a fraction of users.
• A/B testing: Testing different variations using attribute targeting.
• Multi-variant configuration: Delivering different JSON, string, number, or boolean values based on rules.

Key Concepts:

• Apps: The top-level organizational unit (maps to a project or service).
• Flags: Named toggles containing a key, variations, targeting rules, and state.
• Variations: The possible values a flag returns (must all be the same type: boolean, string, number, or JSON).
• Targeting rules: Priority-ordered conditions where the first match wins.
• Evaluation context: Key-value attributes (e.g., userId, country) used for rule matching and rollout bucketing.
• Percentage rollouts: Uses consistent hashing on a configurable attribute to ensure sticky bucketing for users.

The nature-reviewer skill simulates a pre-submission peer review package from the perspective of a Nature journal reviewer. Unlike tools designed to write author rebuttals, this skill focuses on evaluating manuscripts against official Nature editorial criteria.

Key Characteristics:

• Strict Adherence: It uses the official Nature Editorial criteria and processes as its primary source of truth to avoid generalized or fictionalized peer-review personas.
• Conservative Simulation: It does not invent reviewer identities, institutions, or specialized personas. Instead, it generates three distinct reports that differ only in their focus areas based on the same factual foundation.
• Output Structure: By default, it provides a structured review consisting of a setup, three individual reports, a cross-review synthesis, and a risk assessment.

Note: If your goal is to write point-by-point responses or revision letters, use the nature-response skill instead.

Cloudflare offers several observability features for Workers. Choose the one that matches your requirements for data type, access method, and cost:

Workers Logs

• Description: Console output from Workers (console.log/warn/error).
• Access: Dashboard (Real-time Logs), Logpush, Tail Workers.
• Cost: Free (included with all Workers).
• Retention: Real-time only (no historical storage in dashboard).

Workers Traces

• Description: Execution traces including timing, CPU usage, and outcome.
• Access: Dashboard (Workers Analytics → Traces), Logpush.
• Cost: $0.10/1M spans (GA pricing starts March 1, 2026); 10M free/month.
• Retention: 14 days included.

Analytics Engine

• Description: High-cardinality event storage and SQL queries.
• Access: SQL API, Dashboard (Analytics → Analytics Engine).
• Cost: $0.25/1M writes beyond 10M free/month.
• Retention: 90 days (configurable up to 1 year).

Tail Workers

• Description: Workers that receive logs/traces from other Workers.
• Use Cases: Log filtering, transformation, external export.
• Cost: Standard Workers pricing.

Logpush

• Description: Stream logs to external storage (S3, R2, Datadog, etc.).
• Access: Dashboard, API.
• Cost: Requires Business/Enterprise plan.

yao-meta-skill (Yielding AI Outcomes) is a toolset designed to create, evaluate, package, and govern reusable AI agent skills. Unlike simple prompt generators, it focuses on transforming fragmented workflows, prompts, transcripts, and notes into structured, portable, and verifiable AI assets.

Key Capabilities:

• Intent Modeling: Converts rough workflows into clear tasks, outputs, constraints, and quality standards.
• Skill IR (Intermediate Representation): Uses a platform-agnostic structure to record intent, triggers, I/O, boundaries, and deliverables, preventing vendor lock-in.
• Cross-Platform Compilation: Compiles a single skill definition into formats compatible with OpenAI, Claude, generic agent skill packages, and VS Code scenarios.
• Quality & Governance: Provides output evaluation labs, evidence ledgers, runtime permission detection, and a 'Review Studio' for comprehensive auditing.
• SkillOps Lifecycle: Supports a continuous loop of deployment, telemetry (adoption drift), and iterative improvement based on real-world feedback.