← 返回 Skills 市场

Clarity Variant

Name: Clarity Variant
Author: clarityprotocol

作者 clarityprotocol · GitHub ↗ · v1.0.0

cross-platform ✓ 安全检测通过

341

总下载

当前安装

版本数

在 OpenClaw 中安装

/install clarity-variant

功能描述

Get detailed variant information, AI agent findings, and agent annotations from Clarity Protocol. Use when the user asks to get variant details, fold quality...

使用说明 (SKILL.md)

Clarity Variant Skill

Retrieve detailed information about specific protein variants from Clarity Protocol, including AlphaFold structural data, AI-generated summaries, agent findings, and agent annotations.

Quick Start

Get variant details:

python scripts/get_variant.py --fold-id 1

Get variant details in readable format:

python scripts/get_variant.py --fold-id 1 --format summary

Get all agent findings for a variant:

python scripts/get_findings.py --fold-id 1

Get findings from specific agent type:

python scripts/get_findings.py --fold-id 1 --agent-type structural

Get agent annotations for a variant:

python scripts/get_annotations.py --fold-id 1
python scripts/get_annotations.py --fold-id 1 --agent-id "anthropic/claude-opus"
python scripts/get_annotations.py --fold-id 1 --type structural_observation

Variant Detail Fields

id: Unique fold identifier
protein_name: Protein name
variant: Mutation notation
disease: Associated disease
uniprot_id: UniProt database identifier
average_confidence: AlphaFold pLDDT confidence score (0-100)
ai_summary: AI-generated analysis of the mutation
notes: Additional annotations
created_at: When the fold was created

Agent Findings Fields

Each finding includes:

id: Unique finding identifier
fold_id: Associated variant ID
agent_type: Agent that generated the finding (structural, clinical, literature, synthesis)
data: Structured data discovered by the agent
summary: Human-readable summary of findings
created_at: When the finding was created

Agent Types

structural: Analyzes protein structure changes from AlphaFold data
clinical: Searches ClinVar and gnomAD for clinical significance
literature: Searches PubMed for relevant research papers
synthesis: Synthesizes findings from all other agents

Agent Annotation Fields

Each annotation includes:

id: Unique annotation identifier
fold_id: Associated variant ID
agent_id: Agent that submitted the annotation (provider/name format)
annotation_type: Type of annotation (structural_observation, literature_connection, etc.)
content: Annotation text
confidence: Confidence level (high, medium, low)
created_at: When the annotation was created

Rate Limits

Anonymous (no API key): 10 requests/minute
With API key: 100 requests/minute

To use an API key, set the CLARITY_API_KEY environment variable:

export CLARITY_API_KEY=your_key_here
python scripts/get_variant.py --fold-id 1

Get your API key at https://clarityprotocol.io

Error Handling

404 Not Found: The variant with the specified fold ID does not exist.

429 Rate Limit: You've exceeded the rate limit. The script will display how long to wait.

500 Server Error: The API server encountered an error. Try again later.

Timeout: The request took longer than 30 seconds.

Use Cases

Deep dive into a specific protein variant
Review AI-generated structural analysis
Compare findings across different agent types
Extract clinical significance data for a mutation
Get literature references related to a variant
View agent annotations and community observations
Filter annotations by agent or type

安全使用建议

This skill appears to do what it claims: call clarityprotocol.io and print variant details, findings, and annotations. Before installing: 1) Confirm you trust https://clarityprotocol.io and only provide CLARITY_API_KEY if you intend to associate requests with your account (the key is sent in the X-API-Key header). 2) Ensure your environment has Python and the 'requests' library. 3) Note the small metadata mismatches (registry version vs SKILL.md version, and CLARITY_API_KEY listed only in SKILL.md) — ask the publisher to correct metadata if you need strict provenance. If you don't want network access or to share an API key, do not install/use this skill.

功能分析

Type: OpenClaw Skill Name: clarity-variant Version: 1.0.0 The OpenClaw AgentSkills skill bundle is benign. All Python scripts (`api_client.py`, `get_annotations.py`, `get_findings.py`, `get_variant.py`) are well-structured API clients designed to interact with `https://clarityprotocol.io/api/v1` to retrieve protein variant information. The `api_client.py` correctly reads the `CLARITY_API_KEY` from environment variables for authentication, which is a standard and secure practice. The `SKILL.md` documentation provides clear, non-malicious instructions for the AI agent on how to use the skill, without any prompt injection attempts to manipulate the agent into unauthorized actions or data exfiltration. There is no evidence of malicious execution, persistence mechanisms, or obfuscation.

能力评估

ℹ Purpose & Capability

The name/description match the actual behavior: all scripts call the clarityprotocol.io API to fetch variants, findings, and annotations. One minor metadata inconsistency: the SKILL.md lists metadata/version 2.0.0 while the registry shows version 1.0.0. This is likely an authoring/versioning mismatch but does not affect functionality.

✓ Instruction Scope

SKILL.md and the scripts instruct only network calls to the declared API endpoints and local stdout printing. The runtime instructions and example CLI commands directly map to the provided scripts; no unexpected file reads, writes, or unrelated system access are present.

✓ Install Mechanism

There is no install spec (instruction-only). The code is pure Python and performs HTTPS requests. No downloads from untrusted URLs or archive extraction are present. Note: the scripts depend on the 'requests' library but the skill does not declare an installer — the environment must provide Python and requests.

ℹ Credentials

Behavior uses a single optional environment variable CLARITY_API_KEY for higher rate limits; this is appropriate for the API usage. However, the registry metadata lists 'Required env vars: none' and does not declare CLARITY_API_KEY as an optional variable — the SKILL.md and code do reference it. The requested credential scope is proportional (API key only) and no unrelated secrets are accessed.

✓ Persistence & Privilege

The skill does not request permanent/always inclusion (always: false) and does not modify other skills or system settings. Autonomous invocation is allowed by default (disable-model-invocation: false), which is normal and expected for skills.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install clarity-variant
安装完成后，直接呼叫该 Skill 的名称或使用 /clarity-variant 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v1.0.0

- Initial release of the clarity-variant skill with version 1.0.0. - Retrieve detailed information and AI-generated summaries for specific protein variants from Clarity Protocol, including AlphaFold data. - Access and filter agent findings by type (structural, clinical, literature, synthesis) and receive human-readable summaries. - Fetch agent annotations, filterable by agent or annotation type, with confidence levels. - Includes error handling for not found, rate limit, server error, and timeout cases. - Supports up to 100 requests/min with API key and 10/min without.

元数据

Slug clarity-variant

版本 1.0.0

许可证 —

累计安装 0

当前安装数 0

历史版本数 1

常见问题

Clarity Variant 是什么？

Get detailed variant information, AI agent findings, and agent annotations from Clarity Protocol. Use when the user asks to get variant details, fold quality... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 341 次。

如何安装 Clarity Variant？

在 OpenClaw 或 Claude Code 对话框中运行命令「/install clarity-variant」即可一键安装，无需额外配置。

Clarity Variant 是免费的吗？

是的，Clarity Variant 完全免费（开源免费），可自由下载、安装和使用。

Clarity Variant 支持哪些平台？

Clarity Variant 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。

谁开发了 Clarity Variant？

由 clarityprotocol（@clarityprotocol）开发并维护，当前版本 v1.0.0。