基于 SOC 职业分类
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/majiayu000/claude-skill-registry --skill competitor-trial-monitor命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
LLM token logprobs and calibration. Per-decision confidence, ECE, Brier, reliability diagrams, low-confidence triage.
Analyze LLM token logprobs and calibration. Use for per-decision confidence, ECE, Brier scores, reliability diagrams, and low-confidence triage.
回顾最近 N 天的 Claude Code 使用记录——扫描原始会话数据，按主题分组汇总"我都做了什么"，并从个人操作系统视角输出模式、风险与增删建议。当用户说 /recap、"看看我这几天做了什么"、"回顾一下我最近的会话"、"这两天我用 claude 干了啥"、"活动回顾" 时使用。
| name | competitor-trial-monitor |
| description | Monitor competitor clinical trial progress and alert on market risks |
| version | 1.0.0 |
| category | Pharma |
| tags | [] |
| author | AIPOCH |
| license | MIT |
| status | Draft |
| risk_level | High |
| skill_type | Hybrid (Tool/Script + Network/API) |
| owner | AIPOCH |
| reviewer | |
| last_updated | 2026-02-06 |
Monitor competitor clinical trial progress and alert on market risks.
| Command | Description | Parameters |
|---|---|---|
add | Add trial to watchlist | --nct (required), --company, --drug, --indication |
list | List all monitored trials | None |
remove | Remove trial from watchlist | --nct (required) |
scan | Scan for updates | None |
report | Generate risk report | --days (default: 30) |
add command:
| Parameter | Type | Default | Required | Description |
|---|---|---|---|---|
--nct | string | - | Yes | ClinicalTrials.gov NCT ID |
--company | string | Unknown | No | Competitor company name |
--drug | string | Unknown | No | Drug name |
--indication | string | Unknown | No | Indication/disease |
remove command:
| Parameter | Type | Default | Required | Description |
|---|---|---|---|---|
--nct | string | - | Yes | NCT ID to remove |
report command:
| Parameter | Type | Default | Required | Description |
|---|---|---|---|---|
--days | int | 30 | No | Report time range in days |
python scripts/main.py add --nct NCT05108922 --company "Pfizer" --drug "PF-07321332" --indication "COVID-19"
python scripts/main.py scan
python scripts/main.py list
python scripts/main.py remove --nct NCT05108922
python scripts/main.py report --days 30
Monitoring configuration and data stored in ~/.openclaw/competitor-trial-monitor/:
watchlist.json - Monitoring listhistory/ - Historical snapshotsalerts/ - Alert records| Event | Risk Level | Description |
|---|---|---|
| Enrollment Completion | 🟡 Medium | Competitor enters next phase |
| Data Unblinding | 🔴 High | Results about to be announced |
| Results Publication | 🔴 High | Direct impact on market competition |
| Regulatory Submission | 🔴 High | Marketing application in progress |
| Approval Granted | 🔴 Critical | Direct competition begins |
pip install requests python-dateutil
~/.openclaw/competitor-trial-monitor/config.json:
{
"alert_channels": ["feishu"],
"scan_interval_hours": 24,
"risk_threshold": "medium"
}
| Risk Indicator | Assessment | Level |
|---|---|---|
| Code Execution | Python scripts with tools | High |
| Network Access | External API calls | High |
| File System Access | Read/write data | Medium |
| Instruction Tampering | Standard prompt guidelines | Low |
| Data Exposure | Data handled securely | Medium |
No additional Python packages required.