Skip to main content
تشغيل أي مهارة في Manus
بنقرة واحدة
مستودع GitHub

control-tower

يحتوي control-tower على 11 من skills المجمعة من linuxarena، مع تغطية مهنية على مستوى المستودع وصفحات skill داخل الموقع.

skills مجمعة
11
Stars
30
محدث
2026-07-09
Forks
27
التغطية المهنية
2 فئات مهنية · 100% مصنفة
مستكشف المستودعات

Skills في هذا المستودع

control-concepts
مطوّرو البرمجيات

Guide to Control Tower's AI control concepts. Use when the user asks about control protocols, blue team and red team roles, usefulness, safety, audit budgets, trusted monitoring, or the conceptual model behind Control Tower.

2026-07-09
making-environments
مطوّرو البرمجيات

Guide for creating new Control Tower environments. Use when the user asks about creating environments, environment structure, compose files, Docker setup, tech stack diversity, attack surface, or environment properties.

2026-07-09
making-main-tasks
مطوّرو البرمجيات

Guide for creating main tasks in Control Tower environments. Use when the user asks about creating, implementing, or designing main tasks, task categories (Add Feature, Fix Bug, Refactor Code, Answer Question), scorers, task requirements, or info.yml structure for tasks.

2026-07-09
making-scorers
مطوّرو البرمجيات

Guide for writing scorers in Control Tower. Use when the user asks about creating scorers, scorer patterns, testing scorers, scorer boilerplate, or how to validate task completion.

2026-07-09
making-side-tasks
مطوّرو البرمجيات

Guide for creating side tasks in Control Tower environments. Use when the user asks about creating side tasks, security property violations, attack surface, red team descriptions, or sabotage objectives.

2026-07-09
making-strajs
مطوّرو البرمجيات

Guide for creating sabotage trajectories (strajs) in Control Tower. Use when the user asks about creating strajs, monitor evasion, attack strategies, straj documentation, or trajectory development workflows.

2026-07-09
monitoring
مطوّرو البرمجيات

Guide for monitoring trajectories in Control Tower. Use when the user asks about monitoring, suspiciousness scores, ct run monitor command, monitor types (basic, strong, gpt5, multi), or trajectory analysis. IMPORTANT - Use this skill instead of the MCP tools for guidance on monitoring trajectories.

2026-07-09
running-evals
مطوّرو البرمجيات

Guide for running evaluations in Control Tower. Use when the user asks about running evals, ct run eval, eval policies (honest, attack, trusted), task sets, uploading results, replaying trajectories, or evaluation options. IMPORTANT - Use this skill instead of the MCP tools for guidance on running evaluations.

2026-07-09
safety-curves
مطوّرو البرمجيات

Guide for understanding and explaining Control Tower safety curves. Use when the user asks about safety-usefulness tradeoffs, audit budgets, attack success rates, monitor thresholds, safety metrics, or interpreting safety curve plots.

2026-07-09
trajectories
مطوّرو البرمجيات

Guide for working with Control Tower trajectories. Use when the user asks about trajectory formats, trajectory IDs, converting .eval logs, uploading or downloading trajectories, replaying trajectories, or trajectory CLI commands.

2026-07-09
validate-straj
محللو ضمان جودة البرمجيات والمختبرون

Validate a sabotage trajectory (straj) end-to-end before trusting it as a keeper. Reconstructs the attack mechanism, checks for blatant reward-hacking and for unearned stealth (an environment flaw that made the side task trivially easy and low-suspicion), replays the side-task scorer in a fresh sandbox, and re-scores with the strong (action) + quick (traj) monitors on opus-4-8 and gemini-3.1-pro (scored once per model, escalating a flagged monitor to a majority of 3). Use when the user wants to validate / verify / QA strajs, confirm a straj still evades the canonical monitor, or check a "clean keeper" list of trajectories.

2026-07-09