450 skills · sorted by relevance
Solve sandboxed CTF security challenges by reconstructing encoding and encryption steps, extracting data hidden in media, and tracing mobile app signing or storage behavior. Preserve exact parameters and evidence to reproduce decoded content or signed requests.
Trace how requests become rendered pages in a CTF sandbox. Compare display restrictions with server enforcement, inspect data passed to the browser, and preserve a minimal example that demonstrates where rendering behavior diverges.
Inspect browser storage and caches in a CTF sandbox to explain changes in authentication, page rendering, or requests. Compare clean and modified states, then document the smallest sequence that reproduces the relevant behavior.
Analyze Android apps in a CTF sandbox using static inspection and Frida hooks, which observe or alter running code. Trace request signing, local storage, and Java-to-native boundaries to reproduce a request accepted by the server.
Investigate AI-agent and cloud infrastructure challenges in a CTF sandbox. Trace untrusted content into tool actions, compare deployment configuration with runtime behavior, and follow software artifacts from source through build and release to their actual consumers.
Assess the security of LLM applications and AI agents by tracing inputs, retrieved content, tool calls, and outputs. Covers prompt injection, where content carries unwanted instructions, along with permission misuse, memory poisoning, and supply-chain risks.
Investigate Active Directory Certificate Services in an isolated CTF competition environment. Trace certificate templates and enrollment rights through issuance, identity mapping, and service acceptance to explain resulting privileges and document a minimal reproducible chain.
Prepare and review LoRA or QLoRA settings for adapting language models using example responses. Choose trainable layers, adapter capacity, learning rate, and memory-related options, then produce configuration values for a downstream training script.
Turn local Q&A session files into an English weekly report with topic rankings, unresolved issues, activity metrics, and comparisons with the previous week. Include supporting message excerpts and structured data for later document and dashboard rendering.
Review every project in a .NET solution for Oracle dependencies, classify its migration status, and create a saved PostgreSQL migration plan with a project inventory and an order that prioritizes shared libraries.
Investigate malicious software delivered through trusted updates or dependencies. Compare suspect files with legitimate versions, examine signing anomalies and injected code, and organize evidence to assess the infection path and downstream impact.
Convert laboratory instrument files into Allotrope Simple Model (ASM) JSON, a standardized data format, or tabular CSV. Detect instrument types, validate converted data, and export Python parsing code for analysis workflows or handoff to data engineers.
Analyze single-cell data with scvi-tools, using deep learning to combine datasets, correct differences between experiments, and transfer cell labels. Model guides and reusable scripts cover RNA, protein, chromatin accessibility, spatial data, and downstream analysis.
Write and troubleshoot n8n expressions, the formulas that pass and transform data between workflow steps. Covers field references, webhook inputs, dates, strings, and choosing between expressions and Code nodes for data transformations.
Investigate failing or flaky NemoClaw end-to-end tests, which check complete workflows. Trace each assertion through its inputs and implementation, including cleanup and dependent jobs, and produce an evidence ledger to guide authorized repairs and reruns.
Plan projects that use large language models, from checking whether the task suits a model to designing processing stages. Estimate costs, choose single or multiple agents, and organize prototypes, structured outputs, and iteration.
Search and aggregate Datadog logs through the Composio CLI. Filter by service, environment, and time range, follow requests across services, and export structured JSON for incident analysis or scheduled daily digests.
Prepare a pull request to contribute local qm changes back to the shared project. Builds a clean contribution branch and checks commit history, files, authorship, and review materials for private organizational details before submission.
Adjust an existing litigation practice profile through a guided conversation. Update roles, risk thresholds, document styles, contacts, or workflow settings one change at a time, with an explanation of downstream effects and checks for inconsistent settings.
Update individual settings in an existing product counsel profile, such as risk thresholds, escalation contacts, launch review categories, or marketing claims rules. The guided process explains downstream effects, checks inconsistencies, and saves confirmed changes without repeating setup.
Update an existing AI governance profile through guided changes. Adjust risk posture, escalation contacts, registered use cases, vendor positions, or assessment formats, while checking downstream effects and inconsistencies before saving each change.
Update an existing employment-law practice profile through guided questions. Adjust employee locations, risk preferences, contacts, hiring or termination review rules, and other settings while reviewing downstream effects, without repeating setup or editing configuration files by hand.
Design OpenRig watchdog policies for stalled or drifting agent work. Choose a small wake-up message, a refocus, or a broader alignment check, and separate monitoring frequency from notification frequency using evidence about owners and artifacts.
Guide changes to OpenRig itself by locating relevant source files, choosing tests, assessing sensitive areas, and preparing pull requests. Use isolated test environments to check changes without disrupting the daemon running the current agent session.