185 skills (repositories by wshobson) · sorted by popularity
Map security threats into attack trees, branching diagrams that connect an attacker’s goal to possible steps. Assess cost, time, expertise, and detection likelihood to identify defense gaps, prioritize mitigations, and explain risks to stakeholders.
Set up automated security checks that inspect source code without running the application. Configure Semgrep, SonarQube, or CodeQL, add project-specific rules, reduce false alarms, and define criteria for blocking problematic changes.
Create automated shell script tests with Bats, a Bash testing tool. Check exit codes, output, and failure cases, organize reusable test helpers and data, and run checks across shells or in CI/CD pipelines.
Set up ShellCheck to inspect shell scripts without running them. Understand warnings, configure checks for the intended shell, document exceptions, and integrate analysis into CI, editors, or checks that run before commits.
Build web interfaces that adapt to screen and component widths. Use CSS Grid, flexible text and spacing, and container queries, which respond to a component’s available space, to adjust layouts, images, navigation, and tables.
Build React Native mobile interfaces for iOS and Android, covering styling, screen navigation, gesture interactions, and animations. The skill guides React Navigation and Reanimated usage, responsive layouts, and performance improvements for mobile components.
Capture and analyze network traffic to understand custom protocols, including message boundaries and field meanings. Use the findings to document formats, investigate communication problems, and validate behavior through replay and tests with unusual inputs.
Scan a codebase to create project documentation and project-specific agent instructions. The first run examines the whole project; later runs focus on changed files, with human confirmation required before updating agent instructions after architectural changes.
Review AI-generated code for problems hidden behind successful runs. Check failure handling, resource cleanup, unusual inputs, nonexistent dependencies, and departures from project conventions to identify missing safeguards before merging or accepting the work as complete.
Helps agents manage long tasks by checking for forgotten instructions and drifting conventions. It guides progress summaries, rule checks after context compaction, and handoff notes when work should continue in a fresh session.
Help agents continue work in projects using Superself. Read current goals and decisions, attach work to tracked units, record progress with supporting evidence, and preserve confirmed decisions so later sessions can resume with context.
Prepare datasets for language model training by formatting examples, checking conversation templates, and packing examples into training sequences. Document data sources, synthetic data ratios, and validation results in a dataset card before starting a run.
Evaluate whether a fine-tuned model is ready for release by checking training data, general capability loss, comparisons with the base model, and staged production rollout. Produces an evidence-based promotion or rejection report with one prioritized remedy when rejected.
Decide whether an LLM needs additional training or whether retrieval and better prompts will suffice. Match available examples, preferences, or verifiable results to a training method, then assess model size and memory requirements before starting.
Build searches that find similar meanings using vector databases, which store numerical representations of data. Choose search indexes, combine semantic and keyword search, and tune retrieval quality and response time for search, recommendations, or AI answer systems.
Tune vector indexes, which organize data for similarity searches, to balance speed, memory use, and missed matches. Choose index types, adjust HNSW settings, and assess compression options using benchmarks with real queries.
Prepare GRPO reinforcement learning configurations for tasks with programmatically checkable answers, such as math, code, and structured output. Design and inspect reward functions, then select training variants when runs show instability or exploit flaws in scoring.
Analyze compiled programs without running them by recognizing branches, loops, data structures, and common instruction patterns. Use disassembly and decompilation, which translate machine code into readable representations, to reconstruct program logic and document findings.
Investigate security incidents using memory dumps, saved copies of RAM. The skill guides memory acquisition, process and network analysis, suspicious code detection, and evidence extraction with Volatility and related tools, including checks for capture integrity.
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.
Structure Python code to release files and database connections reliably, including when errors occur. Covers context managers, which handle setup and cleanup, asynchronous resources, nested cleanup, and streaming responses that retain accumulated state.
Measure Python execution time and memory use to locate slow or resource-heavy code. Use profiling results to guide improvements in data structures, caching, input and output operations, algorithms, and parallel processing.
Add Python type hints and configure strict checking with mypy or pyright to catch type errors before execution. Covers reusable classes that preserve type information, interfaces defined by required members, and checks for possibly missing values.
Implement Python error handling with early input checks, appropriate exception types, and clear messages. Handle individual failures in batch jobs, preserve error context for debugging, and use Pydantic models to validate structured input.