174 skills · sorted by relevance
Analyze Apache and Nginx access logs for attack attempts, scanner activity, and repeated login requests. Add geographic context to source IP addresses and produce a prioritized findings report to support intrusion investigations and monitoring reviews.
Investigate attempts to gain higher privileges on Windows and Linux using endpoint and security logs. Guide hypothesis testing, evidence analysis, false-positive checks, and reporting to help assess suspicious privilege changes and the scope of a compromise.
Analyze ModSecurity, AWS WAF, and Cloudflare logs for SQL injection, attempts to manipulate database queries through web requests. Groups related requests, tracks source IPs, classifies attack methods, and produces incident reports.
Configure Fail2ban to detect port scans, repeated SSH login attempts, and suspicious web requests from server logs. Create custom detection patterns, automatically block source IP addresses, and set up notifications and longer bans for repeat offenders.
Search past coding sessions across Claude Code, Codex, and Cursor to recover earlier attempts, failed approaches, decisions, and findings. It filters history by topic and time, then summarizes technical details relevant to the question.
Create spreadsheets, diagrams, and PDF reports in a staged workflow. Allocate execution attempts across deliverables, check generated files, and use simpler methods or alternative formats when tool errors or limited remaining attempts interrupt progress.
Test how API-accessible language models respond to attempts to bypass safety filters. The skill covers prompt templates, input transformations, parallel response comparisons, and Hermes configuration, with automated scoring of refusals, answer quality, and speed.
Inspect local AI coding session logs with agenttrace to identify cost spikes, delays, failed tools, and retry loops. Produce readable reports, compare attempts, and configure automated checks for unusual or unhealthy runs.
Keep a short, persistent work journal so an agent can resume across sessions. Record completed work, current status, next steps, and unsuccessful attempts, then read the latest entry when restarting or summarize the work when closing it.
Investigate suspected data theft from AWS S3 by comparing access logs, GuardDuty findings, and Macie classifications. Identify unusual bulk downloads and transfers across accounts, assess sensitive data exposure, and build automated detection rules.
Examine Windows endpoint logs for attempts to avoid security detection, including log clearing, altered file timestamps, injected code, and disabled protection. Correlate events to investigate suspicious behavior and develop detection rules with context for legitimate activity.
Identify runtime signs of attackers breaking out of Docker or Kubernetes containers. Review namespace changes, privilege abuse, sensitive host access, and unusual system calls to guide incident investigations and compare monitoring coverage across security tools.
Screen AI application inputs and historical logs for prompt injection, where malicious instructions try to redirect the model. Combine pattern matching, text structure scoring, and a DeBERTa classifier to flag suspicious content and produce JSON results.
Analyze Windows PowerShell event logs to reconstruct scripts split across records and identify encoded commands, suspicious downloads, and security scanning bypass attempts. Produce a report with recovered scripts, risk scores, and mappings to documented attack techniques.
Analyze access logs from AWS API Gateway, Kong, and Nginx with pandas, a Python data analysis library. Examine resource access patterns, authentication failures, and suspicious requests to investigate API abuse and inform detection rules.
Hand an ongoing task to a fresh agent with a self-contained briefing. The skill gathers context, decisions, failed attempts, acceptance criteria, and constraints, then launches the receiving agent in the current workspace or a requested isolated workspace.
Helps AI agents recover from repeated failures by reviewing previous attempts, checking original sources, testing different hypotheses, and verifying results. It combines structured troubleshooting with performance review rhetoric modeled on large technology companies.
Review lessons from difficult tasks, debugging, and failed attempts, then turn them into reusable guidance. Update relevant skill instructions or shared memory so future tasks can benefit from what was learned.
Add safety checks to LLM applications with NeMo Guardrails. This skill guides input and output validation, detection of attempts to bypass safety rules, personal information masking, and checks for unsupported or inaccurate answers.
Index reference libraries locally with XERJ and retrieve relevant implementations before coding. Use the retrieved source to understand unfamiliar API behavior, port algorithms, or investigate errors that repeated attempts have not resolved.
Turn a concept’s origins into a magazine-style visual story. Six distinct layouts combine diagrams, annotations, and typography to trace a concrete problem through failed attempts and a turning point, revealing the concept’s name at the end.
Diagnose failed connections to government websites and corporate portals by checking network access, SSL certificates, and proxy settings. If access remains unavailable, the workflow helps identify alternative data sources and document attempts and next steps.
Organizes creation of a spreadsheet, a diagram, and a summary PDF as a related report package. Allocates attempts across components, checks generated files, and provides fallback methods when a tool or output fails.
Create a related Excel workbook, PNG diagram, and PDF report in one workflow. It allocates execution attempts across stages, checks output files, and provides retries or simpler versions when generation encounters errors.