AGENTIC MEMORY
Skills
Useful instructions for your AI. Search, read and use them through the same MCP connection.
security-review
AI-powered codebase security scanner that reasons about code like a security researcher — tracing data flows, understanding component interactions, and catching vulnerabilities that pattern-matching tools miss. Use this skill when asked to scan code for security vulnerabilities, find bugs, check for SQL injection, XSS, command injection, exposed API keys, hardcoded secrets, insecure dependencies, access control issues, or any request like "is my code secure?", "review for security issues", "audit this codebase", or "check for vulnerabilities". Covers injection flaws, authentication and access control bugs, secrets exposure, weak cryptography, insecure dependencies, and business logic issues across JavaScript, TypeScript, Python, Java, PHP, Go, Ruby, and Rust.
security-threat-model
Repository-grounded threat modeling that enumerates trust boundaries, assets, attacker capabilities, abuse paths, and mitigations, and writes a concise Markdown threat model. Trigger only when the user explicitly asks to threat model a codebase or path, enumerate threats/abuse paths, or perform AppSec threat modeling. Do not trigger for general architecture summaries, code review, or non-security design work.
self-eval
Use after finishing a task, review or session to grade the work honestly. Scores it on two axes, forces a devil's-advocate pass against score inflation and keeps scores across sessions.
self-improving-agent
Curate the agent's own memory into durable project knowledge. Reviews Claude Code auto-memory (MEMORY.md and its topic files) for learnings worth keeping, promotes proven ones into CLAUDE.md or .claude/rules/, records a correction as a lesson that persists across sessions, prunes stale or duplicate entries, and turns a recurring fix into a reusable skill. Use whenever the user asks what you have learned or saved about the project, which memories should become permanent rules, to remember a lesson or stop repeating a mistake, or to clean up, audit or check the health of memory.
semantic-kernel
Create, update, refactor, explain, or review Semantic Kernel solutions using shared guidance plus language-specific references for .NET and Python.
semgrep
Runs a Semgrep security scan over a codebase: detects languages, selects rulesets, presents the plan for explicit approval, then runs every approved ruleset through scripts/run-scans.sh, which batches the semgrep processes and writes scans.json, and merges the output to SARIF. Supports two scan modes, "run all" for full ruleset coverage and "important only" for security findings at medium-to-high confidence and impact. Uses Semgrep Pro for cross-file taint analysis when it is available. Use when asked to scan code for vulnerabilities, run a security audit with Semgrep, find bugs, or perform static analysis. For the same scan without the approval gate, use the /static-analysis:semgrep-scan workflow.
semgrep-rule-creator
Creates custom Semgrep rules for detecting security vulnerabilities, bug patterns, and code patterns. Use when writing Semgrep rules or building custom static analysis detections.
semgrep-rule-variant-creator
Creates language variants of existing Semgrep rules. Use when porting a Semgrep rule to specified target languages. Takes an existing rule and target languages as input, produces independent rule+test directories for each language.
senior-architect
Use for system architecture decisions (monolith vs microservices, database choice, scalability, ADRs, design reviews) or architecture diagrams. Analyzes dependencies with dependency_analyzer.py, assesses the project with project_architect.py and draws Mermaid or PlantUML with architecture_diagram_generator.py.
senior-backend
Use for backend work: REST or GraphQL APIs, auth, microservices, PostgreSQL queries, migrations or load tests. Decides with backend_decision_engine.py, scaffolds with api_scaffolder.py, migrates with database_migration_tool.py and load-tests with api_load_tester.py.
senior-computer-vision
Use for computer vision work: object detection, segmentation, training a custom model, or optimizing and deploying inference (YOLO, DETR, SAM, ONNX, TensorRT). Builds datasets with dataset_pipeline_builder.py, trains with vision_model_trainer.py and tunes inference with inference_optimizer.py.
senior-data-engineer
Use for data pipelines and ETL or ELT (Spark, Airflow, dbt, Kafka, data modeling, data quality). Orchestrates with pipeline_orchestrator.py, validates with data_quality_validator.py and tunes jobs with etl_performance_optimizer.py.
senior-data-scientist
Use for experiment design, causal inference, feature engineering or predictive model evaluation on tabular data. Designs A/B tests with experiment_designer.py, builds features with feature_engineering_pipeline.py and evaluates models with model_evaluation_suite.py.
senior-devops
Use for CI/CD pipelines, infrastructure as code, containers and deployments on AWS, GCP or Azure. Generates pipelines with pipeline_generator.py, scaffolds Terraform with terraform_scaffolder.py and manages releases with deployment_manager.py.
senior-frontend
Use for React, Next.js, TypeScript or Tailwind work: components, performance, bundle size, scaffolding or frontend review. Decides with frontend_decision_engine.py, scaffolds with frontend_scaffolder.py and component_generator.py, and analyzes bundles with bundle_analyzer.py.
senior-fullstack
Use when starting a fullstack project, choosing a stack (Next.js, FastAPI, MERN, Django) or auditing a codebase's quality. Picks the stack with fullstack_decision_engine.py, scaffolds with project_scaffolder.py and scores code with code_quality_analyzer.py.
senior-ml-engineer
Use for putting ML models or LLM features into production: deployment, MLOps, drift monitoring, RAG pipelines, LLM API cost and retries. Deploys with model_deployment_pipeline.py, monitors with ml_monitoring_suite.py and builds RAG with rag_system_builder.py.
senior-pm
Use for project or portfolio management: plans, status reports, risk registers, capacity or executive reporting on multi-workstream programs. Runs project_health_dashboard.py, risk_matrix_analyzer.py and resource_capacity_planner.py.
senior-prompt-engineer
Use when optimizing a prompt, building an eval set, measuring RAG retrieval quality or validating an agent's tool config. Iterates with prompt_optimizer.py, scores RAG with rag_evaluator.py and checks agents with agent_orchestrator.py.
senior-qa
Use for generating or improving tests in React or Next.js apps (Jest, React Testing Library, MSW, Playwright, coverage gaps). Generates suites with test_suite_generator.py, scaffolds E2E with e2e_test_scaffolder.py and reads coverage with coverage_analyzer.py.
senior-secops
Use for application security operations: security reviews, CVE remediation, hardening, secrets and auth, or SOC 2, PCI-DSS, HIPAA and GDPR checks. Scans with security_scanner.py, assesses CVEs with vulnerability_assessor.py and checks controls with compliance_checker.py.
senior-security
Use for STRIDE threat modeling, DREAD scoring or a quick secret scan, or to route a security request to the right specialist. Models threats with threat_modeler.py and scans with secret_scanner.py.
sentry
Use when the user asks to inspect Sentry issues or events, summarize recent production errors, or pull basic Sentry health data via the Sentry CLI; perform read-only queries using the `sentry` command.
seo-audit
Use when a site is not ranking or needs an SEO audit (technical, on-page, meta tags), before giving advice. Scans pages with seo_checker.py and scores site health with seo_health_scorer.py.
Third-party instructions in their original language. Reading does not install files, run code or grant permissions. Snapshots are updated only after review.