technical-debt-detector
Identify and prioritize technical debt in Python codebases. Use when the user asks to find tech debt, analyze code quality, identify what needs refactoring, find security issues, check test coverage gaps, review dependencies, find TODOs/FIXMEs, or assess maintainability. Triggers on phrases like "find technical debt", "what's wrong with this codebase", "where should I focus refactoring", "audit this code", "find TODOs", "check for security issues", "analyze dependencies", or "what needs tests". Complements python-simplifier skill (use that for complexity and code smell analysis).
code-auditor
Analyze a project to provide a summary of line counts per programming language (e.g., how many lines of Go vs Rust). Generates a PDF summary report.
detecting-anomalies
Detect anomalies in metrics and time-series data using OPAL statistical methods. Use when you need to identify unusual patterns, spikes, drops, or outliers in observability data. Covers statistical outlier detection (Z-score, IQR), threshold-based alerts, rate-of-change detection with window functions, and moving average baselines. Choose pattern based on data distribution and anomaly type.
performance-patterns
Use when user asks about N+1 queries, performance optimization, query optimization, reduce API calls, improve render performance, fix slow code, optimize database, or reduce bundle size. Provides guidance on identifying and fixing performance anti-patterns across database, backend, frontend, and API layers.
aggregating-gauge-metrics
Aggregate pre-computed metrics (gauge, counter, delta types) using OPAL. Use when analyzing request counts, error rates, resource utilization, or any numeric metrics over time. Covers align + m() + aggregate pattern, summary vs time-series output, and common aggregation functions. For percentile metrics (tdigest), see analyzing-tdigest-metrics skill.
research-strategy
Conduct systematic research with confidence scoring, source validation, and structured reporting for technology decisions and codebase analysis. Use for complex research tasks, technology selection, or best practice discovery.
benchmark-report-creator
Use PROACTIVELY when creating research reports, experiment writeups, technical whitepapers, or empirical study documentation. Orchestrates the complete benchmark report pipeline with structure, diagrams, hi-res PNG capture, and PDF export. Provides working scripts, CSS templates, and complete command sequences for publication-quality AI/ML benchmark reports. Not for slides, blog posts, or simple README files.
db-anti-patterns
Detection rules and grep patterns for database performance anti-patterns. Use when scanning codebase for N+1 queries, sequential queries, or connection pool issues.
use-case-data-patterns
Analyzes how user-facing use cases map to data access patterns and architecture. Auto-triggers when: implementing new features that need existing pattern understanding, explaining how a feature works in the data layer, planning changes affecting data access, asking "how does X work in our codebase?", or tracing a user action through the system architecture.
time-series-analysis
Analyze event datasets (logs) and intervals over time using OPAL timechart. Use when you need to visualize trends, track metrics over time, or create time-series charts. Covers timechart for temporal binning, bin duration options (1h, 5m, 1d), options(bins:N) for controlling bin count, and understanding temporal output columns (_c_valid_from, _c_valid_to, _c_bucket). Returns multiple rows per group for time-series visualization. For single summaries, see aggregating-event-datasets skill.
performance
Performance optimization and bottleneck detection. Identifies N+1 queries, memory leaks, async issues, and caching opportunities. Use when investigating slow operations, optimizing response times, or detecting performance issues.
dspy-framework
Expert guidance for using the DSPy framework to design, optimize, debug, and refactor LLM programs. This skill should be used when asked to use DSPy, when a task involves DSPy components, when changing code that impacts a DSPy implementation, or when analyzing a codebase for DSPy opportunities.
languages-frameworks
Expert guidance on 9 programming languages and 10+ frameworks. Compare, select, and master language ecosystems.
local-knowledge
Leverage personal notes and documentation through Terraphim's role-based search. AI agents can search developer's local knowledge organized by domain (Rust, frontend, architecture) using the terraphim-agent REPL commands.
vibe-coding-security-awareness-overview
Understand the security risks inherent in AI-generated code and vibe coding. Use this skill when you need to understand why AI generates insecure code, statistics on vulnerabilities, real-world breach examples, or overall security awareness for AI-assisted development. Triggers include "vibe coding security", "AI code security", "AI vulnerabilities", "security risks AI code", "why AI insecure", "AI security awareness", "AI generated code risks".
extracting-session-data
Locates, lists, filters, and extracts structured data from Claude Code native session logs. Supports both single and multiple session analysis.
code-explainer
Explains code in beginner-friendly terms. Use when user asks 'what does this do', 'how does this work', 'explain this code', or needs to understand generated code. Breaks down complex code into simple explanations for learning.
debugging-systematically
AI agent follows a 5-phase debugging process with reproduction, isolation, hypothesis testing, and root cause resolution. Use when investigating bugs, troubleshooting issues, or hunting errors.
langfuse-trace
Analyze Langfuse trace JSON exports using jq queries. Use when user provides a Langfuse trace file (.json) for analysis, debugging agent behavior, checking token usage, or investigating tool calls. Triggers on phrases like "analyze trace", "check this langfuse", "debug agent run", or when user shares a trace JSON file path.
deep-research
Deep technical research using Firecrawl Agent for autonomous web investigation, competitive analysis, and implementation pattern discovery.
semantic-intelligence
Use Julie's semantic search capabilities for conceptual code understanding. Activates when searching for concepts, cross-language patterns, business logic, or exploring unfamiliar code. Combines text and semantic search for optimal results.
local-knowledge
Leverage personal notes and documentation through Terraphim's role-based search. AI agents can search developer's local knowledge organized by domain (Rust, frontend, architecture) using the terraphim-agent REPL commands.