immacualate

An integrated skill for exploring and searching skills/prompts. It activates when users request skill installation, prompt search, or prompt improvement.

Agent Teams Orchestration Engine for team formation, task distribution, dependency management, and result aggregation.

Executes all project verify skills to generate an integrated pattern verification report. Use after feature implementation, before PR, and during code review.

This automatic cleanup skill activates before a session ends, using four parallel subagents to detect document updates, recurring patterns, learning points, and follow-up tasks, while a verification subagent removes duplicates and presents options to the user. Triggers include /session-wrap, session wrap-up, session cleanup, and task wrap-up.

Manage major dependency version upgrades with compatibility analysis, staged rollout, and comprehensive testing. Use when upgrading framework versions, updating major dependencies, or managing breaking changes in libraries.

Summarizes or extracts text/transcripts from URLs, podcasts, and local files, serving as a great fallback for transcribing YouTube videos.

Apply STRIDE methodology to systematically identify threats. Use when analyzing system security, conducting threat modeling sessions, or creating security documentation.

Analyzes session changes to detect missing validation skills. Dynamically explores existing skills, creates new ones, or updates existing skills, then manages the project CLAUDE.md.

Security Pipeline - Automated verification for CWE Top 25 and STRIDE.

Integrated Verification Engine - Sub-agent based fresh-context verification loop (v6)

Skill to automatically detect and execute project build systems.

Optimizes the Claude Code development workflow by offering Context Engineering, Sub-agents, TDD, and post-development verification. It is triggered by CC project start, CLAUDE.md/spec.md creation, and commands like /handoff, /verify, /commit-push-pr, sub-agent/Explore, or parallel development requests with Agent Teams.

Master systematic debugging techniques, profiling tools, and root cause analysis to efficiently track down bugs across any codebase or technology stack. Use when investigating bugs, performance issues, or unexpected behavior.

Trigger when the user requests a review of frontend files (e.g., .tsx, .ts, .js). Support both pending-change reviews and focused file reviews while applying the checklist rules.

Evaluates LLMs across 60+ academic benchmarks like MMLU and HumanEval. It's an industry standard used by EleutherAI, HuggingFace, and major labs for benchmarking model quality, comparing models, and tracking training progress, supporting HuggingFace, vLLM, and APIs.

Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.

Guides security professionals in implementing defense-in-depth security architectures, achieving compliance with industry frameworks (SOC2, ISO27001, GDPR, HIPAA), conducting threat modeling and risk assessments, managing security operations and incident response, and embedding security throughout the SDLC.

Analyzes session work to automatically convert reusable patterns into Claude Code skills. It actively analyzes sessions, checks for duplicates, and creates new skills, differing from other skill management tools.

Expert guidance for Next.js Cache Components and Partial Prerendering (PPR).

Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks using pass@k metrics. This industry standard from the BigCode Project, used by HuggingFace leaderboards, is ideal for benchmarking code models and measuring code generation quality.

Use when adding new error messages to React, or when encountering "unknown error code" warnings.

Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles.

Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills, commands, or agents.