Penetration testing labs require careful state tracking across reconnaissance, exploitation, and privilege escalation. This skill coordinates an authorized lab workflow with structured notes, attempts, and completion criteria.

Security teams need a structured way to review exploit workflows and understand operational risk. This skill organizes exploitation methods, payload choices, and post-access checks for controlled lab or audit review.

Authorized security labs often require tracking across recon, exploitation, and privilege escalation. This skill coordinates agent delegation and state-driven decisions for controlled CTF-style assessments.

Development sessions are hard to reconstruct after commits, tool changes, and context switches. This skill guides Chronicle session tracking, summaries, search, and Obsidian documentation from one workflow.

Development sessions are hard to review when details stay in chat history or local logs. This skill turns Chronicle data into structured Obsidian notes with summaries, metadata, and links.

Remote Chronicle sessions can be hard to summarize when the source machine lacks Gemini access. This skill guides export, local summarization, and structured import back to the source system.

Development work can become hard to connect to milestones, sessions, and roadmap priorities. This skill uses Chronicle MCP tools and CLI workflows to track progress and next steps.

Teams lose track of decisions, blockers, and prior implementation details across development sessions. This skill searches Chronicle history and returns focused context for current work.

AI assistants lose time when they ignore prior Chronicle sessions and roadmap context. This skill guides them to search history, choose MCP or CLI, and reuse project knowledge.

Complex agent work can fail when one context window carries every task. This skill helps Claude, Codex, and Claude Code design agent systems with clear handoffs.

Long AI sessions can waste tokens, slow responses, and lose important context. This skill gives Claude, Codex, and Claude Code practical patterns for compacting, masking, caching, and budgeting context.

Agent systems can become unreliable when prompts, tools, history, and retrieval compete for context. This skill explains context components and practical patterns for budgeting, progressive disclosure, and validation.

Long conversations and large prompts can make AI agents lose important information or follow conflicting context. This skill helps Claude, Codex, and Claude Code identify degradation patterns and choose mitigation strategies.

LLM evaluation is hard to make consistent across teams and models. This skill helps design judge prompts, rubrics, metrics, and bias checks for repeatable assessments.

Teams lose context when technical choices are made without a durable record. This skill creates clear ADRs that capture options, rationale, consequences, and reversal cost.

Daily status updates often become too long or vague for fast team coordination. This skill turns work notes into concise standup reports with clear outcomes, focus items, and blockers.

Teams need consistent structures for reusable domain guidance. This skill provides a customizable template for frameworks, processes, outputs, anti-patterns, and intake questions.

Code reviews can become inconsistent, vague, or overly focused on style. This skill applies a three-pass method, practical checks, and focused feedback.

API teams need fast proof that documented endpoints work together before deeper testing. This skill parses specifications, builds ordered flows, and generates Python scripts that exercise expected successful paths.

Teams using two AI agents need clear roles, task states, and handoff rules. This skill explains a Cursor and Claude Code workflow with examples.