Maintain a structured planning document tree made of roadmap/status files, implementation status or handoff TODO files, topic notes, decision records, open questions, ideas/inspiration pools, and repository/file-structure hygiene plans. Use when Codex needs to create, reorganize, audit, or update a multi-file plan…
Use when the user is debugging a bug, tracing an error, or asking why something fails. Examples: "Why is X failing?", "Where does this error come from?", "Trace this bug".
Use when the user asks about GitNexus itself — available tools, how to query the knowledge graph, MCP resources, graph schema, or workflow reference. Examples: "What GitNexus tools are available?", "How do I use GitNexus?".
Use when editing AgentHTML artifacts, agent-html files, Gallery Preview DSL, blocks, components, sections, prompt schema, or runtime-rendered artifact content. Before editing AgentHTML content, read .agents/skills/agent-html/references/prompt-schema.md for the current DSL contract and enabled component grammar.
A writing aid for academic papers in LaTeX, a system commonly used to format research documents. It also covers BibTeX, a tool for managing references, and checks writing and formatting rules.
Use when a mostly complete ML conference paper needs self-review, pre-submission QA, camera-ready checking, section-by-section critique, citation-risk inspection, or rebuttal/review-response drafting. Skip this for initial drafting and use paperreview only when the user explicitly wants external submission.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, or tool integrations.
Detect application-context mismatch after execution. Fires when correct output may not fit the actual context. Type: (ApplicationDecontextualized, AI, CONTEXTUALIZE, Result) → ContextualizedExecution.
Convergence-paced review-resolve loop over a change and its governing surfaces. Verifies each finding against the codebase and the base it is measured from, then re-reviews until each is disposed of.
A task-analysis skill that creates a written requirements analysis before implementation begins. It examines the task’s scope, context, effects on other parts, and risks from the supplied task reference.
A guide to organising project documentation and deciding what it should contain, including README files, contribution guides, architecture notes, and API documentation. A README is the main introduction to a project.
Load when reflecting on AI collaboration quality or tracking growth over time. Analyzes session history to surface how deeply you think with AI tools and whether your orchestration sophistication matches your cognitive depth. Provides actionable nudges to push toward more strategic work.
A one-time deployment tool that adds a project governance system built around AGENTS.md, project instructions, documentation, hooks, continuous integration, and maintenance scripts.
Use when bootstrapping, auditing, improving, or retrospecting on human-AI collaboration systems in a project, especially around context entrypoints, authority, staged scope, local drafts, verification, decision records, documentation drift, and correction loops.
Analyze the user's Claude Code collaboration style. Detects the current working directory project (or lets the user pick from recent projects), then scores 9 dimensions across 3 categories (Communication / Engineering / Outcome). Baselines are computed deterministically by scripts; Claude adds a bounded evidence-cited…
Alternative Slowbar coffee intelligence — scientific analysis from seed to cup using First Principle + System Thinking. Covers: varieties, terroir, cultivation, disease diagnosis, processing, roasting physics/chemistry, extraction science, brewing, business strategy, storytelling. ALWAYS trigger for coffee-related…