Setup modular y extensible para trabajar con Python, R y Quarto en Neovim, con integración profunda de IA (local + remota) y gestión de conocimiento.
This repository also configures its own agents. See what dotmesh tells them →
Skill Claude CodeCodex
Writing rules for prose that does not read as AI-generated. Covers inflated importance, promotional wording, vague attribution, forced rules of three, em dash and bold abuse, chatbot fingerprints. It says what to cut; redaccion-explicativa says what a text must carry, and wins when they pull apart. Load before…
Skill Claude CodeCodex
Designs stable interfaces. Use when defining APIs, CLIs, module boundaries, config schemas, file formats, component props, commands, or any contract other code or users depend on.
Skill Claude CodeCodex
Spanish writing rules for peninsular formal Spanish. Load when drafting or editing Spanish text that lands in a deliverable: README, doc, report, informe, ficha, visible UI text in a frontend (JSX/TSX, Vue, Svelte, HTML, i18n string files) or a slide deck (.pptx, slides artifact). Chat replies to the user do not load…
Skill Claude CodeCodex
Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensions before it enters the main branch.
Skill Claude CodeCodex
Simplifies working code without changing behaviour. Use after code works but is harder to read, test, review, or maintain than necessary, or when reviewing avoidable complexity.
Skill Claude CodeCodex
Guides systematic debugging. Use when tests fail, builds break, commands error, runtime behaviour is unexpected, or a previous fix did not address the root cause.
Skill Claude CodeCodex
Reads mesh-review V2 event-sourced review threads and acts on a document's open comments. Use when the user wants an AI agent to process review comments anchored to a document, when you find events under .ai/review/, or when asked to resolve, address, or work through review comments on a document.
Skill Claude CodeCodex
Documents durable decisions and context. Use when making architecture or tooling decisions, changing interfaces, adding conventions, or recording knowledge future humans or agents will need.
Skill Claude CodeCodex
Build and sharpen a project's domain model (its ubiquitous language). Use when pinning down domain terminology, when another skill needs to maintain CONTEXT.md, or when a fuzzy or overloaded term needs a canonical definition.
Skill Claude Code
Use this skill to generate well-branded interfaces and assets for dotmesh — a personal, monochrome-first developer design system (Microsoft-style black & white with muted syntax accents) for theming terminal, editor, prompt and macOS surfaces — either for production or throwaway prototypes/mocks/etc. Contains…
Skill Claude CodeCodex
Structures git workflow practices. Use when making any code change. Use when committing, branching, resolving conflicts, or when you need to organize work across multiple parallel streams.
Skill Claude CodeCodex
Get relentlessly interviewed about a plan or design until every branch of the decision tree is resolved. User-facing trigger for a grilling session.
Skill Claude CodeCodex
Interview the user relentlessly about a plan or design until you reach a shared, documented understanding. Use when the user wants to stress-test a plan or requirements before building, or uses any 'grill' / 'grill me' trigger phrase. Also records glossary terms and ADRs when the plan sharpens domain terminology or…
Skill Claude CodeCodex
Compact the current conversation into a handoff document so another agent can pick up the work. Use when switching between OpenCode, Claude Code and Codex mid-task, or when ending a session with work still in flight.
Skill Claude CodeCodex
Control herdr from inside it. Manage workspaces and tabs, split panes, spawn agents, read output, and wait for state changes — all via CLI commands that talk to the running herdr instance over a local unix socket. Use when running inside herdr (HERDRENV=1).
Skill Claude CodeCodex
Refines vague ideas before planning or implementation. Use when the user has a rough concept, competing options, an unclear problem, or asks to ideate, stress-test, or choose a direction.
Skill Claude CodeCodex
Delivers changes incrementally. Use when implementing any feature or change that touches more than one file. Use when you're about to write a large amount of code at once, or when a task feels too big to land in one step.
Skill Claude CodeCodex
Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible.
Skill Claude CodeCodex
Reviews security-sensitive work. Use when handling secrets, tokens, credentials, permissions, user or local data, external input, shell commands, dependencies, auth, storage, logs, or network integrations.
Skill Claude CodeCodex
Grounds implementation in current sources. Use when code, config, commands, APIs, SDKs, frameworks, CLIs, or best practices depend on versioned or external documentation.
Skill Claude CodeCodex
Creates specs before coding. Use when starting a new project, feature, or significant change and no specification exists yet. Use when requirements are unclear, ambiguous, or only exist as a vague idea.
Skill Claude CodeCodex
Drives development with tests. Use when implementing any logic, fixing any bug, or changing any behavior. Use when you need to prove that code works, when a bug report arrives, or when you're about to modify existing functionality.
Skill Claude CodeCodex
Handles failed tool calls safely. Use when a tool, command, MCP call, filesystem operation, network request, or agent action fails and you are considering a retry or recovery step.
Skill Claude CodeCodex
Stop agent work until a human gives a closed decision. Use when a task is blocked on human choice, approval, credentials, destructive action, ambiguous scope, or review/security findings. In OpenCode, prefer the native question tool; elsewhere emit WAITFORUSER: and stop.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: