robsonrung
59 skills with substantive source documentation and an official publisher or observed installation demand. Read each skill’s original documentation through its card.
robsonrungreview-gate
Return a machine-readable review verdict for a PR or branch. Use when a workflow needs a merge gate with structured evidence; use full-review for a human-facing review.
- instalações
- 3
- GitHub Stars
- 2
- Atualizado
- 8 de set.
robsonrungadvanced-react
Plan, implement, or review React component structure, state placement, re-renders, and async behavior using composition first. Use for component design or behavior problems; use react for compiler setup and version-specific APIs.
- instalações
- 2
- GitHub Stars
- 2
- Atualizado
- 8 de set.
robsonrungagent-architecture-lens
Review agent control flow, durable state, retries, and recovery. Use when choosing a loop or state graph, or when a tool-calling workflow must survive failures and resume safely.
- instalações
- 2
- GitHub Stars
- 2
- Atualizado
- 8 de set.
robsonrungagents-md-craft
Create, audit, or simplify project instruction files such as AGENTS.md and CLAUDE.md. Use to fix instruction drift or separate conditional guidance; use skill-expert for SKILL.md files.
- instalações
- 2
- GitHub Stars
- 2
- Atualizado
- 8 de set.
robsonrungarchitecture-lens
Review code-level coupling, cohesion, dependency direction, and module boundaries. Use when deciding where code belongs or whether to split, merge, or refactor a module; use macro-architecture for system shape.
- instalações
- 2
- GitHub Stars
- 2
- Atualizado
- 8 de set.
robsonrungbrainstorm
Explore an uncertain idea and recommend whether to build, defer, reduce scope, or reject it. Use for brainstorming or a build decision; use interview-me next to settle requirements.
- instalações
- 2
- GitHub Stars
- 2
- Atualizado
- 8 de set.
robsonrungbrowser-smoke
Smoke-test the routes a branch or PR changes in a real browser. Use when the user asks to smoke-test a branch or PR, test affected pages, or run a diff-scoped browser test. It tests changed routes, not whole-product release QA.
- instalações
- 2
- GitHub Stars
- 2
- Atualizado
- 8 de set.
robsonrungcapture-learning
Capture a verified, reusable solution in docs/solutions. Use when asked to document a solved problem or when a delivery workflow selects learning capture; use session-handoff for work continuity.
- instalações
- 2
- GitHub Stars
- 2
- Atualizado
- 8 de set.
robsonrungclaude-runner
Execute prompts using Claude CLI in headless print mode from the current workspace. Use when users explicitly request Claude execution, when a cross-runner workflow selects Claude as the preferred model, or when repo automation needs a Claude CLI seat alongside the other runner seats.
- instalações
- 2
- GitHub Stars
- 2
- Atualizado
- 8 de set.
robsonrungclean-code
Refactor existing code with behavior-preserving Clean Code practices. Use for local naming, readability, duplication, or structure problems; use architecture-lens for module boundary decisions.
- instalações
- 2
- GitHub Stars
- 2
- Atualizado
- 8 de set.
robsonrungcline-runner
Run a prompt through Cline CLI with structured output. Use when Cline is requested or an approved workflow selects a Cline provider/model route, including the Muse and Minimax seats.
- instalações
- 2
- GitHub Stars
- 2
- Atualizado
- 8 de set.
robsonrungcmux-cli
Control cmux workspaces, panels, terminal input, notifications, and sidebar state through its CLI. Use when the user asks to inspect or manage cmux, create or target a workspace or panel, send text or keys, or report task status in cmux.
- instalações
- 2
- GitHub Stars
- 2
- Atualizado
- 8 de set.
robsonrungcodex-runner
Execute prompts using Codex CLI in non-interactive exec mode. Use when users explicitly request Codex execution, when a workflow needs a Codex CLI run inside this repository, or when a cross-runner workflow selects Codex as the preferred model and native Codex subagents are unavailable.
- instalações
- 2
- GitHub Stars
- 2
- Atualizado
- 8 de set.
robsonrungcoding-design-plan
Plan the implementation shape of one approved coding task. Use when a module, data, API, component, or deployment boundary still needs a design decision; use to-tasks for task decomposition.
- instalações
- 2
- GitHub Stars
- 2
- Atualizado
- 8 de set.
robsonrungcoding-review-simplify
Review a completed code change for behavior-preserving simplification, local correctness, and maintainability. Use after implementing a scoped task or when the user asks to simplify a concrete diff. Do not use as a full feature review or to choose the delivery reviewer plan.
- instalações
- 2
- GitHub Stars
- 2
- Atualizado
- 8 de set.
robsonrungcollaborative-delivery
Deliver an approved task through an auditable multi-model panel with test, review, and verification evidence. Use when the user requires a recorded panel trail for implementation. For the normal fast path, use implement-and-review or implement-tasks.
- instalações
- 2
- GitHub Stars
- 2
- Atualizado
- 8 de set.
robsonrungconsensus-summary-html
Render an existing models-consensus result as a self-contained HTML decision brief. Use when asked to visualize a council report; preserve its opinions and evidence without running a new council.
- instalações
- 2
- GitHub Stars
- 2
- Atualizado
- 8 de set.
robsonrungdata-systems-coding-lens
Review implementation risks in persistent state and asynchronous data paths. Use for schemas, migrations, queues, caches, retries, or concurrent writes; use macro-architecture to decide service and data ownership.
- instalações
- 2
- GitHub Stars
- 2
- Atualizado
- 8 de set.
robsonrungdcode-runner
Execute prompts using DeepAgents CLI (dcode) non-interactive mode with the user's already-configured model and credentials. Use only when the user explicitly requests dcode or DeepAgents execution. It is not an approved implementation or review route.
- instalações
- 2
- GitHub Stars
- 2
- Atualizado
- 8 de set.
robsonrungdecide-about-disagreements
Help the user resolve material disagreements in an existing models-consensus result. Present recorded opinions, distinct options, and a recommendation for each open decision without rerunning the council or implementing it.
- instalações
- 2
- GitHub Stars
- 2
- Atualizado
- 8 de set.
robsonrungdesign-gate
Select relevant design lenses for a planned slice and return a proceed-or-revise verdict. Use during task planning or when a design boundary changes; invoke a named lens directly for a single-lens review.
- instalações
- 2
- GitHub Stars
- 2
- Atualizado
- 8 de set.
robsonrungdesign-patterns
Choose or review a Gang-of-Four pattern when recurring code structure creates a concrete design problem. Use to compare a named pattern with a simpler design; use architecture lenses for system boundaries.
- instalações
- 2
- GitHub Stars
- 2
- Atualizado
- 8 de set.
robsonrungdiagnose
Find and prove the cause of a bug, failing test, or unexpected behavior. Use for unexplained failures, including pipeline verification failures; an understood failure within a TDD loop stays with tdd.
- instalações
- 2
- GitHub Stars
- 2
- Atualizado
- 8 de set.
robsonrungdistributed-systems-patterns
Choose or review distributed topology and event-stream patterns. Use for replicas, shards, container helpers, queues, or event-driven adoption and migration; use macro-architecture for overall system style.
- instalações
- 2
- GitHub Stars
- 2
- Atualizado
- 8 de set.