yokeloop

Finds problems in code, fixes them and produces a report. Used when the user writes "review", "code review", "find issues", "find bugs", "check code", "code analysis", "prepare a report", "what's wrong with the code", or after /do to analyze changes.

Prepares a project for the yoke flow — stack detection, generation of CLAUDE.md and yoke-context.md. Used when the user writes "bootstrap", "set up yoke", "prepare the project", "yoke init", "setup yoke", "first run", "connect yoke", "create CLAUDE.md".

Executes a task per plan. Triggered when the user writes "execute", "do", "run the plan", "implement", or passes a path to a plan file and asks to execute it.

Skill factory for the yoke plugin. Full pipeline for creating a new skill: task analysis, design with a mermaid diagram, implementation of SKILL.md and agents, quality validation, documentation creation, updating README and CLAUDE.md. Used when the user writes "create a skill", "new skill", "add a skill", "make a skill", "skill for".

Publishing the yoke plugin: quality checks, documentation validation, version bump, tag, push, GitHub release. Used when the user writes "release", "publish", "ship version", "make a release", "prepare a release", "new version".

Validates SKILL.md files changed in the current branch against elements-of-style (Strunk) for prose and plugin-dev's skill-development conventions for structure, applies safe fixes automatically, and reports the rest. Activates when the user writes "validate", "validate skill", "validate skills", "validate changed skills", "lint skills", "валидайт", "валидайт скилы", "прогони валидацию", "проверь

Codebase exploration and brainstorming. Activates when the user writes "explore", "explain", "compare", "what if", "brainstorm", "investigate", "figure out", "analyze", "how is it built", "how does it work", "tell me about", "why", "what are the options", "suggest an approach", "show the architecture".

Quick fix or follow-up change. Used when the user writes "fix", "patch", "correct", "tweak", "polish", "small fix", "quick fix", or describes a small change after /do.

Git staging and commit with smart file grouping. Activated when the user writes "commit", "gca", "make a commit", "commit changes", or after /task, /plan, /do, /review.

Builds an implementation plan from a task file. Triggered when the user writes "build a plan", "make a plan", "plan", "plan the implementation", "prepare a plan", or passes a path to a task file and asks to plan execution.

Creates or updates a GitHub Pull Request. Activated on "pr", "pull request", "create pr", "update pr", "open pr", or after /gp.

Turns the current conversation and codebase understanding into a PRD, publishes it as a GitHub issue, and saves a local copy in docs/ai. Does not interview — synthesizes what is already known. Activates when the user writes "prd", "create a prd", "write a prd", "turn this into a prd", "product requirements doc", "draft requirements".

Git push with checks and report. Used when the user writes "push", "gp", "git push", or after running /do and /review to send changes.

Docs-aware grilling: interrogates the user's plan one question at a time AND maintains the domain glossary (CONTEXT.md) and architecture decision records (docs/adr/) inline as decisions crystallise. Used to stress-test a plan against the project's language and documented decisions; for a plain interview that writes no files, use grill. Activates when the user writes "grill-docs", "grill with docs"

Interviews the user one interactive question at a time about a plan or design, walking each branch of the decision tree to a shared understanding; every question offers a recommended answer. A read-only interview that writes no files — for the variant that also captures terminology and decisions into CONTEXT.md and ADRs, use grill-docs. Activates when the user writes "grill", "grill me", "poke hol

Shows development status in the repository: branch, uncommitted changes, recent commits, diff vs main, hot files, semantic summary. Used when a developer writes "status", "gst", "git status", "what's going on", "repo state", "show changes".

Compacts the current conversation into a handoff document so a fresh agent can continue the work, referencing existing artifacts instead of duplicating them. Saves to the OS temp directory. Activates when the user writes "handoff", "hand off", "compact the conversation", "summarize for the next session", "prepare a handoff doc", "pass this to another agent".

Explains how to use yoke and lists the available skills; also greets new users. Activated when the user writes "help", "how do I use yoke", "how to use", "what skills are available", "hi", "hello", "where do I start", or on first contact with yoke.

Breaks a plan, spec, or PRD into independently-grabbable GitHub issues using vertical slices (tracer bullets), publishes them in dependency order, and saves a local index in docs/ai. Activates when the user writes "issues", "break into issues", "create tickets", "split into tasks", "decompose into issues", "make implementation tickets", "tracer bullets".

Regenerates the public skill catalog from `skills/*/SKILL.md` — per-skill MDX pages under `site/src/content/docs/skills/`, the table between `<!-- yoke:skills:start -->` markers in `README.md`, and the bullet list between the same markers in `CLAUDE.md`. Activates when the user writes "sync docs", "regenerate docs", "update the skill catalog", "rebuild docs", "refresh the catalog", or passes `--ch

Drafts a task file for AI implementation. Triggered when the user writes "create a task", "task from ticket", "draft a task", "prepare an implementation prompt", or passes a ticket URL / feature description.