medley-tools

Plugin medley-tools from marketplace medley56 in medley56/llm-tooling. Commands read from the repo's manifest — 1 month ago.

Skills (8)

• commit

  Decides what in the working tree belongs in a commit, writes a Conventional Commits message, and creates the commit locally. Invoked as /medley-tools:commit, or when the user asks to "commit this", "commit my changes", or "write a commit message". Excludes review and planning artifacts, and asks whe

• create-gauntlet-loop-prompt

  Interactively builds a "Gauntlet Loop" prompt — a goal-plus-quality-bar prompt that a coding agent runs as a builder/critic loop until the output matches or beats a reference standard. Use when the user says they want to "create a gauntlet loop", "run a gauntlet loop", "write a gauntlet prompt", "se

• create-presentation

  Creates a reveal.js HTML presentation from markdown content, a topic description, or rough notes. Use when the user asks to "create a presentation", "make slides", "build a slide deck", "create a reveal.js presentation", or provides content and asks for a presentation. Accepts optional theme prefere

• implement-change

  End-to-end path from a change request to implemented, verified code: reads the request from wherever it lives (a markdown file, a Jira ticket, a Notion page, a GitHub issue, or the prompt itself), runs the implementation-planner agent to draft an approach, runs it past the implementation-plan-review

• pr-create

  Writes a reviewer-focused description for the current branch and opens the pull request on GitHub. Invoked as /medley-tools:pr-create, or when the user asks to "open a PR", "put up a PR", "create a pull request", or "write a PR description". Opens a draft by default, for a self-review with pr-review

• pr-fix

  End-to-end handling of review feedback on a pull request: pulls the PR's unresolved comments, runs the github-pr-fix-planner agent to plan a response to each one, walks the user through them, implements the approved fixes, verifies and reviews the result, pushes, and replies on each comment thread.

• pr-review

  Pull request review: runs the github-pr-reviewer agent on a PR and reports its major weaknesses; on request, goes on to draft review comments, iterate on them with the user, and post the review to GitHub. Invoked as /medley-tools:pr-review, or when the user asks to "review this PR", "what's wrong wi

• ticket-refine

  Audits a draft ticket against the code and systems it will touch before it is assigned, so its scope holds up when a developer starts: confirms the goal, sends read-only investigators across every repo, doc, and ticket likely to be involved, trims the extra scope they claim down to what the goal can

Subagents (9)

• github-pr-fix-planner

  Pulls GitHub PR review comments and plans fixes. Use when the caller asks to "fix PR comments", "address review feedback", or "resolve PR review". Accepts a PR number, URL, or auto-detects the PR from the current branch. Uses GitHub MCP server tools to fetch comments; uses the gh CLI only when the c

• github-pr-reviewer

  Reviews GitHub pull requests and produces a structured code review document organized by concept, merging the findings of three implementation-reviewer agents — two on Sonnet, one on its own model — primed with a local-ci-runner agent's check results. Use when the caller asks to "review this PR", "r

• implementation-plan-reviewer

  Adversarially reviews a draft implementation plan before it goes to the user for approval, hunting for unnecessary complexity and missed details. Use when the caller has a drafted plan — from the implementation-planner agent or written by hand — and wants it challenged: "review this plan", "poke hol

• implementation-planner

  Explores a codebase and drafts an implementation approach for a proposed change. Use when the caller has a change request — a ticket, a spec, a feature brief, a bug report — and needs the approach worked out before any code is written. Returns the files involved, options with trade-offs, ordered ste

• implementation-reviewer

  Adversarially reviews a code change against the one set of review standards: correctness, security, performance, the repo's style, unnecessary abstraction, test coverage and factoring, documentation, and fidelity to the agreed plan or the change's stated intent. Has the local-ci-runner agent run the

• local-ci-runner

  Runs a repo's CI checks locally — tests, linters, type checkers, format checks — and reports what failed, and whether each failure predates the change when given a base ref. Use when the caller asks to "run the tests", "run pytest", "run the linters", "run CI locally", "check if this passes", or nee

• repo-instructions-update-planner

  Read-only planning agent that audits LLM instruction files and produces an update plan. Use when the caller asks to "update instructions", "sync instructions with code", "check instruction consistency", "audit LLM instructions", "review CLAUDE.md files", "review copilot-instructions", "check the roa

• ticket-scope-investigator

  Investigates one repo, documentation set, ticket trail, or web source against a draft ticket, before the ticket is assigned, to find incorrect claims, missing requirements, and undocumented scope the work cannot be done without. Use when the caller has a draft ticket and needs to know whether it und

• ticket-scope-trimmer

  Challenges scope that investigators claim a ticket needs, deciding item by item whether it must be part of the ticket to meet its goal, can be deferred to a separate ticket, or can be dropped. Use when the caller has a list of claimed additional scope for a draft ticket and wants it cut down: "trim