A spec-driven workflow: /milestone keeps local-only project direction and optionally syncs epic progress read-only from Beads; /specify authors stories/epics, /refine revises a story, /board shows the backlog, /solve implements one in an isolated worktree, /validate merges after human review, and /orchestrate runs ordered story/epic targets behind one GitHub PR or GitLab MR with explicit post-merge --finalize for complete epics. Requires bd for the story workflow and milestone sync.
Plugin sdd from marketplace sdd in codxse/sdd. Commands read from the repo's manifest — 1 month ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
boardShow the bd backlog as a status board, or one story by its id. Read-only, any model tier. Use when the user asks to see/list/view their stories, "show the board", or "show story <id>".
milestoneCreate, show, update, or sync the local-only project milestone stored in .milestone.md. Uses a lightweight Socratic loop to clarify the outcome, then tracks done conditions, current epic, bd epic progress, and milestone work not yet represented by an epic. Use when the user asks to set a milestone,
orchestrateAutomate /solve -> review -> land across an ordered set of bd stories and/or epics, with one integration branch and one final GitHub PR or GitLab MR. Frontier model only. Epics expand to their story children; input order controls serial scheduling, --parallel dispatches a ready wave, and --finalize
refineRevise an existing bd story contract by id — typically one labelled needs-refinement after a /solve spec-gap or /validate change-request. Frontier model only; WHAT-only, never code, and returns the story to ready for /solve. Use when the user asks to refine/revise/update a story.
solveImplement one bd story by id in an isolated git worktree+branch at .worktree/<id>, ending at needs-review for /validate. Any tier — matched to the story''s own complexity call. --unattended (passed by /orchestrate when dispatching headless) turns every live question into the spec-gap stop-and-hand-b
specifyAuthor one bd story, or decompose a large goal into an epic. Frontier model only. Authoring only — /board views, /refine revises. Use when the user asks to specify or spec out a problem or goal, open a case, or write a new story or epic.
validateHuman review gate for a needs-review story by id: runs a review pass at effort high via a rung-pinned reviewer subagent that applies fixes in place on bd/<id>, then enacts your verdict — approve (land it on the branch it was forked from, close, unblock dependents), another pass, or a wrong contract
story-reviewer-strongReview-and-apply for one bd story branch during /validate — runs code-review-quality (or the host's own code review) with fixes applied against the story's contract inside its worktree, leaves fixes unstaged. Frontier-rung reviewer, for solver-frontier stories, same-rung step-ups, and the default wh
story-reviewerReview-and-apply for one bd story branch during /validate --unattended — runs code-review-quality (or the host's own code review) with fixes applied against the story's contract inside its worktree, leaves fixes unstaged. Medium-rung reviewer, for solver-budget and solver-medium stories. Spawned by
sh "${CLAUDE_PLUGIN_ROOT}/hooks/session-context.sh"
sh "${CLAUDE_PLUGIN_ROOT}/hooks/session-context.sh"
Multi-axis code review before merge — correctness, readability, architecture, security, performance — reported as severity-labelled findings and a verdict. Reviews the working diff by default, or a commit, branch, tag, path, or PR. --effort sets depth; --fix applies the fixes in place and leaves them uncommitted. Any model tier; no dependencies.
1 skill
Skill for creating and updating CLAUDE.md and other LLM project context files. Teaches what to include, what to omit, and how to keep context lean.
1 skill
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Backend API design, GraphQL architecture, workflow orchestration with Temporal, and test-driven backend development
9 skills · 1 command · 8 agents
AI-supervised issue tracker for coding workflows
1 skill · 1 agent · hooks
PRD generation and conversion skills for the Ralph autonomous agent loop
2 skills
MiniMax AI skills library for frontend, fullstack, Android, iOS, shader, GIF sticker, document, presentation, spreadsheet, and multimodal media workflows
18 skills
Worktrunk is a CLI for Git worktree management, designed for parallel AI agent workflows. This plugin provides configuration guidance (LLM commit messages, project hooks, worktree paths), automatic activity tracking (🤖/💬 indicators in `wt list` showing active Claude sessions), and a `/wt-diff` pane showing each worktree's changes.
2 skills · hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.