Backend-agnostic project management for AI-native teams. Ingests research, triages and specs work items, coordinates risk-gated sprint execution, and syncs with GitHub Issues. Also includes an explicit single-task managed workflow (/pm:dev-task).
Plugin pm from marketplace studio-moser in Studio-Moser/skills-n-stuff. Commands read from the repo's manifest — 2 days 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.
dev-taskRuns the managed, approval-gated workflow for one large, multi-file Feature-class change. Use when such a change needs that workflow or the user asks for it, such as building a new feature across several files, implementing an approved spec or tracker item end to end, or wanting a plan to approve be
feature-walkthroughRecords a browser walkthrough video of a finished web feature. Use when the user asks for, or accepts an offer of, a recorded walkthrough, demo video, or screen recording of a web feature. Not for native or simulator apps.
house-rulesProvides Studio Moser conventions for change classes, branches, file naming, commits, pull requests, testing, and pre-commit security checks. Use when naming a branch or file, writing a commit message or PR body, choosing tests for a change, or running the pre-commit security check.
ingestImports new Product Pulse daily, weekly, or deep-dive reports into the configured issue tracker. Use when new reports are ready to import. Not for triaging existing candidates or reconciling completed work.
reconcileReconciles the issue tracker against git history and current project state. Use when the tracker may be stale after merges or sprints, or for a periodic reality check. Not for deciding new items or implementing ready work.
setupConfigures PM's issue-tracker backend for a workspace. Use when PM is not yet configured or the user asks to reconfigure it.
shipCarries the current change, or someone else's pull request, to a ready-to-merge or merged PR without further check-ins: proves it, files the PR, watches checks and reviews, fixes findings, and asks only when blocked. Use when the user says "full stop" (stop when ready to merge) or "full send" (merge
sprint-devBuilds ready owner/ai backlog items from the configured tracker as one sprint. Use when the user asks for a sprint.
tidy-upCleans up the current repository after merged work: fetches the remote first, proves which branches, worktrees, and stashes are already in the base branch, integrates or keeps unmerged work, and deletes merged local and remote branches after one approved plan. Use when the user asks to tidy up, clea
triageMakes keep, reject, and deduplication decisions on `status/needs-triage` items and prepares kept items for execution. Use when items await triage. Not for raw-report ingestion, ready-item implementation, or tracker reconciliation.
code-reviewerBuilds a read-only PM review request for one fixed target, applies the development-specific review axes, and consumes evidence from Harness. Never modifies code.
${CLAUDE_PLUGIN_ROOT}/scripts/check-prereqs.sh $(yq '.backend // "github"' "$(git rev-parse --show-toplevel 2>/dev/null || echo .)/.pm/config.yml" 2>/dev/null || echo github)
Design exploration rounds: fan one brief out into independent HTML variants built by named skills and models, gate first drafts with fresh-context critics, picture them and place the round in a Figma file where each variant opens its live page, edit variants in the page with impeccable live, and carry what the owner wants into the next brief.
6 skills · 6 agents
Lightweight provider-neutral control plane for cost-aware rubric execution, mechanical risk gates, bounded delegation and review, portable personal setup, and evidence-bearing results.
7 skills · hooks
Strategic intelligence system for product teams. Weekly strategy briefs, daily market research, and deep-dive analysis — a three-cadence intelligence system that keeps you focused on what matters.
4 skills
Governed image, video, and audio generation over the Kie.ai MCP. The models are the easy part — this adds the discipline around them: prices a batch and stops for confirmation before spending, downloads every result locally before URLs expire, and logs the prompt that produced each file. Can run exploration rounds on a Flora canvas, where every prompt and iteration stays visible and editable.
1 skill
Serve temporary private previews of local websites through the host's Tailscale, as real pages that outlive the agent session.
1 skill
Transcribe spoken-word audio from YouTube, Shorts, Instagram, TikTok, and Threads. YouTube captions fetched directly (fast, no model). Falls through to local mlx-whisper on Apple Silicon, with a headless-Playwright fallback for Threads.
1 skill
Talk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
Package any website or local web build into a lightweight desktop app with Pake CLI.
1 skill
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.