delivery-team
claudeFive virtual delivery teams (intake, qa, build, release, status) that run a request through plan -> test -> build -> release, plus a read-only status reconciler.
6 skills · 28 agents
Evaluates a folder's outstanding work (typically team-status's stage-map) and gets it moving on whatever track it actually needs. `triage` sorts outstanding items into direct-fixable housekeeping, real work that needs team-intake first, and things only a human can do — then dispatches the first two. `dispatch` decides whether build-ready items should build in parallel worktree efforts, sequentially, or as a single normal session, then dispatches and babysits the runs through to merge. Generic — works on any project using the delivery-team pipeline conventions.
Plugin engineering-manager from marketplace ember-toolkit in saralafleur/ember-claude-toolkit. Commands read from the repo's manifest — 21 days ago.
engineering-managerEvaluates a folder's outstanding work (typically team-status's stage-map) and gets it moving on whatever track it actually needs. `triage` sorts outstanding items into direct-fixable housekeeping, real work that needs team-intake first, and things only a human can do — then dispatches the first two.
em-analystIndependence analyst for the engineering-manager dispatch/triage process. Reads a candidate set of work items — either build-ready items (for dispatch) or not-yet-planned request items (for triage's intake phase) — and determines whether they can safely run concurrently, must run sequentially, shoul
em-judgeOne independent vote in the engineering-manager dispatch/triage judge panel. Invoked 2-3x in parallel, only when em-analyst flags LOW confidence or a genuine ambiguity, to pressure-test whether a set of items — build-ready (dispatch) or not-yet-planned (triage) — should run in parallel, sequentially
em-leadEngineering-manager lead / synthesizer for the dispatch or triage decision. Merges em-analyst's findings (and em-judge's panel votes, if one ran) into a single plan document — dispatch-plan.md for build-ready items (parallel/sequential/single-session, per-item dispatch spec, merge order) or triage-p
Five virtual delivery teams (intake, qa, build, release, status) that run a request through plan -> test -> build -> release, plus a read-only status reconciler.
6 skills · 28 agents
Runs a virtual product team over any web solution — a local repo/folder, or a described live app — and produces one ranked top-10 list of what to build next: `product` for feature/end-user recommendations, `tech` for technical/hardening recommendations. Triage profiles the solution, three specialists (UX, technical, market) propose evidence-grounded candidate features in parallel, an independent validator cross-checks every candidate twice (blind to each other), and a lead reconciles both passes into the requested ranked top 10.
1 skill · 6 agents
The team librarian — curates durable knowledge into a shared, growing library so repeat work approaches one-shot. Organizes knowledge by domain/subdomain/topic with retrieval descriptions, keeps a single Table of Contents, audits its own descriptions and itself for thrashing, and gates every write behind human approval.
1 skill · 3 agents
Two repo-level workflow skills: wrap-up (close out a unit of work — audit, human gate, commit, push, merge, clean up) and create-skill-devops (scaffold a project-scoped /devops toolbox for build-environment setup).
2 skills
Scaffolds a complete, populated UAT story map for an application — discovers roles, workflows, and routes from the codebase, then generates a full role-first test folder tree (happy paths, edge cases, run sheet, scope matrix) plus ready-to-run Playwright MCP UAT execution and status-reset agent prompts.
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.