Gerencia o ciclo de vida completo de trilhas de trabalho (abertura com scaffolding, transição de blocos, fechamento e arquivamento em finalizadas/, propagação de conhecimento para a Wiki e auditoria de invariantes). Use ao criar, atualizar, passar de bloco, fechar ou auditar qualquer trilha.
Drives the user's standard project-start ritual as one unified command. Writes three docs into the project's documents/ folder: (1) a dialogue-first spec.md, (2) an MVP-sliced living plan.md with 🤖/🧑 verification gates, (3) a design.md handed to a design AI. Invoke this whenever the user is starting a NEW project or…
Initialize and maintain project-scoped governance documents for large or long-running work. Use when the user wants a documentation-driven workflow, needs to prevent context drift or stale-file interference, wants spec/design/audit/lessons/decision docs, or wants plan-first handling before non-trivial changes.
A project-management guide for coordinating work from project setup through planning and execution. It includes role definitions, plan checking, and guidance for choosing skills in different situations.
Execute a PRD autonomously using Amp's native features. Converts PRD to JSON, creates branch, implements stories, commits, and tracks progress. Triggers on: execute this prd, run amp-ralph on, implement this prd, start autonomous execution.
Reference for interacting with GitHub (gh CLI), and the Atlassian stack — Jira, Confluence, Bitbucket, JSM — via atlassian-cli. Use when reading/writing issues, PRs, pages, or comments in any of these tools.
Maintain a lightweight docs/tasks/ repo convention for coding-agent tasks and open questions: bootstrap the folder, create task/question markdown files, update status, close or reopen items, list open work, and rebuild the derived index.
High-seniority project manager agent. Plans work, decomposes requests into high-quality tasks with clear acceptance criteria, selects the next unblocked task for other agents, and validates completion vs requirements. Only Project-Manager defines/edits task entries; other agents must not create tasks.
A delivery-summary tool for completed user stories, smaller tasks, or bug fixes. It produces the summary in the conversation and as Markdown and HTML files.
A guided project-initialization skill that interviews the user about a project and fills its AGENTS.md and documentation placeholders. AGENTS.md is a handbook that tells coding agents how to work in a repository.
Use when the user wants one automated GitHub issue-solving pass against the current repository, wants to run the centralized issue solver, or wants to check whether the installed issue-solver skill is out of date.
Scaffold a new research project repository, then run the intake briefing to populate its direction. Use when Hugo starts a new research direction or asks to set up a project repo. Picks the host (Spartan or local), assembles and fills the orchestrator CLAUDE.md, seeds the docs files, sets up local git and pre-commit…
Use Zoe's local orchestration tools to plan engineering work, dispatch subtasks, inspect task or plan status, and list archived plans in the local ai-devops installation. Use this when the user asks Zoe to create or queue development work, check execution state, or inspect recent plans.
Use this when the user wants a summary of a milestone. This is a speed optimized skill that does not do any git actions, so it may be stale. Use /milestone-summary instead for a fresh report.
Scaffold a new BMad project hub interactively. Asks for project name, architecture preset, and repo names — then generates all session files, hub CLAUDE.md, and per-repo CLAUDE.md files. Adapts to the environment: direct file generation in Claude Code, guided text output elsewhere. Use when the user says "setup hub"…
A project-tracking system that connects multiple Git repositories to an Obsidian vault through Markdown notes and commands. It keeps architecture, progress, current focus, and recent changes in one place.
Foundational traceability layer for the entire Plan→Build→Verify→Review→Accept responsibility chain. Every role must leave a traceable record: upstream requirements → execution → output mapping → evidence → persisted record. Without traceability at every link, the chain cannot be audited, handoffs break, and sign-off…
Manage Userorbit resources via the public API. Create and manage feedback, roadmap views, announcements, help center articles, product tours, interactive demos, checklists, surveys, support inbox threads, workflows, subscribers, analytics, and more.
Use when a user wants to add, change, remove, or redesign a feature in an Autorunne-backed repo. Read Autorunne state first, identify the safe change boundary, ask only necessary questions, then implement and verify the smallest safe slice.
Linear integration with Linearis CLI - rules, team config, issue format, and all Linear operations (create, update, comment, list, triage, view, project create/plan). Use when creating or managing Linear issues, referencing issues in commits/PRs, or working with Linear projects.
Full TRD-to-GitHub-issues pipeline for any repo. Use this skill whenever the user invokes /vibe-engineering, mentions "vibe engineering", wants to implement a TRD, wants to break down a technical spec into tickets, or says anything like "bikin issues dari TRD ini", "breakdown TRD", or "buat github issues dari spec…
★not rated 2 1mo agoA119 tokens
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: