Full team execution with Lead/Worker/Reviewer agents running all Plans.md tasks end-to-end. Use when running the complete breezing flow with parallel workers.
EnglishHandles Cursor to Claude Code handoffs — PM plan validation, brainstorm review, and Plans.md sync. Use when bridging between Cursor and Claude Code sessions.
EnglishUse when reviewing PRs that modify the Feature Table in CLAUDE.md or docs/CLAUDE-feature-table.md (auto-triggered). Do NOT load for: standard PR reviews, implementation, or non-Feature-Table docs.
EnglishScaffolds CRUD endpoints, database models, and REST resources. Use when generating create/read/update/delete operations for an entity.
EnglishDistills a session's repeatable workflow into a new project skill in .claude/skills/. Use when a session solved a non-trivial, repeatable problem and the workflow is worth capturing for reuse.
EnglishUse when creating a single project slide or one-page visual summary — project intro image or promotional image for a repo. Do NOT load for: multi-slide decks, video generation, or text-only docs.
EnglishOperates Google Drive, Docs, Sheets, and Slides via gogcli. Use when listing, searching, reading, or updating Google Workspace files.
EnglishRuns interactive brainstorming to capture intent and produce a design spec, then hands off to harness-plan to generate Plans.md. Use when a rough idea needs both shaping and a concrete task list.
EnglishSuggests strategic /compact checkpoints to preserve context across phase transitions. Use when deciding when to compact, checking session tool-call stats, or resetting the compact counter.
EnglishLong-running task harness for multi-session campaigns with compact machine-owned state, immutable feature contracts, and risk-gated review. Use when user says 'start a campaign', 'continue the campaign', 'track features', 'long-running task', or invokes /harness-plan.
EnglishIterates a fresh ralph-worker subagent per attempt in a persistent worktree until tag and verify command both confirm success. Use when running [ralph]-marked tasks or iterate-until-pass loops.
EnglishManages version bumps, CHANGELOG, git tags, and GitHub Releases. Use when cutting a release or updating version metadata.
EnglishManages SSOT memory — decisions.md, patterns.md, and cross-session learnings. Use when recording decisions, searching memory, or promoting learnings.
EnglishRuns Plans.md tasks in a long-running autonomous loop with ScheduleWakeup, sprint contracts, and plateau detection. Use when running tasks overnight or on a scheduled cadence.
EnglishExecutes Plans.md tasks — solo, parallel, or breezing team mode. Use when implementing tasks or running the work loop.
EnglishCreates NotebookLM YAML and structured slide content from project docs. Use when converting documentation into NotebookLM or slide format.
EnglishAnalyzes upstream fork PR changes and ports selected items into the local branch. Use when checking upstream PRs, porting upstream changes, or planning selective upstream integration.
EnglishOrchestrates the full powerball-harness plugin release with build, validation, and version checks. Use when releasing this plugin.
EnglishInternal skill for --resume and --fork workflow boundaries in harness-work. Auto-triggered by orchestration.
EnglishGuides VibeCoder (non-technical users) through natural language development. Use when user asks what to do next, how to use the system, needs help, or is stuck. Do NOT load for: technical-user work, direct implementation requests, or reviews.
EnglishWrites and updates CHANGELOG.md with Unreleased entries or versioned sections. Use when adding CHANGELOG entries or writing GitHub Release notes.
EnglishUse when generating, vectorizing, or converting images to SVG — logos, icons, illustrations, or 'allow1'/'quiver' references.
Uncertain
AGENT SKILLS ATLASIncludes Cc Cursor Cc, Cc Update Review, Distill Session, and other workflows.
Claude Code
Codex
Cursor
GitHub Copilot
Gemini CLISupported by the Atlas install prompt. Skill-specific requirements vary.
Pack stats
What’s included
Breezing
Full team execution with Lead/Worker/Reviewer agents running all Plans.md tasks end-to-end. Use when running the complete breezing flow with parallel workers.
Cc Cursor Cc
Handles Cursor to Claude Code handoffs — PM plan validation, brainstorm review, and Plans.md sync. Use when bridging between Cursor and Claude Code sessions.
Cc Update Review
Use when reviewing PRs that modify the Feature Table in CLAUDE.md or docs/CLAUDE-feature-table.md (auto-triggered). Do NOT load for: standard PR reviews, implementation, or non-Feature-Table docs.
Crud
Scaffolds CRUD endpoints, database models, and REST resources. Use when generating create/read/update/delete operations for an entity.
Distill Session
Distills a session's repeatable workflow into a new project skill in .claude/skills/. Use when a session solved a non-trivial, repeatable problem and the workflow is worth capturing for reuse.
Generate Slide
Use when creating a single project slide or one-page visual summary — project intro image or promotional image for a repo. Do NOT load for: multi-slide decks, video generation, or text-only docs.
Gogcli Ops
Operates Google Drive, Docs, Sheets, and Slides via gogcli. Use when listing, searching, reading, or updating Google Workspace files.
Harness Brainstorming
Runs interactive brainstorming to capture intent and produce a design spec, then hands off to harness-plan to generate Plans.md. Use when a rough idea needs both shaping and a concrete task list.
Harness Compact
Suggests strategic /compact checkpoints to preserve context across phase transitions. Use when deciding when to compact, checking session tool-call stats, or resetting the compact counter.
Harness Plan
Long-running task harness for multi-session campaigns with compact machine-owned state, immutable feature contracts, and risk-gated review. Use when user says 'start a campaign', 'continue the campaign', 'track features', 'long-running task', or invokes /harness-plan.
Harness Ralph Loop
Iterates a fresh ralph-worker subagent per attempt in a persistent worktree until tag and verify command both confirm success. Use when running [ralph]-marked tasks or iterate-until-pass loops.
Harness Release
Manages version bumps, CHANGELOG, git tags, and GitHub Releases. Use when cutting a release or updating version metadata.
Harness Remember
Manages SSOT memory — decisions.md, patterns.md, and cross-session learnings. Use when recording decisions, searching memory, or promoting learnings.
Harness Schedule Run
Runs Plans.md tasks in a long-running autonomous loop with ScheduleWakeup, sprint contracts, and plateau detection. Use when running tasks overnight or on a scheduled cadence.
Harness Work
Executes Plans.md tasks — solo, parallel, or breezing team mode. Use when implementing tasks or running the work loop.
Notebook Lm
Creates NotebookLM YAML and structured slide content from project docs. Use when converting documentation into NotebookLM or slide format.
Port Upstream
Analyzes upstream fork PR changes and ports selected items into the local branch. Use when checking upstream PRs, porting upstream changes, or planning selective upstream integration.
Release This
Orchestrates the full powerball-harness plugin release with build, validation, and version checks. Use when releasing this plugin.
Session Control
Internal skill for --resume and --fork workflow boundaries in harness-work. Auto-triggered by orchestration.
Vibecoder Guide
Guides VibeCoder (non-technical users) through natural language development. Use when user asks what to do next, how to use the system, needs help, or is stuck. Do NOT load for: technical-user work, direct implementation requests, or reviews.
Writing Changelog
Writes and updates CHANGELOG.md with Unreleased entries or versioned sections. Use when adding CHANGELOG entries or writing GitHub Release notes.
Allow1
Use when generating, vectorizing, or converting images to SVG — logos, icons, illustrations, or 'allow1'/'quiver' references.
Quick start
- Choose your skills. Select individual skills above, or choose the entire pack.
- Copy the install prompt. Use Copy install prompt above the list.
- Send it to your agent. Paste into your coding agent’s chat. Your agent reviews the source and guides the setup.
Try it with your agent
After installation, start with a request like:
Use the Breezing skill to help with my task.
Ask me for the context you need before getting started.Requirements & license
- A coding agent that can access your project files and install skills.
- Your agent checks each skill’s instructions, dependencies, and permissions during setup.
- Reported license for the skills shown: MIT. The author’s terms apply.