maggy — Claude Code skill: what it does, how to install
maggy is a Claude Code skill that brings GitHub Issues and Asana tickets into one inbox, starts a TDD run from a ticket, and prepares a daily competitor briefing.
MIT 131 installs ★ 713 updated 2026-10-13
npx skills add alinaqi/maggy --skill maggy -a claude-codeWhat maggy does
Maggy runs a dashboard on your machine. It pulls open tickets from GitHub Issues and Asana, ranks them by urgency and age, and starts a TDD run in the right repo when you press Execute. The services sit behind an IssueTrackerProvider protocol, so swapping a tracker does not touch inbox or executor code. Linear is a stub.
Execute asks the configured iCPG for symbols and blast radius, picks a working directory from ticket keywords, then calls claude -p --dangerously-skip-permissions: analyze, write failing tests, implement. That flag gives the agent write and shell access inside the target repo, and the prompt carries ticket text written by anyone on the team. The directory is checked against codebase roots in ~/.maggy/config.yaml, so the agent stays off arbitrary paths.
You need GITHUB_TOKEN, ANTHROPIC_API_KEY and Python. The dashboard goes up with ./install.sh then python3 -m src.main; setup runs through /maggy-init or a hand-edited config. The competitor feed refreshes once a day from RSS blogs and Google News for the categories you list.
What it helps with
- triage a morning pile of open tickets
- kick off a TDD cycle from a ticket
- route a ticket to the right repo out of several
- get a daily read on competitor releases
- plug in a different tracker without touching services
Example prompts for the agent
- Run
/maggy-initand connect GitHub Issues plus two repos - Open
/maggyand show the top tickets in the inbox - Execute the top ticket and open its session in Sessions
How to install maggy
1Skills CLI (Vercel)
npx skills add alinaqi/maggy --skill maggy -a claude-code2Manually: put the files in place
~/.claude/skills/maggy/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/maggy/
1Skills CLI (Vercel)
npx skills add alinaqi/maggy --skill maggy -a codex2Manually: put the files in place
.agents/skills/maggy/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add alinaqi/maggy --skill maggy -a cursor2Manually: put the files in place
.cursor/skills/maggy/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install alinaqi/maggy skills/maggy2Manually: put the files in place
.github/skills/maggy/SKILL.md1Skills CLI (Vercel)
npx skills add alinaqi/maggy --skill maggy -a gemini-cli2Platform CLI
gemini skills install https://github.com/alinaqi/maggy --path skills/maggyManually: put the files in place
.devin/skills/maggy/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add alinaqi/maggy --skill maggy -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about maggy
How do I install maggy in Claude Code?
Run npx skills add alinaqi/maggy --skill maggy -a claude-code. The skill lands at ~/.claude/skills/maggy/SKILL.md.
What does maggy do?
It merges open tickets from your trackers into one ranked inbox and spawns Claude Code against the matching repo on Execute. A competitor briefing is generated daily.
What do I need before launching the dashboard?
GITHUB_TOKEN, ANTHROPIC_API_KEY, Python, and ~/.maggy/config.yaml with your codebase roots. Then ./install.sh and python3 -m src.main.
Source text
SKILL.md · MIT
--- name: maggy description: Maggy is a local AI engineering command center. AI-prioritized inbox across issue trackers (GitHub Issues/Asana), one-click TDD execute with iCPG context enrichment, daily competitor intelligence briefing. when-to-use: "When you want a persistent dashboard to triage tickets and spawn Claude Code runs against any repo" user-invocable: true effort: medium --- # Maggy Skill **Maggy** is a generic, local AI engineering command center. Install once, point it at your team's issue tracker and codebases, and get: - **AI-prioritized inbox** — ranks open issues by urgency, OKR alignment, and recency - **One-click Execute** — spawns Claude Code locally with iCPG context injected - **Competitor intelligence** — daily AI briefing on your competitive landscape - **No hardcoding** — works for any team, any stack, any issue tracker ### ⚠️ Execute permission model (important) Execute currently runs `claude -p --dangerously-skip-permissions` so the TDD pipeline isn't blocked waiting on approval prompts (subprocess has no terminal). That flag **grants Claude full permission to write/edit files and run shell commands** inside the target codebase, and the prompt it receives includes content from the issue tracker (which any team member can author). **Hardening already in place:** - `working_dir` is validated against the list of codebase roots in `~/.maggy/config.yaml` — Claude can't be pointed at arbitrary filesystem paths. - Only tickets from your configured trackers reach Execute; no public-internet input flows into the prompt. **Roadmap:** move the unconditional flag behind per-codebase config (`auto_approve: true|false`) so privileged execution becomes opt-in. Until then, treat Execute like `git pull && make` on any ticket you push the button for — only run it on repos you own, against tickets from authors you trust. ``` ┌──────────────────────────────────────────────────────────────┐ │ maggy ──────────────┐ │ │ ├── skills/ ← installed globally → ~/.claude/ │ │ ├── commands/ ← installed globally → ~/.claude/ │ │ ├── scripts/icpg/ ← used by Maggy for context enrichment │ │ └── maggy/ ← dashboard: run `./install.sh` to use │ │ ├── src/ │ │ │ ├── providers/ ← GitHub / Asana / Linear │ │ │ ├── services/ ← inbox, competitor, executor │ │ │ └── api/ ← FastAPI routes │ │ └── install.sh │ └──────────────────────────────────────────────────────────────┘ ``` --- ## When Maggy Helps | Scenario | How Maggy helps | |------------------------------------------|-----------------------------------------------| | Morning triage of 50 open issues | AI ranks them; top items stay top | | Implementing a ticket | `Execute` → iCPG-enriched TDD pipeline | | "What are competitors shipping?" | Daily briefing + filterable news feed | | Multiple repos per team | Auto-picks right repo based on ticket content | | New team onboarding | Configure via `/maggy-init`, no code writing | --- ## Install and Configure ```bash # One-time install cd $(cat ~/.claude/.bootstrap-dir)/maggy ./install.sh # Configure # Edit ~/.maggy/config.yaml — see maggy/config.example.yaml for the schema # Credentials export GITHUB_TOKEN=ghp_... export ANTHROPIC_API_KEY=sk-ant-... # Run python3 -m src.main # Or from Claude Code: # /maggy-init # interactive wizard # /maggy # launch dashboard ``` --- ## Provider Abstraction Maggy services never see GitHub/Asana directly — they talk to an `IssueTrackerProvider` Protocol. Drop-in swap between: - `GitHubIssuesProvider` — scans multiple repos, aggregates open issues, maps "done" → closed - `AsanaProvider` — queries projects, respects workspace scope - `LinearProvider` — stub for future The same inbox, Execute pipeline, and Competitor features work with any provider. --- ## Execute Pipeline When you click Execute on a ticket: 1. Maggy queries the configured iCPG for relevant symbols, blast radius, and prior intents 2. Picks the right working directory based on ticket keywords + configured codebases 3. Spawns `claude -p --dangerously-skip-permissions` in that directory 4. Runs analyze → write failing tests → implement 5. Captures output in a session you can follow in the Sessions tab Because the spawned Claude Code runs in the target repo, it picks up: - That repo's `CLAUDE.md` - Your global `~/.claude/CLAUDE.md` - All bootstrap skills - `.claude/hooks/`, `.mcp.json` So Execute gets the full bootstrap experience — not a stripped-down version. --- ## Competitor Intelligence Generic — works for any domain: 1. Configure `competitors.categories: ["fintech", "embedded-finance"]` in `~/.maggy/config.yaml` 2. Click Discover — Claude identifies 12-18 competitors (market leaders, AI-first challengers, vertical specialists) 3. Maggy monitors their RSS blogs + Google News daily 4. Daily briefing is generated once per day (cached), regeneratable on demand --- ## Not Included Maggy MVP is focused. Not shipped: - Meeting bot (voice) - Slack integration - P2P network + session handoff - Self-improvement (`/improve-maggy`) - Linear provider (stub only) These are v2 work. --- ## Files - `maggy/PLAN.md` — architecture rationale - `maggy/README.md` — user docs - `maggy/src/providers/base.py` — IssueTrackerProvider Protocol - `maggy/src/services/executor.py` — TDD pipeline - `maggy/src/services/competitor.py` — discovery + briefing - `maggy/src/services/inbox.py` — AI prioritization - `commands/maggy.md` — `/maggy` launcher - `commands/maggy-init.md` — `/maggy-init` setup wizard
© alinaqi · MIT · alinaqi/maggy