MCP App StoreMCP App StoreRuns an on-demand validation of a project's hierarchical plan tree using a thin wrapper around an existing validation script. It enforces eight invariants (parent existence, children integrity, no orphans, valid status values, monotonic revisions, test_ref existence, DAG no-cycles, and freeze_reason requirements) and surfaces specific failing conditions.
Invoke before plan-modifying operations (/aura-frog:plan-expand, /aura-frog:plan-promote, /aura-frog:plan-archive) and as part of pre-commit hooks when .claude/plans/ contains changes. Avoid running on read-only commands or during undo flows where transient violations are expected.
aura-frog/scripts/plans/validate-plan-tree.sh as the canonical implementation (the skill is a thin wrapper).docs/architecture/HIERARCHICAL_PLANNING.md and getting-started guides.Inference: Built for code-oriented agent harnesses (Claude Code, Codex-style agents) and CI hooks that can run shell scripts and inspect exit codes.
Plan Tree Validator is a thin SKILL.md wrapper around an external bash script (validate-plan-tree.sh). No bundled scripts to execute. The SKILL.md itself is well-structured: clear behavior steps, an 8-invariant table, explicit when-to-invoke/not-invoke guidance, and output discipline. However, it's tightly coupled to the aura-frog ecosystem and won't function without the companion script and .claude/plans/ directory structure.
Pure SKILL.md — no scripts bundled, no executable content. Entirely safe. Niche utility limited to aura-frog users. Well-documented for what it is.
Flutter Expert
Expert Flutter/Dart patterns and best practices for building maintainable cross-platform mobile apps (state management, navigation, testing).
Documentation (ADR & Runbook)
Generates and templates operational documentation: Architecture Decision Records (ADRs) and runbooks, with templates and principles for when and how to record d
Quick Bugfix
A compact TDD-driven bugfix workflow that enforces root-cause investigation, failing-test-first discipline, and stepwise verification to prevent regressions.
Development Worktree
Create an isolated git worktree for feature work, auto-run project setup, and verify a clean test baseline before development.
Readwise Reader Document Management
Manage Readwise Reader documents: list, save, search, move, tag, highlight, export and bulk-edit via official and custom CLIs.
Bounty Hunter — Atlas
Persona skill: 'Atlas' — a profit-focused developer persona for discovering, evaluating and executing paid bounties or freelance tasks with ROI-aware workflows.
Junshi — Research Advisor
Daily strategic research advisor that scans arXiv/venues, digests papers, and proposes bold, ranked research ideas tailored to the user's profile.
Full Stack Builder
End-to-end builder that scaffolds, implements, tests, and optionally deploys web and API applications from a natural-language specification.
ezBookkeeping API Tools
Command-line API tools for ezBookkeeping: record and query transactions, retrieve accounts/categories/tags, and fetch exchange rates for self-hosted personal fi
Feishu Voice Sender
Convert MP3s and send them as native Feishu voice messages (playable voice clips) to users or groups.
Claw Bench
Benchmarking skill that guides an agent through a structured suite of capability tests and reporting steps for leaderboard submission.