MCP App StoreMCP App StoreITP Setup is an interactive preflight skill that detects the host platform and checks for required developer tooling (uv, gh, prettier, ruff, semgrep, gitleaks, node, semantic-release, etc.). It guides the agent through a TodoWrite-driven workflow: detect platform, run checks, present findings, pause for a gate decision, and optionally install missing tools and verify installation. The skill embeds explicit templates and commands to ensure safe, repeatable setup flows.
Use this skill before running ITP workflows or any automation that depends on a consistent developer toolchain. It's appropriate when onboarding a new machine, preparing CI runners, or ensuring local dev environments match project expectations. It also supports a non-interactive --install mode for automated provisioning.
Designed for Claude Code / Claude Code Skills environment and similar agent platforms that support TodoWrite, AskUserQuestion, and Bash actions. The skill assumes an agent runtime that can run shell commands and prompt the user for the interactive gate.
ITP Setup is an interactive preflight/installer skill for Claude Code developer tooling. It detects platform, checks core/devops tools, and optionally installs missing ones via mise or brew. No bundled scripts were present to test. The SKILL.md is well-structured with clear phases, TodoWrite-driven workflow, and good edge case handling. Security deductions for unquoted shell variable PLUGIN_DIR in heredocs and sourcing scripts from a path derived from env vars without verification.
Well-documented skill with clear progressive workflow. The self-evolving skill pattern (post-execution reflection to edit SKILL.md) is interesting but creates a mutable-skill attack surface. Shell variable PLUGIN_DIR sourced without validation is the main security concern. No hardcoded credentials or destructive commands. The --install/--yes flag skips user confirmation gate which is a minor concern but documented.
Alpha Forge Pre-Ship Quality Gates
Pre-merge quality gates for PRs that validate RNG determinism, forked URLs, runtime parameter ranges, and manifest synchronization to reduce review cycles.
Kokoro TTS Server Management
Start, stop, and verify a local Kokoro TTS HTTP server (OpenAI-compatible /v1/audio/speech) with health checks and troubleshooting guidance.
Telemetry Terminology Similarity
Compute multi-layer similarity scores for telemetry/log field names (syntactic, taxonomic, semantic) to surface naming collisions and standardization candidates
Explore (incomplete)
SKILL.md appears empty or missing — this skill looks incomplete or a template; flagged as failed to avoid saving low-quality record.
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.
