MCP App StoreMCP App StoreDelegates coding tasks to a Codex CLI wrapper script that executes changes, captures output, and returns session results. This skill defines invocation rules, error handling, and recommended prompt patterns so an agent can hand off implementation work to Codex safely and effectively.
Use this skill only when the user explicitly requests Codex (phrases like "use codex", "ask codex to..."). It's intended for concrete coding tasks: refactors, bug fixes, and automated edits where Codex will run scripts against a repo workspace and produce patch-like output. Do not call it for generic coding advice.
ask_codex.sh / ask_codex.ps1) that handle session tracking and output capture. (has_scripts: false in repo metadata — check repo for script paths.)Best used with agents that can run shell scripts and read workspace files (Claude Code, Codex-capable agents, CLI-backed subagents).
Codex skill delegates coding tasks to OpenAI's Codex CLI via non-interactive `codex exec`. Well-documented with clear sandbox mode guidance and model tables. No bundled scripts to test. Minor security note: `danger-full-access` sandbox mode is documented but gated behind user confirmation, and `--full-auto` with `workspace-write` is appropriately cautioned. Shell injection risk is low since prompts are positional args, but unquoted prompt strings could be a concern in edge cases.
Attribution to original author is good. Bilingual trigger support mentioned but not demonstrated. Model pricing table adds practical value. No scripts bundled — purely a SKILL.md instruction skill.
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.