Updated 7mo ago
by mzbac
skills
codex skills
27 GitHub stars (27)
Steady at 27 stars — no new stars in the 16 days since Sep 30.
- 7 skills (7 skills found in its SKILL.md files)
- 1 forks (1 forks)
- 7mo ago last update (Last updated 7mo ago)
Install
Skills CLI
npx skills add mzbac/skills
Asks which skills and agents to install. Just one: npx skills add mzbac/skills --skill ask-questions-if-underspecified — add -g for every project.
Claude Code
git clone https://github.com/mzbac/skillscp -r "skills/skills/ask-questions-if-underspecified" ~/.claude/skills/
Copies the ask-questions-if-underspecified skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add mzbac/skills
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md.
-
ask-questions-if-underspecified
Clarify requirements before implementing. Do not use automatically, only when invoked explicitly.
skills/ask-questions-if-underspecified/SKILL.md on GitHub (opens in a new tab) -
code-review
Lightweight code review for diffs/PRs focusing on high-signal simplifications, code smells, security, performance, and whether new tests are needed; focus on recently modified code unless instructed otherwise.
skills/code-review-low/SKILL.md on GitHub (opens in a new tab) -
codex-exec-delegate
Delegate coding tasks to a nested Codex CLI run using `codex exec --yolo -m gpt-5.3-codex -c model_reasoning_effort=xhigh`. Use when you want the current Codex agent to act as an orchestrator (plan/review/verify) while a separate worker session performs edits and runs tests.
skills/codex-exec-delegate/SKILL.md on GitHub (opens in a new tab) -
design-cli
Design or review agent-friendly command-line interfaces for tools, wrappers, and internal platforms. Use when Codex needs to create a new CLI, simplify an existing one, map real workflows to commands and flags, improve `--help` and error behavior, define stdout/stderr and file output contracts, add safety rails for destructive actions, or turn an API/service/browser workflow into a shell-first in…
skills/design-cli/SKILL.md on GitHub (opens in a new tab) -
diagram-first
Diagram-first explanations using ASCII visualizations (sequence diagrams, flowcharts, component maps) to explain code, systems, request/response flows, pipelines, concurrency, and comparisons. Use when the user asks to "draw an ASCII diagram", "show the flow/logic", "visualize the architecture", "explain how it works", or when a diagram would reduce ambiguity in a technical explanation.
skills/diagram-first/SKILL.md on GitHub (opens in a new tab) -
planning-with-files
Transforms workflow to use Manus-style persistent markdown files for planning, progress tracking, and knowledge storage. Use when starting complex tasks, multi-step projects, research tasks, or when the user mentions planning, organizing work, tracking progress, or wants structured output.
skills/planning-with-files/SKILL.md on GitHub (opens in a new tab) -
posd-code-review
Review a codebase, directory, or PR diff using John Ousterhout’s “A Philosophy of Software Design” principles. Use when the user wants design/maintainability feedback: complexity (dependencies/obscurity), deep modules, information hiding/leakage, interface design (common case), layering, error-handling strategy, comments and naming/obviousness. Do NOT use for formatting-only or lint-only requests…
skills/posd-code-review/SKILL.md on GitHub (opens in a new tab)
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.