⏳ This skill is pending AI review.

Scores will appear once the review pipeline completes.

v3.1.0

audit

jhostalek@jhostalek⭐ 11 stars· last commit 24d ago· 0 open issues

Run an explicitly selected code or UX audit, or a full fourteen-dimension sweep.

Choose how to use this skill

You do not need every option. Choose the path your AI client supports. The stable page stays the same; versioned files are immutable.

1. Native installer

This listing has no registered native installer command. Use the complete package or source fallback below, depending on what your client supports.

Do not guess an installer command or replace an existing version without reviewing the diff.

2. Complete package recommended

Download the ZIP when available. It includes SKILL.md plus the references, security notes and version metadata.

No complete ProSkills package is published for this listing yet.

3. Prompt-only

Copy the prompt above when the agent can read the stable page or when you want to adopt the workflow without installing a skill.

Need only the instruction file?

Download SKILL.md only if your client requires a single file. The complete ZIP is safer for a full installation because it preserves the references and release context.

No path installs or executes anything by itself. Your agent still needs access to the project files. Before updating, compare the installed version and review the diff.

—/10

// RATINGS

⭐GitHub Stars
⭐⭐ 11 on GitHubGitHub ↗

Growing

🟢ProSkills Score
—
📍

Not yet listed on ClawHub or SkillsMP

// README

dotclaude

skills for agentic coding tools. extremely opinionated. updated (almost) daily.

heads up: this is a global ~/.claude configuration repo — skills that apply across all projects. project-specific instructions (CLAUDE.md, TOOLS.md, skills) live in individual repositories.

build

start here. intent-brief clarifies intent, sota finds a current expert recommendation, and design explores alternatives.

skill
intent-briefevidence-first intent brief with questions reserved for hard-to-reverse decisions
sotacurrent expert recommendation grounded in brief web research
designdivergent exploration with independent reasoning agents

quality

before you ship. review what you built, refactor what's messy, audit what's bloated or stale.

skill
judgeindependent expert review before accepting work
auditindependent reviews through focused audit dimensions
writingrewrite AI slop into text a person would write
distillcompress rough text into expert-register English
query-refinerrewrite a rough question into a precise expert query

use /audit <dimension> [path] for a focused review, /audit full for all code dimensions, or /audit ux for usability. each dimension gets one independent reviewer of the whole scope. audits are read-only; scope defaults to changed files.

ship

git workflow from branch to PR to merge.

skill
git-workflowcommit, PR, merge, and rebase conventions
timesheetmonthly timesheet entries from git

when they run

in Claude and Codex, git-workflow and query-refiner load automatically when relevant. all other skills require explicit invocation.

use /name for standalone skills in Claude, or select the skill with $ in Codex.

Use /writing or $writing to rewrite the last agent response. Add text, a file, or feedback to choose a different target or explain what should change.

install

Codex plugin

Add the marketplace and install the plugin:

codex plugin marketplace add JHostalek/dotclaude
codex plugin add jhostalek-skills@jhostalek

Claude Code plugin

Add the marketplace and install the plugin:

/plugin marketplace add JHostalek/dotclaude
/plugin install jhostalek-skills@jhostalek

Skills are versioned with the plugin and invoked as /jhostalek-skills:<skill-name>. The plugin contains skills only.

Pi package

Install directly from Git:

pi install git:github.com/JHostalek/dotclaude

Invoke skills as /skill:<skill-name>. Use pi update --extensions to update the package.

releases

Claude Code, Codex, and Pi share one semantic version. Releases use annotated vMAJOR.MINOR.PATCH tags and are recorded in CHANGELOG.md. See RELEASING.md for the release procedure.

Editable standalone skills

Symlink the skills you use from the source checkout:

git clone [email protected]:JHostalek/dotclaude.git ~/dotclaude
mkdir -p ~/.claude/skills
ln -s ~/dotclaude/skills/git-workflow ~/.claude/skills/git-workflow

For Codex, use ~/.codex/skills as the link destination.

contributing

this project is owned and maintained by me alone. issues and pull requests are not accepted.

license

CC0 1.0 — public domain.

// HOW IT'S BUILT

// FILES

2 files shipped with this skill. Inline text is the catalog copy. The upstream link is the source repository.

  • skills/audit/SKILL.md580 Bupstream ↗
    ---
    name: audit
    description: Run an explicitly selected code or UX audit, or a full fourteen-dimension sweep.
    argument-hint: "[full|dimension...] [path] [review only]"
    disable-model-invocation: true
    ---
    
    Audit `$ARGUMENTS` using [the shared workflow](references/workflow.md). It defines scope, lens selection, evidence, corrections, and completion. Read only the selected lenses; read [integration](references/integration.md) for multiple dimensions.
    
    Examples: `/audit security src/auth`, `/audit correctness contracts src/api review only`, `/audit ux /settings`, `/audit full`.
    
  • README.mdupstream ↗

    Contents are not inlined in the catalog. Open the upstream file.

Plain-text copy, no login: /skill-bundles/jhostalek-dotclaude-skills-audit.md

// REPO STATS

11 stars
0 open issues
Last commit: 24d ago