By geemus
Reusable agent skills for Claude Code — commit safety, plan generation, PR review, prose refinement, and more.
Produces a complete health report on a skill library: per-skill structural validation followed by cross-skill analysis covering trigger conflicts, redundancy, workflow coverage gaps, and composition chains. Auto-fixes unambiguous minor structural issues (whitespace, missing optional metadata) and formats all other findings with format-review-comments. TRIGGER when: user asks to audit skills, check skill coverage, validate all skills, find gaps in skills, check for trigger conflicts, or health-check the skill library. DO NOT TRIGGER when: user asks to create, update, rename, or delete a skill (use upsert-skill instead); or to evaluate a single skill for quality (use review-skill instead).
Stages changes safely, generates a conventional-commit message from the diff, and blocks secrets or debug artifacts from being committed. TRIGGER when: user asks to commit, save changes, stage files, write a commit message, run git commit, check in my changes, or commit my work. DO NOT TRIGGER when: user asks to push, open a PR, or create a branch.
Formats code review and PR feedback using the Conventional Comments standard (label [decorations]: subject). Apply proactively whenever posting review comments or any critique of code or pull requests. Invoke directly when the user asks to format feedback, use conventional comments style, or label a review comment as blocking, suggestion, or nitpick.
Reads a structured plan from a GitHub issue and orchestrates the full delivery workflow: parses unchecked tasks in dependency order, steps through them one at a time, commits via create-commit, reviews via review-pr, and opens a PR linked back to the plan issue. Use when the user says "implement #N", "implement this plan", "execute plan #N", "work through issue #N", "implement the plan in #N", or "carry out the tasks in #N". TRIGGER when: user wants to execute or implement a plan stored as a GitHub issue. DO NOT TRIGGER when: user wants to create or update a plan (use upsert-plan instead).
Polishes drafted prose for clarity, conciseness, and consistent voice before it is posted or presented. Apply after drafting any plan, review summary, or written output to catch filler phrases, passive constructions, and inconsistent terminology. Use when the user asks to polish, clean up, improve, edit, or tighten writing — also triggered by "refine this draft", "make this clearer", or "improve my writing". Also composable: other skills invoke it as a late-stage refinement step. TRIGGER when: user asks to polish, edit, or improve prose. DO NOT TRIGGER when: user asks to format or lint code (use language-specific tools instead), or when this skill is already running as a composable step within another skill.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Reusable agent skills for Claude Code and other AI coding agents. Follows the agentskills.io open standard and ships a native Claude Code plugin manifest for one-command installation.
| Skill | Trigger | Purpose |
|---|---|---|
audit-skills | /hax-yax:audit-skills | Produce a full health report on the skill library: structural validation per skill and cross-skill analysis covering trigger conflicts, redundancy, workflow gaps, and composition chains |
create-commit | /hax-yax:commit | Stage changes safely, generate a conventional-commit message, and block secrets from being committed |
format-review-comments | applied proactively during code review | Format review and feedback comments using the Conventional Comments standard |
implement-plan | /hax-yax:implement-plan | Fetch a structured plan from a GitHub issue and orchestrate the full delivery workflow: step through unchecked tasks in dependency order, commit, review, validate, and open a PR |
refine-prose | /hax-yax:refine-prose | Polish drafted prose for clarity, conciseness, and consistent voice before presenting or posting |
review-agents-md | /hax-yax:review-agents-md | Audit AGENTS.md and equivalent agent instruction files for completeness, accuracy, agent-friendliness, freshness, scope coherence, and leanness |
review-plan | /hax-yax:review-plan | Evaluate a structured work plan across six quality dimensions: objective clarity, task actionability, dependency correctness, acceptance criteria completeness, scope appropriateness, and structural completeness |
review-pr | /hax-yax:review-pr | Conduct a systematic PR review across logic, security, performance, test coverage, and documentation |
review-skill | /hax-yax:review-skill | Evaluate a skill for effectiveness across instruction clarity, trigger discoverability, example completeness, composability, and scope coherence |
upsert-agents-md | /hax-yax:upsert-agents-md | Create or update AGENTS.md and equivalent agent instruction files by surveying the repository |
upsert-plan | /hax-yax:upsert-plan | Create and update structured work plans as GitHub issues |
upsert-skill | /hax-yax:upsert-skill | Manage the lifecycle of reusable agent skills stored under .agents/skills/ |
Install from a local clone using --plugin-dir:
git clone https://github.com/geemus/hax-yax
claude --plugin-dir ./hax-yax
Or install directly from the repository URL once Claude Code supports remote plugin installation:
claude plugin install https://github.com/geemus/hax-yax
Skills are registered under the hax-yax namespace (e.g. /hax-yax:upsert-plan). Run /help inside Claude Code to see all available commands.
If you already have the repository checked out and want skills available without the plugin namespace, the .claude/skills symlink points to .agents/skills/ for direct discovery by Claude Code:
# From within the repository, skills load automatically.
# From another project, symlink or copy the skills directory:
ln -s /path/to/hax-yax/.agents/skills .claude/skills
├── AGENTS.md # Agent guidance (agents.md standard)
├── CHANGELOG.md # Version history
├── LICENSE
├── README.md # This file
├── .claude/
│ └── skills -> ../.agents/skills # Symlink for standalone Claude Code use
├── .claude-plugin/
│ └── plugin.json # Claude Code plugin manifest
└── .agents/
└── skills/
└── <skill-name>/ # One directory per skill
├── SKILL.md # Required: YAML frontmatter + instructions
├── scripts/ # Optional: executable scripts
├── references/ # Optional: reference materials
└── assets/ # Optional: templates and examples
Skills follow the format defined in .agents/skills/upsert-skill/references/skill-format.md. Use the upsert-skill skill (/hax-yax:upsert-skill) to create or update skills with guided steps and validation.
Commits follow Conventional Commits: <type>[scope]: <description>.
MIT — see LICENSE.
npx claudepluginhub geemus/plugins --plugin hax-yaxCoding workflow skills: intelligent commits, push & PR, branch cleanup, CLAUDE.md maintenance, README generation, changelog creation, README updating, and GitHub Actions setup
PR review, interactive git diff annotation review, and writing style guide
Software engineering discipline: output styles, coding fundamentals, and universal development practices
Editorial "Essentials" bundle for Claude Code from Antigravity Awesome Skills.
Plugin-safe Claude Code distribution of Antigravity Awesome Skills with 1,561 supported skills.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques