ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified

agent-portability-checker

Audit agent skills for platform lock-in and cross-agent compatibility. Use when checking if a skill is portable, making a skill work across multiple agents (OpenClaw, Claude Code, Codex, etc.), fixing hardcoded paths, or preparing a skill for multi-platform distribution. Checks for hardcoded platform paths, missing env var support, and platform-specific dependencies.

skill-install ā€” Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/99rebels/agent-portability-checker
Or

Agent Portability Checker šŸ”Œ

Audit an agent skill for platform lock-in. Auto-fixes what it can, flags what needs manual attention.

Why

Skills with hardcoded paths only work on one platform. This tool catches those issues and fixes them ā€” making your skills work everywhere agents run.

When to Use

  • "Is this skill portable?"
  • "Make this skill cross-platform"
  • "Check for hardcoded paths"
  • "Prepare a skill for other agents"

How to Run

python3 scripts/audit.py <skill_dir>          # audit only
python3 scripts/audit.py <skill_dir> --fix    # auto-fix + audit
python3 scripts/audit.py <skill_dir> --json   # structured output

What It Checks

šŸ“ Hardcoded paths     ā€” platform-specific dirs like ~/.<platform>/ in scripts
šŸ”§ SKILL_DATA_DIR      ā€” env var support for data dir resolution
šŸ“¦ XDG fallback        ā€” ~/.config/<skill>/ fallback path
šŸ”Œ Platform CLI deps    ā€” external binary dependencies (e.g. clawhub, gh)
šŸ·ļø  User-Agent strings ā€” platform names in HTTP headers
šŸ“„ SKILL.md paths      ā€” platform-specific path references in docs
šŸ–„ļø  Headless setup     ā€” OAuth scripts without --no-browser flag
šŸ”‘ Credential env vars ā€” file-only credentials with no env var alternative

Output Example

āŒ github-growth-tracker ā€” 8 errors, 9 warnings (9 auto-fixable)

šŸ“ Hardcoded Paths
  āŒ scripts/github_tracker.py:28: ~/.<platform>/ [auto-fix]
  āŒ scripts/github_tracker.py:31: ~/.<platform>/ [auto-fix]

šŸ”§ SKILL_DATA_DIR: Not supported ā€” scripts use hardcoded paths
šŸ”§ XDG Fallback: Missing ~/.config/ fallback path

Two-Phase Flow

  1. Audit ā€” show all findings (auto-fixable + manual)
  2. Fix ā€” apply auto-fixes, show brief "what changed" confirmation

The agent reads the script output and formats it for the current channel. See references/formatting.md for Slack/WhatsApp/Discord styling.

Auto-Fixes

  • Replaces ~/.<platform>/credentials/ with $SKILL_DATA_DIR
  • Replaces ~/.<platform>/workspace/data/<skill>/ with $SKILL_DATA_DIR/<skill>/
  • Strips platform names from User-Agent strings
  • Replaces hardcoded paths in SKILL.md with <DATA_DIR> placeholder

āš  Output styling is never modified. Emojis, formatting, and visual elements in script output are preserved exactly as-is.

Manual flags require human review (platform CLI deps, headless setup, env var alternatives).

Formatting

Read references/formatting.md for channel-specific styling (Slack, WhatsApp, Discord, terminal).

The Portability Pattern

Skills that work everywhere follow this:

1. Resolve data dir via $SKILL_DATA_DIR (set by agent platform)
2. Fall back to ~/.config/<skill>/ (XDG-compliant, works everywhere)
3. Accept credentials via env var OR file (env var preferred)
4. Output to stdout ā€” no platform messaging APIs
5. Self-contained scripts ā€” no platform SDK imports
Read Full Documentation on GitHub

Metadata

Author@99rebels
Stars4473
Views0
Updated2026-05-01
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build ā€” we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-99rebels-agent-portability-checker": {
      "enabled": true,
      "auto_update": true
    }
  }
}
Safety NoteClawKit audits metadata but not runtime behavior. Use with caution.

Related Skills

github-growth-tracker

Track GitHub repo growth (stars, forks, issues, commits) with periodic digests and trend analysis. Compare your repos against a watchlist. Use when checking repo stats, monitoring growth, setting up a github digest, comparing repos, or managing a repo watchlist. Requires GITHUB_TOKEN environment variable or GitHub PAT (see Credentials).

99rebels 4473

gmail-checker

Check Gmail for unread inbox emails, filtered by priority. Use when asked to check emails, check inbox, email digest, email summary, or "any new mail". Outputs a brief list sorted by priority (HIGH/MEDIUM/LOW). Skips marketing, promotions, social, and update categories. Configurable via gmail-config.json.

99rebels 4473

invoice-extractor

Extract structured data from invoices and receipts (PDFs and images). Output JSON, CSV, or build a running expense ledger. Use when someone shares an invoice to process, asks to track expenses, categorize spending, or prepare tax documents.

99rebels 4473

skill-polisher

Polish a skill's SKILL.md for ClawHub readability without sacrificing LLM effectiveness. Use when improving a skill's listing, making a skill look better on ClawHub, or preparing a skill for publish. Rewrites SKILL.md with better formatting, then audits the changes to ensure nothing the LLM needs was lost. Moved content goes to references/ ā€” never deleted.

99rebels 4190