Skip to main content
hc
Submit
skillsSource-backedReview first Safety ✓ Privacy ✓

Agent Skills ZIP Packaging QA Capability Pack Skill

Expert Agent Skills ZIP packaging QA capability pack applying documented skills directory layout, SKILL.md frontmatter checks, archive validation, and install smoke tests from official skills and plugin packaging documentation.

by kiannidev·added 2026-06-16·
Claude CodeCodexWindsurfGeminiCursorCLI
HarnessClaude CodeCodexWindsurfGeminiCursorCLI
Level:expertType:capability-packVerified:validated
Review first — review before installing

Open the source and read safety notes before installing.

Safety notes

  • ZIP archives can bundle scripts and hooks—scan for outbound network calls before distribution.
  • Do not publish archives containing secrets, tokens, or personal machine paths.
  • Treat installable skill zips as supply-chain artifacts requiring checksum publication.

Privacy notes

  • Example prompts in skills may contain internal codenames—redact before public release.
  • QA logs may capture file paths from developer machines—sanitize shared reports.

Prerequisites

  • Skill source tree or ZIP archive ready for QA.
  • Claude Code profile to test local skill discovery.
  • Checklist owner before publishing to marketplace or HeyClaude.

Schema details

Install type
package
Reading time
8 min
Difficulty score
68
Troubleshooting
Yes
Breaking changes
No
Source repository stats
Scope
Source repo
Package metadata
Skill and platform metadata
Skill type
capability-pack
Skill level
expert
Verification
validated
Verified at
2026-06-16
Retrieval sources
https://code.claude.com/docs/en/skillshttps://code.claude.com/docs/en/pluginshttps://github.com/anthropics/claude-codehttps://developers.google.com/search/docs/fundamentals/creating-helpful-content
Tested platforms
Claude CodeClaudeCursorGeneric AGENTS
PlatformSupportInstall path
claude-codeNative.claude/skills/<skill-name>/SKILL.md
codexNative.agents/skills/<skill-name>/SKILL.md
windsurfNative.windsurf/skills/<skill-name>/SKILL.md
geminiNative.gemini/skills/<skill-name>/SKILL.md or .agents/skills/<skill-name>/SKILL.md
cursorAdapter.cursor/rules/<skill-name>.mdc
cliManualAGENTS.md or tool-specific context file
Full copyable content
# Trigger
"Apply the agent skills ZIP packaging QA capability pack."

# Required output
1) Archive layout and manifest findings
2) Frontmatter and metadata gaps
3) Install smoke test results
4) Security and secret scan summary
5) Release readiness verdict

About this resource

Knowledge Freshness

Grounded in official Claude Code skills and plugin packaging documentation verified on 2026-06-16.

Retrieval Sources

Source Verification Notes

Verified on 2026-06-16:

  • Skills documentation describes skill directories, SKILL.md metadata, and discovery paths in Claude Code.
  • Plugin docs cover packaging layouts for distributing skills, hooks, and commands in archives.
  • Teams validate archives with test installs before sharing internally or submitting to directories.
  • Frontmatter fields should match HeyClaude category expectations when submitting to awesome-claude.
  • Checksums or signed releases reduce tampering risk for shared ZIP distributions.

Scope Note

Community QA workflow applying documented packaging steps—not an official Anthropic QA product. Complements packaging-claude-code-plugins-as-zip-archives guide with skill-specific review matrices.

Core Workflow

  1. Verify archive root contains expected skill folder and SKILL.md or .mdx layout per docs.
  2. Validate frontmatter: name, description, allowed-tools hints, and retrieval sources when applicable.
  3. Scan for secrets, absolute paths, and unexpected binaries.
  4. Test install or symlink into Claude Code skills path; invoke skill once in staging.
  5. Record checksum, version, and reviewer sign-off before release.

Capability Scope

  • Layout and manifest validation.
  • Metadata completeness review.
  • Secret and path hygiene scan.
  • Install smoke test checklist.
  • Release readiness verdict with rollback notes.

Production Rules

  • Block release when secrets or unpinned remote install scripts are detected.
  • Require human sign-off before publishing installable zips to shared marketplaces.
  • Document checksum and source commit in release notes.
  • Redact internal paths from QA reports shared externally.

Review Matrix

Finding Action
Missing SKILL.md Block release
Secret in tree Rotate and remove before repack
Install fails Fix layout before distribution
Metadata drift Align to skills doc before submit

Output Contract

  1. Layout findings.
  2. Metadata gaps.
  3. Smoke test results.
  4. Security scan summary.
  5. Release readiness verdict.

Troubleshooting

Issue: Skill not discovered after install Fix: Confirm path matches documented skills directory and reload Claude Code session.

Issue: ZIP too large for email distribution Fix: Host on git release with checksum instead of ad-hoc file shares.

Duplicate Check

Complements packaging-claude-code-plugins-as-zip-archives (plugin zips) and HeyClaude validation scripts. No skills capability pack focuses on ZIP QA matrices for Agent Skills.

Editorial Disclosure

Independent entry by kiannidev from public documentation.

#skills#packaging#zip#qa#capability-pack

Source citations

Add this badge to your README

Show that Agent Skills ZIP Packaging QA Capability Pack Skill is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.

Listed on HeyClaude
[![Listed on HeyClaude](https://heyclau.de/badge/skills/agent-skills-zip-packaging-qa-capability-pack.svg)](https://heyclau.de/entry/skills/agent-skills-zip-packaging-qa-capability-pack)

How it compares

Agent Skills ZIP Packaging QA Capability Pack Skill side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.

FieldAgent Skills ZIP Packaging QA Capability Pack Skill

Expert Agent Skills ZIP packaging QA capability pack applying documented skills directory layout, SKILL.md frontmatter checks, archive validation, and install smoke tests from official skills and plugin packaging documentation.

Open dossier 		Claude Code Plugin Marketplace Authoring Capability Pack Skill

Expert plugin marketplace authoring capability pack applying documented marketplace.json catalogs, /plugin marketplace add flows, private repo distribution, and supply-chain review from official plugin marketplace documentation.

Open dossier 		Agent Skills Cross-Platform Adapter Capability Pack Skill

Expert agent skills cross-platform adapter capability pack for porting Claude Code SKILL.md workflows to Codex, Cursor, Windsurf, and Generic AGENTS runbooks while preserving scope, safety notes, and source-backed contracts.

Open dossier 		Agent Skills Enterprise Provisioning Capability Pack Skill

Expert agent skills enterprise provisioning capability pack for rolling out Claude Code skills across Claude for Enterprise with scope controls, admin policy alignment, user-only versus model-invoked skills, and audit-ready docs.

Open dossier
Trust
Install riskReview firstReview firstReview firstReview first
Notes Safety ✓ Privacy ✓ Safety ✓ Privacy ✓ Safety ✓ Privacy ✓ Safety ✓ Privacy ✓
Categoryskillsskillsskillsskills
Sourcesource-backedsource-backedsource-backedsource-backed
Authorkiannidevkiannidevkiannidevkiannidev
Added2026-06-162026-06-162026-06-142026-06-14
Platforms
Claude CodeCodexWindsurfGeminiCursorCLI
Claude CodeCodexWindsurfGeminiCursorCLI
Claude CodeCodexWindsurfGeminiCursorCLI
Claude CodeCodexWindsurfGeminiCursorCLI
Source repo————
Safety notes✓ZIP archives can bundle scripts and hooks—scan for outbound network calls before distribution. Do not publish archives containing secrets, tokens, or personal machine paths. Treat installable skill zips as supply-chain artifacts requiring checksum publication.✓Autonomous runs can execute tools without mid-run user input—scope paths and connectors first. Do not enable destructive automation without explicit approval gates. Review outputs as draft until a human validates evidence.✓Not every Claude Code command or MCP tool exists on other platforms; do not imply feature parity without verification. Adapted skills must preserve destructive-action warnings and approval requirements from the source workflow. Cross-platform copies should not strip `safetyNotes` or `privacyNotes` to save space. Platform-specific secret handling differs; never copy Claude Code env patterns blindly into other hosts. This skill produces adaptation plans; it must not run destructive commands on the target platform without explicit approval.✓Model-invoked skills load descriptions at session start and can trigger side effects if not marked user-only or restricted with allowed-tools. Enterprise-wide skill rollout amplifies any destructive workflow across all provisioned users. Skills referencing external MCP servers inherit third-party data-handling risk outside Anthropic policies. Admin-managed allowlists and enterprise settings may block certain skill locations or plugin sources. This skill recommends rollout phases; it must not deploy skills org-wide without explicit admin approval.
Privacy notes✓Example prompts in skills may contain internal codenames—redact before public release. QA logs may capture file paths from developer machines—sanitize shared reports.✓Run output may contain proprietary code and credentials. Summaries for external channels require redaction.✓Adaptation reviews may expose internal runbooks, customer workflows, and repository conventions embedded in source skills. Generic AGENTS exports shared across teams can leak path patterns and tool names if pasted into public issues. Public adaptation summaries should describe platform gaps and preserved boundaries, not full internal skill bodies.✓Enterprise skill inventories can reveal internal team workflows, compliance processes, and repository naming conventions. Skill descriptions loaded at startup may expose sensitive operational details to every session in scope. Rollout comms should describe approved skill categories and boundaries, not full internal SKILL.md contents.
Prerequisites
  • Skill source tree or ZIP archive ready for QA.
  • Claude Code profile to test local skill discovery.
  • Checklist owner before publishing to marketplace or HeyClaude.
  • Claude Code version and plan eligibility per official documentation.
  • Team policy for autonomous or shared automation workflows.
  • Staging environment for safe validation.
  • Human owner for production rollout approval.
  • The source Claude Code `SKILL.md` or HeyClaude capability pack to adapt.
  • The target platform or host (Codex, Cursor, Windsurf, Generic AGENTS, or mixed).
  • Knowledge of platform-specific skill, rule, or AGENTS.md conventions on the target host.
  • Redacted examples of commands, tools, or MCP dependencies the source skill assumes.
  • Claude for Enterprise or equivalent org-wide Claude Code deployment context.
  • Inventory of approved skills, plugins, or internal SKILL.md packages to provision.
  • Access to admin setup docs, enterprise policy constraints, and security review stakeholders.
  • Understanding of which repositories and teams will receive each skill scope.
Install————
Config————
Citations
ClaimUnclaimedUnclaimedUnclaimedUnclaimed

Signals

Loading live community signals…

More like this, weekly

A short, calm digest of reviewed Claude resources. Unsubscribe any time.