Real Skill packageSource verifiedClawHub registry

skill-author

Author, harden, and publish agent skills for ClawHub — write skills that conform to ClawHub conventions (frontmatter, structure, naming, versioning, licensing), run pre-publish hardening, and remediate clawhub.ai security-audit findings. Use when creating a skill for ClawHub, preparing a new version to publish, or when given a clawhub.ai/<owner>/<slug>/security-audit page.

Identity and source

Publisher attributionJnJnregistry owner unverified by skillvetai
Functional categoryAgent Engineering, Security & Governanceautomatically inferred · 72% rule confidence
Package forminstruction bundle6 recorded files
Canonical sourceClawHub registryclawhub:sunshinejnjn:skill-author
Open canonical source ↗

Platform declarations

These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.

OpenClawnative officialProvenance: registry distribution

Independent structural checks

These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.

Claude Codepasses structure
Checker 0.1.0 · agent-skills-2026-08-13+claude-code-docs-2026-08-13 · 9/20/2026.claude/skills/skill-author

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenAI Codexpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+codex-docs-2026-08-13 · 9/20/2026.agents/skills/skill-author

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenClawpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+openclaw-docs-2026-08-13 · 9/20/2026skills/skill-author

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

Installation and inspection

This command is recorded from the source ecosystem and resolves the registry's latest release. The fixed release shown on this page should be inspected before adoption.

clawhub install @sunshinejnjn/skill-author
clawhub inspect @sunshinejnjn/skill-author --version 1.1.0

Security evidence

SkillVetAI static result: no findings detected

This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.

Status
completed
Coverage
full text content
Files
6 / 6 inspected as text
Checked
9/20/2026, 4:09:55 PM
Scanner
0.1.3
Policy
1.0.3
2 inferred permission indicators
  • network access — automatically inferred
  • filesystem write — automatically inferred
3 dependency and API indicators
  • api: 10.71.253.215
  • api: api.github.com
  • api: clawhub.ai
External clawhub result: clean

This is registry-supplied evidence for the recorded release, not an independent SkillVetAI scan. Check the canonical source for the full report, scanner versions, scope, and current moderation state.

Evidence checked
9/20/2026, 2:01:58 PM
Release binding
Matches this record
  • vt: clean
  • skillspector: suspicious
  • llm: clean

Recorded files

The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.

Package content hashsha256:e680431dd6404d5a2ecf80349aea277130e9e6dd3f51c6f4d0fadb8f3257fac2
Show up to 6 recorded paths
  • README.md
  • references/audit-patterns.md
  • references/authoring-guide.md
  • references/publish-checklist.md
  • skill-card.md
  • SKILL.md

Source changelog

v1.1.0 (initial release, all-English): skill-author — Author, harden, and publish agent skills for ClawHub. Four capabilities: (1) AUTHOR — write ClawHub-conformant skills via references/authoring-guide.md (frontmatter field reference verified against CLI source, slug/naming rules incl. protected namespaces, versioning & tags, file layout & allowed text extensions, license model, description writing, SKILL.md body conventions, security by design); (2) HARBARDEN -> Harden — 10-point pre-publish checklist (registry diff, dead links, doc/code consistency, secrets, artifacts, LICENSE/VERSION); (3) Remediate — 9 audit patterns -> fixes in references/audit-patterns.md, distilled from two real cases (epic-novel-writer 1.2.1 command injection; image-with-comfyui 1.7.1 data egress + supply chain), incl. false-positive handling; (4) Publish & verify — publish with itemized changelog, poll through…