skill-authorAuthor, 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.
Install via ClawdBot CLI:
clawdbot install sunshinejnjn/skill-authorGrade Limited — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Accesses sensitive credential files or environment variables
/etc/passwdPotentially destructive shell commands in tool definitions
rm -rf /Calls external URL not in known-safe list
https://clawhub.ai/sunshinejnjn/skill-authorUses known external API (expected, informational)
api.github.comGenerated Sep 29, 2026
A developer has built a utility they want to share on ClawHub but has never navigated the platform's frontmatter, naming, and licensing conventions. They use skill-author to scaffold the folder, generate conforming frontmatter, and run the pre-publish hardening checklist before their first `clawhub publish`.
A maintainer receives a clawhub.ai security-audit URL with hard findings flagged at specific file:line locations. Using skill-author's remediation workflow, they classify findings into hard vs. soft, apply the matching audit-pattern fixes, and re-verify compilation and tests before republishing.
A platform team standardizes how all employees author agent skills for an internal ClawHub mirror. They adopt skill-author to enforce consistent description-as-triggers phrasing, pinned dependency versions, and loopback-default endpoints across dozens of team-authored skills.
An open-source maintainer is preparing a semver bump for a widely-used skill and needs to confirm the new release is a deliberate superset of the registry version. They use skill-author to diff local vs. registry, verify LICENSE and VERSION alignment, and poll the moderation queue until the publish flips to Latest.
A contributor drafts a skill with a coding assistant and suspects it may contain command injection in shell examples, unpinned git clones, or lingering build artifacts. They run skill-author's security-by-design self-check and authoring guide review to catch issues before the static pattern scan and LLM review layers flag them.
Individual maintainers use skill-author to produce polished, audit-clean skills that attract stars, contributors, and sponsorship. Reliable, well-documented skills build reputation that converts into GitHub Sponsors, consulting leads, or paid premium variants.
Consultancies offer ClawHub skill authoring, hardening, and audit remediation as a billable service for clients who lack internal expertise. skill-author's structured workflows reduce delivery time and make quality outcomes repeatable across client engagements.
Platform engineering teams deploy skill-author as an internal standard to keep a private ClawHub-compatible registry compliant with corporate security policies. This supports the broader sale of the company's AI platform or developer productivity suite.
💬 Integration Tip
Pair skill-author with the ClawHub CLI (`npm i -g clawhub`) and grant Read/Write/Edit/Exec tools so the agent can scaffold, verify, and publish without manual file juggling. Fetch audit pages with web_fetch and run the publish checklist as a gate in CI before invoking `clawhub publish`.
Scored Sep 29, 2026
Audited Sep 29, 2026 · audit v1.0
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope,...
Security scanner for AI agent skills. 9 built-in detection signatures. Identifies secrets, unsafe execution patterns, and prompt injection. Sub-50ms results.
Wallet anti-theft guard. One-click scan for high-risk wallet approvals to protect user assets. Use when a user asks for a wallet security check, wallet healt...
Comprehensive security audit for an agent's full skill stack. Chains scanner, differ, trust-verifier, and health-monitor into a single assessment with priori...
GEO Audit — AI Search Visibility Checker for ChatGPT, Perplexity, Claude & Gemini. 29-point GEO readiness checklist: robots.txt AI crawler access, Index...
Senior SecOps engineer skill for application security, vulnerability management, compliance verification, and secure development practices. Runs SAST/DAST sc...