Real Skill packageSource verifiedClawHub registry

lintlang

Agent instruction quality audit — lint SKILL.md, CLAUDE.md, AGENTS.md, GEMINI.md files, tool definitions, system prompts, and agent configs with the deterministic LintLang CLI. Runs on request when the user names a file. Catches ambiguous tool descriptions, missing stop conditions, schema/description mismatches, and prompts embedded in Python. Zero-LLM static analysis; no model calls and no network calls during a scan. Not for general code review or prose documentation.

Identity and source

Publisher attributionRoli Boschregistry owner unverified by skillvetai
Functional categorySearch, Research & Knowledgeautomatically inferred · 63% rule confidence
Package forminstruction bundle3 recorded files
Canonical sourceClawHub registryclawhub:roli-lpci:package
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 · 10/3/2026.claude/skills/lintlang

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 · 10/3/2026.agents/skills/lintlang

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 · 10/3/2026skills/lintlang

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 @roli-lpci/package
clawhub inspect @roli-lpci/package --version 1.0.0

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
3 / 3 inspected as text
Checked
10/3/2026, 5:16:15 AM
Scanner
0.1.3
Policy
1.0.3
2 inferred permission indicators
  • network access — automatically inferred
  • filesystem write — automatically inferred
2 dependency and API indicators
  • api: clawhub.ai
  • api: github.com
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
10/2/2026, 8:33:23 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 hashsha256:40c63ed139965a9ad32991d45352999d9f0f092b544fa6de727df78e4678971d
Show up to 3 recorded paths
  • PUBLISH-NOTES.md
  • skill-card.md
  • SKILL.md

Source changelog

- Update to version 1.1.0 with expanded audit instructions and detailed usage guidance. - Clarifies intended use: lints natural-language agent instructions (SKILL.md, CLAUDE.md, AGENTS.md, GEMINI.md, prompts, tool definitions, agent configs) for structure and clarity. - Enforces zero-LLM/static analysis: no model calls, no network access during scan. - Adds precise runner selection: prefers installed lintlang CLI (v0.8.2+), falls back to uvx for pinning, or relays install command. - Clearly separates what the tool is for (agent instruction audit) and is not for (code review, general linting, or agent safety verification). - Outputs actionable, severity-ranked findings without rewriting user files or guessing targets.